CN118784810A - Image processing method, device, storage medium and chip - Google Patents

Abstract

The present disclosure relates to an image processing method, device, storage medium and chip, the method comprising: in response to an acquisition instruction of a first image, acquiring a first image and multi-directional environmental information, the multi-directional environmental information comprising environmental information respectively detected by a plurality of color temperature sensors, each of which has a different detection direction; determining a confidence value that a scene corresponding to a target color temperature sensor is a target scene according to the multi-directional environmental information, the detection direction of the target color temperature sensor corresponding to the first image; determining a target white balance point according to the multi-directional environmental information when the confidence value is greater than a preset confidence threshold; processing the first image according to the target white balance point to obtain a target image. The white balance point corresponding to the current scene can be accurately determined, and the problem of misjudgment of the white balance color temperature of the target scene can be solved.

Description

Image processing method, device, storage medium and chip

Technical Field

The present disclosure relates to the field of image processing, and in particular to an image processing method, device, storage medium and chip.

Background Art

In the related technologies, most of them use unidirectional multi-channel color temperature sensors to assist in white balance calculation. However, due to the limited detection field of view of the color temperature sensor, when faced with a large area of pure color or misleading color scenes, it is often impossible to effectively calculate the true color temperature of the scene.

Summary of the invention

In order to overcome the problems existing in the related art, the present disclosure provides an image processing method, device, storage medium and chip.

According to a first aspect of an embodiment of the present disclosure, there is provided an image processing method, including:

In response to an instruction to acquire a first image, acquire the first image and multi-directional environmental information, wherein the multi-directional environmental information includes environmental information respectively detected by a plurality of color temperature sensors, and each of the color temperature sensors has a different detection direction;

Determining, according to the multi-directional environmental information, a confidence value that a scene corresponding to a target color temperature sensor is a target scene, wherein a detection direction of the target color temperature sensor corresponds to the first image;

In a case where it is determined that the confidence value is greater than a preset confidence threshold, determining a target white balance point according to the multi-directional environmental information;

The first image is processed according to the target white balance point to obtain a target image.

According to a second aspect of an embodiment of the present disclosure, there is provided an image processing apparatus, including:

an acquisition module, configured to acquire the first image and multi-directional environmental information in response to an acquisition instruction of the first image, wherein the multi-directional environmental information includes environmental information respectively detected by a plurality of color temperature sensors, each of which has a different detection direction;

A first determination module is configured to determine, based on the multi-directional environmental information, a confidence value that a scene corresponding to a target color temperature sensor is a target scene, wherein a detection direction of the target color temperature sensor corresponds to the first image;

A second determination module is configured to determine a target white balance point according to the multi-directional environment information when it is determined that the confidence value is greater than a preset confidence threshold;

The fourth determination module is configured to process the first image according to the target white balance point to obtain a target image.

According to a third aspect of an embodiment of the present disclosure, there is provided an image processing apparatus, including:

processor;

a memory for storing processor-executable instructions;

Wherein, the processor is configured to:

In response to an instruction to acquire a first image, acquire the first image and multi-directional environmental information, wherein the multi-directional environmental information includes environmental information respectively detected by a plurality of color temperature sensors, and each of the color temperature sensors has a different detection direction;

Determining, according to the multi-directional environmental information, a confidence value that a scene corresponding to a target color temperature sensor is a target scene, wherein a detection direction of the target color temperature sensor corresponds to the first image;

In a case where it is determined that the confidence value is greater than a preset confidence threshold, determining a target white balance point according to the multi-directional environmental information;

The first image is processed according to the target white balance point to obtain a target image.

According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the program instructions are executed by a processor, the steps of any one of the methods described in the first aspect of the present disclosure are implemented.

According to a fifth aspect of an embodiment of the present disclosure, a chip is provided, comprising a processor and an interface; the processor is used to read instructions to execute any one of the methods described in the first aspect of the present disclosure.

The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by acquiring environmental information detected by multiple color temperature sensors, namely, multi-directional environmental information, and based on the confidence of the target scene corresponding to the target color temperature sensor of the multi-directional environmental information, further determining whether to trigger the multi-directional white balance based on the confidence, and after determining that the multi-directional white balance is triggered, determining the white balance point based on the environmental information detected by the multiple color temperature sensors and processing the image, the white balance point corresponding to the current scene can be accurately determined, and the problem of misjudgment of the white balance color temperature of a large area of pure color and misleading color light source scenes, resulting in poor image processing effects, can be avoided.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

Fig. 1 is a flow chart showing an image processing method according to an exemplary embodiment.

Fig. 2 is a schematic diagram showing a first mapping relationship table according to an exemplary embodiment.

Fig. 3 is a schematic diagram showing a preset signal curve according to an exemplary embodiment.

Fig. 4 is a schematic diagram showing a mapping relationship between a fifth weight and a second deviation value according to an exemplary embodiment.

Fig. 5 is a flow chart showing an image processing method according to an exemplary embodiment.

Fig. 6 is a block diagram showing an image processing apparatus according to an exemplary embodiment.

Fig. 7 is a block diagram showing a device for image processing according to an exemplary embodiment.

DETAILED DESCRIPTION

Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

FIG1 is a flowchart of an image processing method according to an exemplary embodiment. The method may be used in a terminal, such as a photographing system of the terminal, or may also be used in a vehicle-mounted camera, a monitoring system, etc. The executor of the method may be, for example, a processor or any other electronic device with information processing capabilities. As shown in FIG1 , the method includes the following steps.

S101. In response to an instruction to obtain a first image, obtain the first image and multi-directional environmental information, where the multi-directional environmental information includes environmental information respectively detected by a plurality of color temperature sensors, each of which has a different detection direction.

The instruction for acquiring the first image may be, for example, an instruction generated by a user's operation, such as pressing a capture button or a user's voice command for capturing an image, etc. This is not limited in the embodiments of the present disclosure.

For example, the multiple color temperature sensors may include a first color temperature sensor and a second color temperature sensor, for example, they may be a front color temperature sensor and a rear color temperature sensor of a mobile phone. Specifically, the first color temperature sensor and the second color temperature sensor may be, for example, front and rear bidirectional multi-channel color temperature sensors. Alternatively, the first color temperature sensor and the second color temperature sensor may also be two monitoring devices located at the same position and shooting at different angles. The monitoring device may include a color temperature sensor, and the shooting angle of the monitoring device is the same as or close to the detection angle of the color temperature sensor therein. Alternatively, the multiple color temperature sensors may also include more color temperature sensors, and the present disclosure does not limit the number of color temperature sensors.

In some embodiments, the multi-directional environmental information includes at least one or more of the following detected by multiple color temperature sensors: environmental correlated color temperature (CCT), luminance (Lv) information, infrared information, and environmental white point. That is, the environmental information may include one or more of the following: environmental correlated color temperature, luminance information, infrared information, and environmental white point.

