CN109379538B

CN109379538B - Image acquisition device, system and method

Info

Publication number: CN109379538B
Application number: CN201811260834.0A
Authority: CN
Inventors: 刘源
Original assignee: Alibaba Group Holding Ltd; Advanced New Technologies Co Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2018-10-26
Filing date: 2018-10-26
Publication date: 2021-06-22
Anticipated expiration: 2038-10-26
Also published as: CN109379538A; CN113452926A; CN113452926B

Abstract

One or more embodiments of the present specification disclose an image acquisition device, system, and method to realize fully automatic image acquisition and annotation, thereby improving image recognition efficiency and image annotation efficiency, and reducing image annotation costs. The device includes: a controllable light source for providing illumination in a shooting scene; a processor for controlling the controllable light source to start and adjusting the working parameters of the controllable light source, so as to make the controllable light source work The parameters conform to preset working parameters; the processor is further configured to preprocess the shooting object and/or the shooting scene, so that the shooting object and/or the shooting scene meet the preset shooting conditions; a shooting device , for shooting the shooting object in the shooting scene to obtain a first image of the shooting object; and a network communication device for uploading the first image to the cloud for storage.

Description

Image acquisition device, system and method

Technical Field

The present disclosure relates to the field of image capturing technologies, and in particular, to an image capturing apparatus, system, and method.

Background

The current mainstream of image recognition is a deep learning method based on a Convolutional Neural Network (CNN), and therefore, the scale and quality of an image training data set have a great influence on the recognition accuracy. Efficient image recognition can be used in a plurality of fields, for example, in the field of unmanned retail, and the commodities are identified by using an image recognition technology in a computer vision-based mode, so that the commodities which are purchased by a consumer are determined, and a subsequent payment operation is started.

In addition, in the existing scheme, when an image is identified, a manual or semi-automatic labeling tool is mainly used for labeling the image, if the scale of an image training data set is large, a large amount of manpower is needed, the efficiency is low, the cost is high, and errors are easy to occur in manual labeling, so that the image identification effect is influenced.

Disclosure of Invention

One or more embodiments of the present disclosure provide an image capturing device, an image capturing system, and an image capturing method, which are used to achieve full-automatic image capturing and labeling, so as to improve image recognition efficiency and image labeling efficiency and reduce image labeling cost.

To solve the above technical problem, one or more embodiments of the present specification are implemented as follows:

in one aspect, one or more embodiments of the present specification provide an image capturing apparatus including:

a controllable light source for providing illumination in a shooting scene;

the processor is used for controlling the controllable light source to start and adjusting the working parameters of the controllable light source so as to enable the working parameters of the controllable light source to accord with preset working parameters; wherein the working parameter comprises at least one of illumination intensity, illumination color and color temperature;

the processor is further used for preprocessing a shooting object and/or the shooting scene so that the shooting object and/or the shooting scene meet a preset shooting condition;

the shooting device is used for shooting the shooting object in the shooting scene to obtain a first image of the shooting object;

and the network communication device is used for uploading the first image to a cloud for storage.

In one embodiment, the processor comprises:

the motion control device is used for controlling the shooting object and/or the shooting device to move in the shooting scene until the shooting object and the shooting device meet a preset position relation; wherein the moving operation comprises a translation operation and/or a rotation operation.

In one embodiment, the processor comprises:

image recognition means for locating the photographic subject from the photographic scene; carrying out image segmentation processing on the shooting object and other objects except the shooting object in the shooting scene to obtain an image of a first object; identifying a color of an image of the first object as a specified color; wherein the first object includes a shooting background.

In one embodiment, the processor is further configured to:

before the shooting object is shot in the shooting scene, determining a first shooting parameter corresponding to the current shooting environment according to a corresponding relation between a preset shooting environment and a shooting parameter of a shooting device;

and adjusting the current shooting parameters of the shooting device to the first shooting parameters.

In one embodiment, the processor is further configured to:

before the first image is uploaded to a cloud end for storage, determining corresponding pixel information of the shooting object in the first image;

marking a mapping relation between the pixel information and the key information of the shooting object in the first image; wherein the key information includes a name and/or a keyword of the photographic subject.

In one embodiment, the processor is further configured to:

after the shooting object is shot in the shooting scene to obtain a first image of the shooting object, carrying out image processing on the first image to obtain a second image; wherein the image processing comprises at least one of image cropping, light effect processing and color processing;

correspondingly, the network communication device is further configured to:

and uploading the second image to a cloud for storage.

In one embodiment, the apparatus further comprises:

a memory for storing the first image locally.