The environment-correlated color temperature is the correlated color temperature of the current environment detected by the corresponding color temperature sensor, the infrared information may be, for example, an infrared radiation ratio (IRRATIO), and the environment white point may include, for example, two parameters, R/G and B/G, corresponding to the current environment. It is understandable that each color temperature sensor may detect at least one of the environment-correlated color temperature, brightness information, infrared information, and environment white point. The specific information included in the environment information may be determined according to the capability of the color temperature sensor, and the present disclosure does not limit this.

S102: Determine, according to the multi-directional environmental information, a confidence value that a scene corresponding to a target color temperature sensor is a target scene, wherein a detection direction of the target color temperature sensor corresponds to the first image.

It is worth noting that the shooting direction of the first image may correspond to the detection direction of at least one color temperature sensor among the multiple color temperature sensors. For example, if the shooting direction of the shooting device of the first image is the same as the detection direction of the first color temperature sensor, or if the deviation between the shooting direction and the detection direction is less than a preset threshold, it can be determined that the detection direction of the first color temperature sensor corresponds to the first image.

For example, if the shooting direction of the camera that shoots the first image is the same as the detection direction of the first color temperature sensor, it can be determined that the target color temperature sensor is the first sensor, that is, the detection direction of the first color temperature sensor corresponds to the first image.

Optionally, the target scene may include, for example, a pure color scene and/or a mixed color scene, or may be other scenes, which are not limited in the embodiments of the present disclosure.

Among them, a pure color scene may, for example, refer to a scene in which an area with the same color temperature in a picture captured by a color temperature sensor is larger than a preset threshold, a mixed color scene may, for example, refer to a scene in which an area with similar color temperature in a picture captured by a color temperature sensor is larger than a preset threshold, and similar color temperature may refer to a scene in which the color temperature difference between two pixels is smaller than a preset difference threshold.

In some optional embodiments, determining, in step S102, according to the multi-directional environmental information, a confidence value that the scene corresponding to the target color temperature sensor is the target scene includes:

At least one confidence parameter is determined according to the multi-directional environmental information, and different confidence parameters are determined according to different sub-information in the multi-directional environmental information; the confidence parameters are weighted according to the preset confidence weights corresponding to each of the confidence parameters to obtain the confidence value.

Specifically, the confidence parameter may be determined based on the difference between the environmental information detected by the target color temperature sensor and the environmental information detected by other color temperature sensors in the multi-directional environmental information, or may be determined based on the temporal continuity of the environmental information detected by the target color temperature sensor.

For example, the confidence parameters may include C0, C1, C2, C3, C4, and C5, and different confidence parameters may characterize the confidence that the scene corresponding to the multi-directional environmental information in different dimensions is the target scene. For example, different confidence parameters may be determined based on different information in the multi-directional environmental information.

S103: When it is determined that the confidence value is greater than a preset confidence threshold, determine a target white balance point according to the multi-directional environment information.

Among them, the preset confidence threshold can be calibrated by those skilled in the art based on historical experience or experimental results, and the embodiments of the present disclosure do not limit its specific value.

For example, the multiple color temperature sensors may include a first color temperature sensor and a second color temperature sensor, and the confidence parameters include C0, C1, C2, C3, C4, and C5. The confidence weights corresponding to each confidence parameter may be T0, T1, T2, T3, T4, and T5, respectively. Then, whether to trigger multi-directional white balance may be determined based on the following formula:

T0*C0+T1*C1+T2*C2+T3*C3+T4*C4+T5*C5>=Double CS Trigger Threshold.

The Double CS Trigger Threshold may be a preset confidence threshold for triggering multi-directional white balance. When a weighted result calculated based on the confidence parameter and the confidence weight corresponding to each confidence parameter is greater than the preset trigger threshold, it may be determined that the bidirectional white balance is triggered.

In some embodiments, a white balance point may be determined based on the environmental information detected by the first color temperature sensor in the multi-directional environmental information, another white balance point may be determined based on the environmental information detected by the second color temperature sensor, and then a target white balance point may be determined based on the two white balance points.

In other embodiments, other methods may be used, such as determining the target white balance point based on multi-directional environmental information and integrating environmental information detected by each color temperature sensor. Some possible implementations of the present disclosure will be described in detail below and will not be repeated here.

S104: Process the first image according to the target white balance point to obtain a target image.

Optionally, after obtaining the target image, the target image can be stored or displayed. For example, if the acquisition instruction of the first image is an acquisition instruction corresponding to a user shooting with a rear camera of a mobile phone, the first image initially acquired by the rear camera can be processed to obtain the target image, and the target image can be displayed on the mobile phone screen and stored in the storage device of the mobile phone.

In the embodiments of the present disclosure, by acquiring environmental information detected by multiple color temperature sensors, i.e., multi-directional environmental information, and based on the confidence of the target color temperature sensor corresponding to the target scene of the multi-directional environmental information, further determining whether to trigger the multi-directional white balance based on the confidence, and after determining to trigger the multi-directional white balance, determining the white balance point based on the environmental information detected by the multiple color temperature sensors and processing the image, the white balance point corresponding to the current scene can be accurately determined, and the problem of misjudgment of the white balance color temperature of a large area of pure color and misleading color light source scenes, resulting in poor image processing effects, can be avoided. In some embodiments, determining the target white balance point based on the multi-directional environmental information includes:

Based on the confidence parameter, determining an output weight corresponding to each of the color temperature sensors;

Determining environmental auxiliary information according to the output weight and the multi-directional environmental information;

A target white balance point is determined according to the environmental auxiliary information.

In some possible implementations, a Pareto optimal frontier multi-objective search strategy may be used to determine the output weights corresponding to each color temperature sensor.

It is worth noting that since at least one confidence parameter is needed for sub-target search, if only a single-target search algorithm is used, linear weighting is required between different sub-targets. Therefore, it is difficult to set a weight vector that can meet the trade-off requirements for environmental information output in different modes. Therefore, a multi-target search algorithm can be used here to avoid the tedious setting of weights for different sub-targets and the trouble of recalculating confidence parameters after changing target weights, thereby obtaining more reasonable output weights of different color temperature sensors.

After the output weights corresponding to the color temperature sensors are determined, the environmental information detected by the color temperature sensors can be weighted and summed in combination with the output weights to obtain the environmental auxiliary information, and then the target white balance point can be determined based on the environmental auxiliary information.

Optionally, the environmental auxiliary information may include, for example, one or more of the environmental correlated color temperature, brightness information, infrared information, and environmental white point weighted according to the environmental information. For example, the environmental auxiliary information may include one or more of the auxiliary environmental information, auxiliary brightness information, auxiliary infrared information, and auxiliary environmental white point. The auxiliary correlated color temperature, auxiliary infrared information, auxiliary brightness information, and auxiliary environmental white point are obtained by weighting the correlated color temperature, infrared information, brightness information, and environmental white point with corresponding weighting coefficients, respectively. For example, the environmental auxiliary information may be New (CCT, LV, IRRATIO, R/G, B/G). It is to be understood that various information in the above environmental auxiliary information may be used to assist in determining the target white balance point, and the embodiments of the present disclosure do not limit their names.

Specifically, what kind of information the environmental auxiliary information includes may be determined based on information detected by each color temperature sensor. For example, if each color temperature sensor cannot detect brightness information, the environmental auxiliary information may not include the auxiliary brightness information.

By adopting the above scheme, the output weights corresponding to each color temperature sensor can be determined based on the confidence parameters, and the environmental auxiliary information can be obtained more accurately based on the output weights, so that the target white balance point can be determined more accurately in combination with the environmental information collected by each color temperature sensor, thereby further improving the accuracy of the target white balance point.

In some optional embodiments, determining a target white balance point according to the environmental auxiliary information includes:

Determine at least one white balance color temperature detection weight according to the environmental auxiliary information, where different white balance color temperature detection weights are determined according to different sub-information in the environmental auxiliary information;

The target white balance point is determined according to the white balance color temperature detection weight.

Optionally, different white balance color temperature detection weights may represent the confidence that the scene corresponding to the environmental auxiliary information in different dimensions is the target scene. For example, different white balance color temperature detection weights may be determined based on different information in the environmental auxiliary information.

By adopting the above scheme, the confidence that the scene corresponding to the environmental auxiliary information of different dimensions is the target scene is determined based on the weighted environmental auxiliary information, that is, the white balance color temperature detection weights of different dimensions, and the target white balance point is determined based on the white balance color temperature detection weights of different dimensions. This scheme can comprehensively integrate different information in the environmental auxiliary information and the possible impact of different information on the target white balance point, so as to more accurately determine the target white balance point, and can further avoid the problem of misjudgment of white balance color temperature in scenes with large areas of pure color and misleading color light sources.

In some optional embodiments, determining a target white balance point according to the white balance color temperature detection weight includes:

Determine a first white balance point corresponding to each of the white balance color temperature detection weights;

Determining an interpolation rate corresponding to each of the white balance color temperature detection weights;

The target white balance point is determined according to the first white balance point corresponding to each of the white balance color temperature detection weights and the interpolation rate corresponding to each of the white balance color temperature detection weights.

It is worth noting that different white balance color detection weights may correspond to different information in the environmental auxiliary information. Different first white balance points may be determined based on different information in the environmental auxiliary information. The first white balance point corresponding to each white balance color temperature detection weight may specifically refer to a white balance point determined based on the information in the environmental auxiliary information corresponding to the white balance color temperature detection weight.

For example, if a white balance color detection weight is based on the auxiliary correlated color temperature and the auxiliary infrared information, then the first white balance point corresponding to the white balance color detection weight may be a first white balance point determined based on the auxiliary correlated color temperature and the auxiliary infrared information.

In some optional embodiments, the interpolation rate corresponding to each white balance color temperature detection weight may be pre-calibrated. Determining the interpolation rate corresponding to each white balance color temperature detection weight may be to obtain the interpolation rate corresponding to each white balance color temperature detection weight from a storage device.

In some other optional embodiments, determining the interpolation rate corresponding to each of the white balance color temperature detection weights includes:

Determine a second white balance point corresponding to the environmental information detected by the target color temperature sensor; determine the distance between the first white balance point corresponding to each of the white balance color temperature detection weights and the second white balance point; and determine an interpolation rate corresponding to each of the white balance color temperature detection weights based on the distance between the first white balance point corresponding to each of the white balance color temperature detection weights and the second white balance point.

Wherein, if the target white balance point is used to process the image corresponding to the detection direction of the first color temperature sensor, the second white balance point may be determined based on the environmental information collected by the first color temperature sensor, for example. If the target white balance point is used to process the image corresponding to the detection direction of the second color temperature sensor, the second white balance point may be determined based on the environmental information collected by the second color temperature sensor, for example.

Optionally, the distance between the first white balance point and the second white balance point may be determined by white balance coordinates corresponding to the first white balance point and the second white balance point, respectively. For example, a coordinate system may be constructed, the horizontal axis of the coordinate system may be, for example, R/G, and the vertical axis may be, for example, B/G, and then the distance between the two white balance points may be calculated based on the coordinates of the two white balance points.

It should be explained that the second white balance point can be understood as an actual white balance point or a real white balance point.

By adopting the above scheme, by determining the first white balance point corresponding to each white balance color temperature detection weight and the distance between each first white balance point and the second white balance point, the interpolation rate corresponding to each white balance color temperature detection weight can be accurately determined based on the distance corresponding to each white balance color temperature detection weight.

In some embodiments, determining the interpolation rate corresponding to each white balance color temperature detection weight according to the distance between the first white balance point and the second white balance point corresponding to each white balance color temperature detection weight includes:

Determining a distance weight corresponding to each of the white balance color temperature detection weights according to a distance between a first white balance point and the second white balance point corresponding to each of the white balance color temperature detection weights;

An interpolation rate corresponding to each white balance color temperature detection weight is determined according to each white balance color temperature detection weight, a distance corresponding to each white balance color temperature detection weight, and a distance weight corresponding to each white balance color temperature detection weight.

Among them, the distance and the distance weight corresponding to the distance can be determined by looking up a table. For example, when the distance is 0, the distance weight corresponding to the distance can be 1. When the distance is greater than or equal to a preset distance threshold, the distance weight corresponding to the distance can be 0. When the distance is less than the preset threshold and greater than zero, the distance and the distance weight corresponding to the distance can be negatively correlated.

By adopting the above scheme, by determining the distance weight corresponding to each distance, and combining the white balance color temperature detection weight and the corresponding distance, the interpolation rate corresponding to each white balance color temperature detection weight can be accurately determined, and then the target white balance point can be accurately determined based on the interpolation rate, which effectively improves the accuracy of the target white balance point and avoids the problem of misjudgment of white balance color temperature in scenes with large areas of pure color and misleading color light sources.

Optionally, determining an interpolation rate corresponding to each white balance color temperature detection weight according to each white balance color temperature detection weight, a distance corresponding to each white balance color temperature detection weight, and a distance weight corresponding to each white balance color temperature detection weight includes:

Determine the product of each white balance color temperature detection weight, the corresponding distance, and the corresponding distance weight, to obtain an interpolation parameter corresponding to each white balance detection parameter;

The interpolation rate corresponding to each white balance color temperature detection weight is determined according to the interpolation parameter corresponding to each white balance color temperature detection weight and the sum of the difference parameters corresponding to all white balance color temperature detection weights.