In another aspect, one or more embodiments of the present specification provide an image capturing system including:

an image acquisition device for providing illumination in a shooting scene; controlling the controllable light source to start and adjusting working parameters of the controllable light source so as to enable the working parameters of the controllable light source to accord with preset working parameters; wherein the working parameter comprises at least one of illumination intensity, illumination color and color temperature; preprocessing a shooting object and/or the shooting scene to enable the shooting object and/or the shooting scene to meet preset shooting conditions; shooting the shooting object in the shooting scene to obtain a first image of the shooting object; uploading the first image to a cloud processing device;

the cloud processing device is used for receiving the first image sent by the image acquisition equipment; and storing the first image.

In another aspect, one or more embodiments of the present specification provide an image capturing method applied to an image capturing apparatus, including:

controlling a controllable light source in a shooting scene to start and adjusting working parameters of the controllable light source so as to enable the working parameters of the controllable light source to accord with preset working parameters; wherein the working parameter comprises at least one of illumination intensity, illumination color and color temperature;

preprocessing a shooting object and/or the shooting scene to enable the shooting object and/or the shooting scene to meet preset shooting conditions;

shooting the shooting object in the shooting scene to obtain a first image of the shooting object;

and uploading the first image to a cloud for storage.

In one embodiment, the preset shooting condition includes that a preset position relationship is satisfied between the shooting object and the shooting device;

correspondingly, the preprocessing the shooting object and/or the shooting scene comprises:

controlling the shooting object and/or the shooting device to move in the shooting scene until the shooting object and the shooting device meet a preset position relation; wherein the moving operation comprises a translation operation and/or a rotation operation.

In one embodiment, the preset shooting condition comprises that the color of a first object in the shooting scene is a specified color; the first object includes a shooting background;

positioning the photographic object from the photographic scene;

performing image segmentation processing on the shooting object and other objects except the shooting object in the shooting scene to obtain an image of the first object;

identifying a color of an image of the first object as the specified color.

In one embodiment, before the photographing of the photographic subject in the photographing scene, the method further includes:

determining a first shooting parameter corresponding to the current shooting environment according to a corresponding relation between a preset shooting environment and a shooting parameter of a shooting device;

In one embodiment, before uploading the first image to a cloud for storage, the method further comprises:

determining corresponding pixel information of the shooting object in the first image;

In one embodiment, after the photographing of the photographic subject in the photographing scene and the obtaining of the first image of the photographic subject, the method further comprises:

performing image processing on the first image to obtain a second image; wherein the image processing comprises at least one of image cropping, light effect processing and color processing;

correspondingly, the uploading the first image to a cloud for storage includes:

and uploading the second image to a cloud for storage.

In another aspect, one or more embodiments of the present specification provide an image capturing apparatus applied to an image capturing device, including:

the control module is used for controlling the start of a controllable light source in a shooting scene and adjusting working parameters of the controllable light source so as to enable the working parameters of the controllable light source to accord with preset working parameters; wherein the working parameter comprises at least one of illumination intensity, illumination color and color temperature;

the processing module is used for preprocessing a shooting object and/or the shooting scene so as to enable the shooting object and/or the shooting scene to meet preset shooting conditions;

the shooting module is used for shooting the shooting object in the shooting scene to obtain a first image of the shooting object;

and the uploading module is used for uploading the first image to a cloud for storage.

correspondingly, the processing module comprises:

the control unit is used for controlling the shooting object and/or the shooting device to move in the shooting scene until the shooting object and the shooting device meet a preset position relation; wherein the moving operation comprises a translation operation and/or a rotation operation.

correspondingly, the processing module comprises:

a positioning unit configured to position the photographic subject from the photographic scene;

the segmentation unit is used for carrying out image segmentation processing on the shooting object and other objects except the shooting object in the shooting scene to obtain an image of the first object;

an identifying unit configured to identify a color of an image of the first object as the specified color.

In one embodiment, the apparatus further comprises:

a first determining module, configured to determine, before the shooting of the shooting object in the shooting scene, a first shooting parameter corresponding to a current shooting environment according to a correspondence between a preset shooting environment and a shooting parameter of a shooting device;

and the adjusting module is used for adjusting the current shooting parameters of the shooting device into the first shooting parameters.

In one embodiment, the apparatus further comprises:

a second determining module, configured to determine pixel information corresponding to the photographic object in the first image before uploading the first image to a cloud for storage;

the marking module is used for marking the mapping relation between the pixel information and the key information of the shooting object in the first image; wherein the key information includes a name and/or a keyword of the photographic subject.