Optionally, determining an interpolation rate corresponding to each white balance color temperature detection weight according to each white balance color temperature detection weight, a distance corresponding to each white balance color temperature detection weight, and a distance weight corresponding to each white balance color temperature detection weight includes:

The interpolation rate corresponding to each white balance color temperature detection weight is determined according to the following formula:

Among them, Blend_Ratio _j represents the interpolation rate corresponding to the j-th white balance color temperature detection weight, Dist _j represents the distance between the j-th white balance color temperature detection weight and the second white balance point, Conf _j represents the distance weight corresponding to the j-th white balance color temperature detection weight, and P _j represents the j-th white balance color temperature detection weight; Dist _i represents the distance between the ith white balance color temperature detection weight and the second white balance point, Conf _i represents the distance weight corresponding to the ith white balance color temperature detection weight, _Pi represents the ith white balance color temperature detection weight, and n represents the number of white balance color temperature detection weights minus one.

It is understandable that j can be any natural number less than or equal to n. For example, the at least one white balance color temperature detection weight can include five white balance color temperature detection weights determined based on different information in the environmental auxiliary information, such as P0, P1, P2, P3, and P4. At this time, n can be 4, and j can be any value of 0, 1, 2, 3, and 4.

By adopting the above scheme, the proportion of each white balance color temperature detection weight in the overall weight can be accurately determined, and then the interpolation rate corresponding to each white balance color temperature detection weight can be more accurately determined based on the proportion of each white balance color temperature detection weight in the overall weight, and then the target white balance point can be determined more accurately.

Optionally, determining the target white balance point according to the first white balance point corresponding to each of the white balance color temperature detection weights and the interpolation rate corresponding to each of the white balance color temperature detection weights includes:

The target white balance point is determined according to the following formula:

Among them, FinalR/G_B/G represents the target white balance point, Blend_Ratio _j represents the interpolation rate corresponding to the j-th white balance color temperature detection weight, _PiR /G_B/G represents the first white balance point corresponding to the j-th white balance color temperature detection weight, and n represents the number of white balance color temperature detection weights.

For example, the at least one white balance color temperature detection weight may include five white balance color temperature detection weights determined based on different information in the environmental auxiliary information, such as P0, P1, P2, P3, and P4. In this case, n may be 4, and j may be any value of 0, 1, 2, 3, and 4.

By adopting the above scheme, by determining the interpolation rate corresponding to each white balance color temperature detection weight and the first white balance point corresponding to each white balance color temperature detection weight, the white balance points corresponding to each white balance color temperature detection weight can be accurately combined based on the interpolation rate, and the target white balance point combined with different information of the multi-directional color temperature sensor can be accurately obtained, thereby effectively improving the accuracy of the target white balance point, and effectively avoiding the problem of white balance color temperature misjudgment in scenes with large areas of pure color and misleading color light sources.

In some embodiments, determining at least one white balance color temperature detection weight according to the environmental auxiliary information includes:

According to the first mapping relationship table, the first weights corresponding to the auxiliary correlated color temperature and the auxiliary infrared information are determined; the first mapping relationship table is determined according to the matching relationship between the correlated color temperature and the infrared information and the target scene.

It is worth noting that the correlated color temperature and infrared information satisfy a certain matching relationship. For example, low color temperature scenes are usually accompanied by lower IRRATIO, while high color temperature scenes correspond to higher IRRATIO. In other words, when the correlated color temperature and infrared information match highly, it can be said that the scene corresponding to the environmental auxiliary information is less likely to be the target scene. When the correlated color temperature and infrared information match less, it can be said that the scene corresponding to the environmental auxiliary information is more likely to be the target scene.

For example, referring to the schematic diagram of the first mapping relationship table shown in FIG2, the first mapping relationship table may be as shown in FIG2, when the auxiliary correlated color temperature CCT is low and the auxiliary infrared information IRRATIO is also low, the value of the first weight may be in the high weight interval, that is, the value of P0 may be in High P0 Area1; when the auxiliary correlated color temperature CCT is high and the auxiliary infrared information IRRATIO is also high, the value of the first weight may be in the high weight interval, that is, the value of P0 may be in High P0 Area2; when the auxiliary correlated color temperature CCT is high and the auxiliary infrared information IRRATIO is low, the value of the first weight may be in the low weight interval, that is, the value of P0 may be in Low P0 Area1; when the auxiliary correlated color temperature CCT is low and the auxiliary infrared information IRRATIO is high, the value of the first weight may be in the low weight interval, that is, the value of P0 may be in Low P0 Area2. Among them, the specific size of the first weight P0 corresponding to different auxiliary correlated color temperatures and auxiliary infrared information can be calibrated according to actual conditions, and the embodiments of the present disclosure are not limited to this.

By adopting the above scheme, by predetermining the first mapping relationship table, the first weight corresponding to the auxiliary correlated color temperature and the auxiliary infrared information can be effectively determined, thereby obtaining a white balance color temperature detection weight that can reliably characterize the confidence that the scene corresponding to the auxiliary correlated color temperature in the environmental auxiliary information and the auxiliary infrared information is the target scene, and the target white balance point can be accurately determined based on the white balance color temperature detection weight to avoid the problem of white balance color temperature misjudgment in scenes with large areas of pure color and misleading color light sources.

In some embodiments, determining at least one white balance color temperature detection weight according to the environmental auxiliary information includes:

According to the second mapping relationship table, a second weight corresponding to the auxiliary correlated color temperature is determined; the second mapping relationship table is determined according to a matching relationship between the correlated color temperature and the target scene.

It is worth noting that, since there is a certain inverse relationship between the correlated color temperature and the pure color scene or the confused color scene, that is, the white balance color temperature detection value of the pure color or the confused color is often far away from the correlated color temperature of the actual output, based on this, the second mapping relationship table can be calibrated according to the matching relationship between the correlated color temperature and the target scene. For example, the white balance color temperature detection weight corresponding to the auxiliary correlated color temperature can be adjusted according to the matching relationship between the correlated color temperature and the target scene based on the second mapping relationship table. For example, the higher the auxiliary correlated color temperature, the lower the value of the second weight P1 can be, and the lower the auxiliary correlated color temperature, the higher the value of the second weight P1 can be.

By adopting the above scheme, by predetermining the second mapping relationship table, and based on the second mapping relationship table and the auxiliary correlated color temperature, a white balance color temperature detection weight that can reliably characterize the confidence that the scene corresponding to the auxiliary correlated color temperature in the environmental auxiliary information is the target scene can be determined, and the target white balance point can be accurately determined based on the white balance color temperature detection weight to avoid the problem of misjudgment of white balance color temperature in scenes with large areas of pure color and misleading color light sources.

In some embodiments, determining at least one white balance color temperature detection weight according to the environmental auxiliary information includes:

Obtain scene brightness information; determine a first deviation value between the target brightness information corresponding to the auxiliary brightness information and the scene brightness information according to a third mapping relationship table, wherein the third mapping relationship table is determined based on a matching relationship between the auxiliary brightness information and the target scene brightness; determine a third weight according to the first deviation value.

The scene brightness information may be collected by a brightness meter. For example, the third mapping relationship table may be as shown in Table 1:

Auxiliary brightness information LV Target brightness information Lux Auxiliary brightness information LV Target brightness information Lux 1 0.9 10 460.8 2 1.8 11 921.6 3 3.6 12 1843.2 4 7.2 13 3686.4 5 14.4 14 7372.7 6 28.8 15 14745.6 7 57.6 16 29491.2 8 115.2 17 58982.4 9 230.4 18 117964.8

Table 1

The unit corresponding to the auxiliary brightness information may be Lv, which may represent the luminous intensity per unit area, and the unit corresponding to the target brightness information may be Lux, i.e., lux.

For example, the corresponding weight P2 of the white balance color temperature detection can be determined by judging whether the current environment scene brightness information is consistent with the auxiliary brightness information. For inconsistent scenes, the color temperature judgment may be misleading, so the third weight P2 can be reduced. The color temperature judgment that deviates from the current Table 1 is very likely to be a white balance result misled by pure color or mixed color, and its corresponding third weight P2 needs to be reduced.

For example, when the auxiliary brightness information is 10, the target brightness information is 460.8. If the value of the scene brightness information is 460.8, that is, the first deviation value is 0, then the value of the third weight P2 can be 1. If the scene brightness information is not 460.8, the greater the difference between the scene brightness information and 460.8, that is, the greater the first deviation value, the lower the value of the third weight P2, until the value of P2 is 0.

By adopting the above scheme, by acquiring the scene brightness information and determining the first deviation value between the target brightness information corresponding to the auxiliary brightness information and the scene brightness information based on the third mapping relationship table, and based on the first deviation value, accurately determining a white balance color temperature detection weight that can reliably characterize the confidence that the scene corresponding to the auxiliary brightness information in the environmental auxiliary information is the target scene, and the target white balance point can be accurately determined based on the white balance color temperature detection weight to avoid the problem of white balance color temperature misjudgment in scenes with large areas of pure color and misleading color light sources.

In some embodiments, determining the white balance color temperature detection weight according to the environmental auxiliary information includes:

According to a preset confidence curve, the weighted confidence corresponding to the auxiliary environmental white point is determined; according to the weighted confidence, a fourth weight is determined; the preset confidence curve is set according to the deviation between the abnormal white balance point and the normal white balance point.

Among them, the normal white balance point and the abnormal white balance point can be pre-calibrated by relevant staff according to the effect of image processing. The normal white balance point can be, for example, a white balance point determined in a non-target scene, which can meet the requirements for the image processing effect. The abnormal white balance point can be a white balance point determined in a target scene, which cannot meet the requirements for the image processing effect. Obviously, there is a certain deviation between the normal white balance point and the abnormal white balance point. Therefore, by setting the preset signal curve Weight Curve, the correct white balance area can be effectively screened, and the fourth weight P3 in the pure color or mixed color scene can be effectively reduced.

For example, FIG3 is a schematic diagram of a preset signal curve according to an exemplary embodiment. Referring to FIG3, the preset signal curve Weight Curve is in a coordinate system, the horizontal axis of the coordinate system is R/G, and the vertical axis is B/G. When the auxiliary environment white point is within the interval formed by the preset signal curve Weight Curve and the horizontal axis, the value of the fourth weight P3 is high. When the auxiliary environment white point is outside the interval formed by the preset signal curve Weight Curve and the horizontal axis, the value of P3 can be low. The present disclosure does not limit the specific value of the fourth weight P3 corresponding to each auxiliary environment white point.

By adopting the above scheme, by setting a preset signal curve, and based on the auxiliary ambient white point and the preset signal curve, a white balance color temperature detection weight that can reliably characterize the confidence that the scene corresponding to the auxiliary ambient white point in the environmental auxiliary information is the target scene can be accurately determined, and the target white balance point can be accurately determined based on the white balance color temperature detection weight to avoid the problem of white balance color temperature misjudgment in scenes with large areas of pure color and misleading color light sources.

In some embodiments, determining at least one white balance color temperature detection weight according to the environmental auxiliary information includes:

A second deviation value from a blackbody radiation curve is determined according to the auxiliary correlated color temperature and the auxiliary infrared information; and a fifth weight is determined according to the second deviation value.

Among them, based on the auxiliary correlated color temperature and the auxiliary infrared information, the deviation DUV from the black body radiation curve (BlackBody Curve) can be derived, and the DUV can be the above-mentioned second deviation value. Through the DUV, that is, the second deviation value, the fifth weight P4 can be determined.

FIG4 is a schematic diagram showing a mapping relationship between a fifth weight and a second deviation value according to an exemplary embodiment. As shown in FIG4 , when the second deviation value, i.e., DUV, is less than 70/-50, the value of the fifth weight P4 may be a preset maximum value, such as 1. When DUV is greater than 70/-50, the value of the fifth weight P4 may be negatively correlated with the size of DUV until the fifth weight P4 is 0. For example, when the second deviation value, i.e., DUV, is equal to 90/-70, the fifth weight P4 is 0.

In some embodiments, determining at least one confidence parameter based on the multi-directional environmental information includes:

A first confidence parameter is determined based on the difference in ambient color temperature detected by the target color temperature sensor and other color temperature sensors; and/or, a second confidence parameter is determined based on the difference in ambient white point detected by the target color temperature sensor and other color temperature sensors; and/or, a third confidence parameter is determined based on the difference in ambient infrared detected by the target color temperature sensor and other color temperature sensors; and/or, a fourth confidence parameter is determined based on the difference in ambient brightness detected by the target color temperature sensor and other color temperature sensors; and/or, a fifth confidence parameter is determined based on the temporal continuity of ambient information detected by the target color temperature sensor; and/or, a fifth confidence parameter is determined based on the degree of matching between the ambient information detected by the target color temperature sensor and the target scene.

For example, the first confidence parameter may be positively correlated with the maximum value of the difference in ambient color temperature detected by the target color temperature sensor and the other color temperature sensors. For example, the larger the maximum value of the difference in ambient color temperature, the larger the first confidence parameter; or, when the difference in ambient color temperature is greater than or equal to a preset threshold, the first confidence parameter is 1, and when the difference in ambient color temperature is less than the preset threshold, the first confidence parameter is linearly correlated with the difference in ambient color temperature. The second confidence parameter, the third confidence parameter, the fourth confidence parameter, and the fifth confidence parameter are similar and will not be described in detail here.

By adopting the above scheme, each confidence parameter can be accurately determined based on the difference between the information detected by the target color temperature sensor and other color temperature sensors, and the time domain continuity of the detected information. Then, based on these confidence parameters, it can be accurately judged whether multi-directional white balancing is needed to avoid the problem of misjudgment of white balance color temperature in scenes with large areas of pure color and misleading color light sources.

FIG5 is a flow chart of an image method according to an exemplary embodiment. The execution subject of the method may be a mobile phone, and the mobile phone may be configured with a front color temperature sensor and a rear color temperature sensor. As shown in FIG5 , the method may include:

S501. In response to an instruction to obtain a first image, obtain bidirectional environmental information, where the bidirectional environmental information includes environmental information detected by a first color temperature sensor and a second color temperature sensor, respectively, and the first color temperature sensor and the second color temperature sensor have different detection directions.

S502: Determine six confidence parameters P0-P5.

S503 , determining output weights W1 and W2 of the front color temperature sensor and the rear color temperature sensor according to confidence parameters P0-P5 and the Pareto optimal frontier multi-objective search strategy.

S504 , generate environmental auxiliary information New (CCT, LV, IRRATIO, R/G, B/G) according to W1 and W2 .

S505 : Generate five white balance color temperature detection weights P0-P4 based on the environmental auxiliary information.

It should be explained that the auxiliary environmental information is obtained by weighted calculation based on the environmental information. It can be understood that the auxiliary correlated color temperature, auxiliary infrared information, auxiliary brightness information and auxiliary ambient white point are respectively related to the correlated color temperature, infrared information, brightness information and ambient white point. The auxiliary correlated color temperature, auxiliary infrared information, auxiliary brightness information and auxiliary ambient white point are respectively obtained by weighted calculation of the correlated color temperature, infrared information, brightness information and ambient white point with the corresponding weighting coefficients.

S506 : Determine the target white balance point of the current environment based on the white balance color temperature detection weights P0 - P4 .

S507: Process the first image according to the target white balance point to obtain a target image.

Among them, the specific optional implementation methods of the above-mentioned steps can refer to the optional implementation methods of other embodiments mentioned above, and will not be repeated here.

Based on the same inventive concept, FIG6 is a block diagram of an image processing device according to an exemplary embodiment. Referring to FIG6 , the image processing device 60 includes:

An acquisition module 61 is configured to acquire the first image and multi-directional environmental information in response to an acquisition instruction of the first image, wherein the multi-directional environmental information includes environmental information respectively detected by a plurality of color temperature sensors, and each of the color temperature sensors has a different detection direction;

A first determination module 62 is configured to determine, based on the multi-directional environmental information, a confidence value that a scene corresponding to a target color temperature sensor is a target scene, wherein a detection direction of the target color temperature sensor corresponds to the first image;

A second determination module 63 is configured to determine a target white balance point according to the multi-directional environment information when it is determined that the confidence value is greater than a preset confidence threshold;

The processing module 64 is configured to process the first image according to the target white balance point to obtain a target image.

Optionally, the first determining module 62 is configured to:

Determining at least one confidence parameter according to the multi-directional environmental information, where different confidence parameters are determined according to different sub-information in the multi-directional environmental information;

The confidence parameters are weighted according to the preset confidence weights corresponding to each of the confidence parameters to obtain the confidence values.

Optionally, the second determining module 63 is configured to:

Based on the confidence parameter, determining an output weight corresponding to each of the color temperature sensors;

Determining environmental auxiliary information according to the output weight and the multi-directional environmental information;

The target white balance point is determined according to the environmental auxiliary information.

Optionally, the second determining module 63 is configured to:

Determine at least one white balance color temperature detection weight according to the environmental auxiliary information, where different white balance color temperature detection weights are determined according to different sub-information in the environmental auxiliary information;

The target white balance point is determined according to the white balance color temperature detection weight.

Optionally, the second determining module 63 is configured to:

Determine a first white balance point corresponding to each of the white balance color temperature detection weights;

Determining an interpolation rate corresponding to each of the white balance color temperature detection weights;

The target white balance point is determined according to the first white balance point corresponding to each of the white balance color temperature detection weights and the interpolation rate corresponding to each of the white balance color temperature detection weights.

Optionally, the second determining module 63 is configured to:

Determine a second white balance point corresponding to the environmental information detected by the target color temperature sensor;

Determine the distance between the first white balance point and the second white balance point corresponding to each of the white balance color temperature detection weights;

Determining a distance weight corresponding to each of the white balance color temperature detection weights according to a distance between a first white balance point and the second white balance point corresponding to each of the white balance color temperature detection weights;

An interpolation rate corresponding to each white balance color temperature detection weight is determined according to each white balance color temperature detection weight, a distance corresponding to each white balance color temperature detection weight, and a distance weight corresponding to each white balance color temperature detection weight.

Optionally, the second determining module 63 is configured to:

Determine the product of each white balance color temperature detection weight, the corresponding distance, and the corresponding distance weight, to obtain an interpolation parameter corresponding to each white balance detection parameter;

The interpolation rate corresponding to each white balance color temperature detection weight is determined according to the interpolation parameter corresponding to each white balance color temperature detection weight and the sum of the difference parameters corresponding to all white balance color temperature detection weights.

Optionally, the second determining module 63 is configured to:

The interpolation rate corresponding to each white balance color temperature detection weight is determined according to the following formula:

Among them, Blend_Ratio _j represents the interpolation rate corresponding to the j-th white balance color temperature detection weight, Dist _j represents the distance between the j-th white balance color temperature detection weight and the second white balance point, Conf _j represents the distance weight corresponding to the j-th white balance color temperature detection weight, and P _j represents the j-th white balance color temperature detection weight; Dist _i represents the distance between the ith white balance color temperature detection weight and the second white balance point, Conf _i represents the distance weight corresponding to the ith white balance color temperature detection weight, _Pi represents the ith white balance color temperature detection weight, and n represents the number of white balance color temperature detection weights.

Optionally, the second determining module 63 is configured to:

The target white balance point is determined according to the following formula:

Among them, FinalR/G_B/G represents the target white balance point, Blend_Ratio _j represents the interpolation rate corresponding to the j-th white balance color temperature detection weight, _PiR /G_B/G represents the first white balance point corresponding to the j-th white balance color temperature detection weight, and n represents the number of white balance color temperature detection weights.

Optionally, the environmental information includes one or more of the following: environmental correlated color temperature, brightness information, infrared information, and environmental white point;

The environmental auxiliary information includes one or more of the following:

Auxiliary correlated color temperature, auxiliary infrared information, auxiliary brightness information, and auxiliary ambient white point.

Optionally, the second determining module 63 is configured to:

Determine, according to the first mapping relationship table, a first weight corresponding to the auxiliary correlated color temperature and the auxiliary infrared information;

The first mapping relationship table is determined according to the matching relationship between the correlated color temperature and infrared information and the target scene.

Optionally, the second determining module 63 is configured to:

Determining a second weight corresponding to the auxiliary correlated color temperature according to a second mapping relationship table;

The second mapping relationship table is determined according to a matching relationship between the correlated color temperature and the target scene.

Optionally, the second determining module 63 is configured to:

Get scene brightness information;

Determine, according to a third mapping relationship table, a first deviation value between the target brightness information corresponding to the auxiliary brightness information and the scene brightness information, wherein the third mapping relationship table is determined according to a matching relationship between the auxiliary brightness information and the target scene brightness;

A third weight is determined according to the first deviation value.

Optionally, the second determining module 63 is configured to:

Determining the weighted reliability corresponding to the auxiliary environment white point according to a preset reliability curve;

Determining a fourth weight according to the weight confidence;

The preset white balance curve is set according to the distribution of abnormal white balance points and normal white balance points.

Optionally, the second determining module 63 is configured to:

Determining a second deviation value from a blackbody radiation curve according to the auxiliary correlated color temperature and the auxiliary infrared information;

A fifth weight is determined according to the second deviation value.

Optionally, the first determining module 62 is configured to:

Determining a first confidence parameter according to a difference in ambient color temperature detected by the target color temperature sensor and other color temperature sensors; and/or,

Determining a second confidence parameter according to the difference in ambient white points detected by the target color temperature sensor and other color temperature sensors; and/or,

Determine a third confidence parameter according to the difference between the ambient infrared detected by the target color temperature sensor and other color temperature sensors; and/or,

Determining a fourth confidence parameter according to a difference in ambient brightness detected by the target color temperature sensor and other color temperature sensors; and/or,

determining a fifth confidence parameter according to the temporal continuity of the environmental information detected by the target color temperature sensor; and/or,

A fifth confidence parameter is determined according to a matching degree between the environmental information detected by the target color temperature sensor and the target scene.

Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

The present disclosure also provides a computer-readable storage medium on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the image processing method provided by the present disclosure are implemented.

Fig. 7 is a block diagram of a device 700 for image processing according to an exemplary embodiment. For example, the device 700 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

7 , the apparatus 700 may include one or more of the following components: a processing component 702 , a memory 704 , a power component 706 , a multimedia component 708 , an audio component 710 , an input/output interface 712 , a sensor component 714 , and a communication component 716 .

The processing component 702 generally controls the overall operation of the device 700, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 702 may include one or more modules to facilitate the interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate the interaction between the multimedia component 708 and the processing component 702.

The memory 704 is configured to store various types of data to support operations on the device 700. Examples of such data include instructions for any application or method operating on the device 700, contact data, phone book data, messages, pictures, videos, etc. The memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

The power supply component 706 provides power to the various components of the device 700. The power supply component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 700.

The multimedia component 708 includes a screen that provides an output interface between the device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front camera and/or a rear camera. When the device 700 is in an operating mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 710 is configured to output and/or input audio signals. For example, the audio component 710 includes a microphone (MIC), and when the device 700 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 704 or sent via the communication component 716. In some embodiments, the audio component 710 also includes a speaker for outputting audio signals.

The input/output interface 712 provides an interface between the processing component 702 and the peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 714 includes one or more sensors for providing various aspects of status assessment for the device 700. For example, the sensor assembly 714 can detect the open/closed state of the device 700, the relative positioning of components, such as the display and keypad of the device 700, the sensor assembly 714 can also detect the position change of the device 700 or a component of the device 700, the presence or absence of user contact with the device 700, the orientation or acceleration/deceleration of the device 700, and the temperature change of the device 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 714 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 714 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 716 is configured to facilitate wired or wireless communication between the device 700 and other devices. The device 700 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 716 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, the apparatus 700 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, and the instructions can be executed by the processor 720 of the device 700 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

In addition to being an independent electronic device, the above-mentioned device can also be a part of an independent electronic device. For example, in one embodiment, the device can be an integrated circuit (IC) or a chip, wherein the integrated circuit can be an IC or a collection of multiple ICs; the chip can include but is not limited to the following types: GPU (Graphics Processing Unit), CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), SOC (System on Chip, SoC), etc. The above-mentioned integrated circuit or chip can be used to execute executable instructions (or codes) to implement the above-mentioned image processing method. The executable instructions can be stored in the integrated circuit or chip, or can be obtained from other devices or equipment, such as the integrated circuit or chip includes a processor, a memory, and an interface for communicating with other devices. The executable instruction may be stored in the memory, and when the executable instruction is executed by the processor, the above-mentioned image processing method may be implemented; alternatively, the integrated circuit or chip may receive the executable instruction through the interface and transmit it to the processor for execution, so as to implement the above-mentioned image processing method.

In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned image processing method when executed by the programmable device.

Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (21)

1. An image processing method, comprising: In response to an instruction to acquire a first image, acquire the first image and multi-directional environmental information, wherein the multi-directional environmental information includes environmental information respectively detected by a plurality of color temperature sensors, and each of the color temperature sensors has a different detection direction; Determining, according to the multi-directional environmental information, a confidence value that a scene corresponding to a target color temperature sensor is a target scene, wherein a detection direction of the target color temperature sensor corresponds to the first image; In a case where it is determined that the confidence value is greater than a preset confidence threshold, determining a target white balance point according to the multi-directional environmental information; The first image is processed according to the target white balance point to obtain a target image. 2. The method according to claim 1, characterized in that, according to the multi-directional environmental information, determining the confidence value that the scene corresponding to the target color temperature sensor is the target scene comprises: Determining at least one confidence parameter according to the multi-directional environmental information, where different confidence parameters are determined according to different sub-information in the multi-directional environmental information; The confidence parameters are weighted according to the preset confidence weights corresponding to each of the confidence parameters to obtain the confidence values. 3. The method according to claim 2, wherein determining the target white balance point according to the multi-directional environmental information comprises: Based on the confidence parameter, determining an output weight corresponding to each of the color temperature sensors; Determining environmental auxiliary information according to the output weight and the multi-directional environmental information; The target white balance point is determined according to the environmental auxiliary information. 4. The method according to claim 3, characterized in that determining the target white balance point according to the environmental auxiliary information comprises: Determine at least one white balance color temperature detection weight according to the environmental auxiliary information, where different white balance color temperature detection weights are determined according to different sub-information in the environmental auxiliary information; The target white balance point is determined according to the white balance color temperature detection weight. 5. The method according to claim 4, characterized in that determining the target white balance point according to the white balance color temperature detection weight comprises: Determine a first white balance point corresponding to each of the white balance color temperature detection weights; Determining an interpolation rate corresponding to each of the white balance color temperature detection weights; The target white balance point is determined according to the first white balance point corresponding to each of the white balance color temperature detection weights and the interpolation rate corresponding to each of the white balance color temperature detection weights. 6. The method according to claim 5, characterized in that the determining the interpolation rate corresponding to each of the white balance color temperature detection weights comprises: Determine a second white balance point corresponding to the environmental information detected by the target color temperature sensor; Determine the distance between the first white balance point and the second white balance point corresponding to each of the white balance color temperature detection weights; An interpolation rate corresponding to each of the white balance color temperature detection weights is determined according to a distance between the first white balance point and the second white balance point corresponding to each of the white balance color temperature detection weights. 7. The method according to claim 6, wherein determining the interpolation rate corresponding to each white balance color temperature detection weight according to the distance between the first white balance point and the second white balance point corresponding to each white balance color temperature detection weight comprises: Determining a distance weight corresponding to each of the white balance color temperature detection weights according to a distance between a first white balance point and the second white balance point corresponding to each of the white balance color temperature detection weights; An interpolation rate corresponding to each white balance color temperature detection weight is determined according to each white balance color temperature detection weight, a distance corresponding to each white balance color temperature detection weight, and a distance weight corresponding to each white balance color temperature detection weight. 8. The method according to claim 7, characterized in that, according to each of the white balance color temperature detection weights, the distance corresponding to each of the white balance color temperature detection weights, and the distance weight corresponding to each of the white balance color temperature detection weights, determining the interpolation rate corresponding to each of the white balance color temperature detection weights comprises: Determine the product of each white balance color temperature detection weight, the corresponding distance, and the corresponding distance weight, to obtain an interpolation parameter corresponding to each white balance detection parameter; The interpolation rate corresponding to each white balance color temperature detection weight is determined according to the interpolation parameter corresponding to each white balance color temperature detection weight and the sum of the difference parameters corresponding to all white balance color temperature detection weights. 9. The method according to claim 7, characterized in that, according to each of the white balance color temperature detection weights, the distance corresponding to each of the white balance color temperature detection weights, and the distance weight corresponding to each of the white balance color temperature detection weights, determining the interpolation rate corresponding to each of the white balance color temperature detection weights comprises: The interpolation rate corresponding to each white balance color temperature detection weight is determined according to the following formula: Among them, Blend_Ratio _j represents the interpolation rate corresponding to the j-th white balance color temperature detection weight, Dist _j represents the distance between the j-th white balance color temperature detection weight and the second white balance point, Conf _j represents the distance weight corresponding to the j-th white balance color temperature detection weight, and P _j represents the j-th white balance color temperature detection weight; Dist _i represents the distance between the ith white balance color temperature detection weight and the second white balance point, Conf _i represents the distance weight corresponding to the ith white balance color temperature detection weight, _Pi represents the ith white balance color temperature detection weight, and n represents the number of white balance color temperature detection weights. 10. The method according to claim 5, characterized in that the determining the target white balance point according to the first white balance point corresponding to each of the white balance color temperature detection weights and the interpolation rate corresponding to each of the white balance color temperature detection weights comprises: The target white balance point is determined according to the following formula: Among them, FinalR/G_B/G represents the target white balance point, Blend_Ratio _j represents the interpolation rate corresponding to the j-th white balance color temperature detection weight, _PiR /G_B/G represents the first white balance point corresponding to the j-th white balance color temperature detection weight, and n represents the number of white balance color temperature detection weights. 11. The method according to any one of claims 4 to 10, characterized in that the environmental information comprises one or more of the following: environmental correlated color temperature, brightness information, infrared information, and environmental white point; The environmental auxiliary information includes one or more of the following: Auxiliary correlated color temperature, auxiliary infrared information, auxiliary brightness information, and auxiliary ambient white point. 12. The method according to claim 11, characterized in that determining at least one white balance color temperature detection weight according to the environmental auxiliary information comprises: Determine, according to the first mapping relationship table, a first weight corresponding to the auxiliary correlated color temperature and the auxiliary infrared information; The first mapping relationship table is determined according to the matching relationship between the correlated color temperature and infrared information and the target scene. 13. The method according to claim 12, characterized in that determining at least one white balance color temperature detection weight according to the environmental auxiliary information comprises: Determining a second weight corresponding to the auxiliary correlated color temperature according to a second mapping relationship table; The second mapping relationship table is determined according to a matching relationship between the correlated color temperature and the target scene. 14. The method according to claim 11, characterized in that determining at least one white balance color temperature detection weight according to the environmental auxiliary information comprises: Get scene brightness information; Determine, according to a third mapping relationship table, a first deviation value between the target brightness information corresponding to the auxiliary brightness information and the scene brightness information, wherein the third mapping relationship table is determined according to a matching relationship between the auxiliary brightness information and the target scene brightness; A third weight is determined according to the first deviation value. 15. The method according to claim 11, characterized in that determining at least one white balance color temperature detection weight according to the environmental auxiliary information comprises: Determining the weighted reliability corresponding to the auxiliary environment white point according to a preset reliability curve; Determining a fourth weight according to the weight confidence; The preset white balance curve is set according to the distribution of abnormal white balance points and normal white balance points. 16. The method according to claim 11, characterized in that determining at least one white balance color temperature detection weight according to the environmental auxiliary information comprises: Determining a second deviation value from a blackbody radiation curve according to the auxiliary correlated color temperature and the auxiliary infrared information; A fifth weight is determined according to the second deviation value. 17. The method according to claim 11, wherein determining at least one confidence parameter according to the multi-directional environmental information comprises: Determining a first confidence parameter according to a difference in ambient color temperature detected by the target color temperature sensor and other color temperature sensors; and/or, Determining a second confidence parameter according to the difference in ambient white points detected by the target color temperature sensor and other color temperature sensors; and/or, Determine a third confidence parameter according to the difference between the ambient infrared detected by the target color temperature sensor and other color temperature sensors; and/or, Determining a fourth confidence parameter according to a difference in ambient brightness detected by the target color temperature sensor and other color temperature sensors; and/or, determining a fifth confidence parameter according to the temporal continuity of the environmental information detected by the target color temperature sensor; and/or, A fifth confidence parameter is determined according to a matching degree between the environmental information detected by the target color temperature sensor and the target scene. 18. An image processing device, comprising: an acquisition module, configured to acquire the first image and multi-directional environmental information in response to an acquisition instruction of the first image, wherein the multi-directional environmental information includes environmental information respectively detected by a plurality of color temperature sensors, and each of the color temperature sensors has a different detection direction; A first determination module is configured to determine, based on the multi-directional environmental information, a confidence value that a scene corresponding to a target color temperature sensor is a target scene, wherein a detection direction of the target color temperature sensor corresponds to the first image; A second determination module is configured to determine a target white balance point according to the multi-directional environment information when it is determined that the confidence value is greater than a preset confidence threshold; The processing module is configured to process the first image according to the target white balance point to obtain a target image. 19. An image processing device, comprising: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: In response to an instruction to acquire a first image, acquire the first image and multi-directional environmental information, wherein the multi-directional environmental information includes environmental information respectively detected by a plurality of color temperature sensors, and each of the color temperature sensors has a different detection direction; Determining, according to the multi-directional environmental information, a confidence value that a scene corresponding to a target color temperature sensor is a target scene, wherein a detection direction of the target color temperature sensor corresponds to the first image; In a case where it is determined that the confidence value is greater than a preset confidence threshold, determining a target white balance point according to the multi-directional environmental information; The first image is processed according to the target white balance point to obtain a target image. 20. A computer-readable storage medium having computer program instructions stored thereon, wherein the program instructions implement the steps of the method according to any one of claims 1 to 17 when executed by a processor. 21. A chip, comprising a processor and an interface; the processor is used to read instructions to execute the method according to any one of claims 1 to 17.