In one embodiment, the apparatus further comprises:

the image processing module is used for shooting the shooting object in the shooting scene to obtain a first image of the shooting object and then carrying out image processing on the first image to obtain a second image; wherein the image processing comprises at least one of image cropping, light effect processing and color processing;

correspondingly, the uploading module comprises:

and the uploading unit is used for uploading the second image to a cloud for storage.

In yet another aspect, one or more embodiments of the present specification provide an image capturing apparatus including:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to:

and uploading the first image to a cloud for storage.

In yet another aspect, an embodiment of the present application provides a storage medium for storing computer-executable instructions, where the computer-executable instructions, when executed, implement the following processes:

and uploading the first image to a cloud for storage.

By adopting the technical scheme of one or more embodiments of the specification, the illumination environment in the shooting scene can be automatically constructed by controlling the starting of the light source in the shooting scene and adjusting the working parameters of the light source; the shot object and/or the shot scene are/is preprocessed, so that the shot object and/or the shot scene meet the preset shooting condition, and therefore shooting preparation can be automatically made before shooting without manual participation; then, the shooting object is shot under the condition that the shooting object and/or the shooting scene meet the preset shooting conditions, a first image of the shooting object is obtained, and the first image is uploaded to a cloud end to be stored. Therefore, the technical scheme realizes full-automatic image acquisition, and the whole image acquisition process does not need manual participation, so that a large amount of human resources are saved, and the image acquisition efficiency is improved.

Furthermore, the technical scheme can determine the corresponding pixel information of the shot object in the first image, and label the mapping relation between the pixel information and the key information (including the name and/or the keyword) of the shot object in the first image, so that the labeling process of the image does not need manual participation, the automation of image labeling is realized, and the efficiency of image labeling is further improved.

Drawings

In order to more clearly illustrate one or more embodiments or technical solutions in the prior art in the present specification, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in one or more embodiments of the present specification, and other drawings can be obtained by those skilled in the art without inventive exercise.

FIG. 1 is a schematic block diagram of an image acquisition device according to one embodiment of the present description;

FIG. 2 is a schematic block diagram of an image acquisition device according to another embodiment of the present description;

FIG. 3 is a schematic block diagram of an image acquisition system in accordance with an embodiment of the present description;

FIG. 4 is a schematic flow chart diagram of an image acquisition method in accordance with one embodiment of the present description;

FIG. 5 is a schematic flow chart diagram of a method of image acquisition according to another embodiment of the present description;

FIG. 6 is a schematic block diagram of an image acquisition device according to one embodiment of the present description;

fig. 7 is a schematic block diagram of an image acquisition apparatus according to an embodiment of the present description.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from one or more of the embodiments of the present disclosure without making any creative effort shall fall within the protection scope of one or more of the embodiments of the present disclosure.

Fig. 1 is a schematic block diagram of an image capturing apparatus according to an embodiment of the present specification. As shown in fig. 1, the image pickup apparatus includes:

a controllable light source 110 for providing illumination in a photographic scene.

In one embodiment, the controllable light source 110 may be a lamp box capable of providing illumination, that is, the lamp box is used to provide illumination for a shooting scene, and the operating parameters of the lamp box are adjustable.

And the processor 120 is configured to control the controllable light source to start and adjust the working parameters of the controllable light source, so that the working parameters of the controllable light source conform to preset working parameters.

Wherein the working parameter comprises at least one of illumination intensity, illumination color and color temperature. The preset working parameters can be set according to the effects of definition, exposure, color and the like of the actually shot image.

The processor 120 is further configured to pre-process the photographic object and/or the photographic scene so that the photographic object and/or the photographic scene satisfy a preset shooting condition.

Wherein the preset shooting condition may include at least one of: the shooting object and the shooting device 130 satisfy a preset position relationship, and the color of the first object in the shooting scene is a designated color. How to pre-process the shooting object and/or the shooting scene to satisfy the preset shooting condition will be described in detail below.

The photographing device 130 is configured to photograph a photographic subject in a photographing scene to obtain a first image of the photographic subject.

The camera 130 may be a camera, and the number of the cameras is not limited. When being equipped with a plurality of cameras in the shooting environment, can set up a plurality of cameras in the different position of shooting the object to shoot the image of shooting the object different angles, be favorable to follow-up training study to the sample image.

If the camera device 130 is a camera, the camera should support an RGB camera (i.e., a camera capable of acquiring color signals) or a depth camera, and can output the acquired image through a USB (Universal Serial Bus) interface, and support multi-path sample image acquisition with different viewing angles.

The network communication device 140 is configured to upload the first image to the cloud for storage.

By adopting the image acquisition equipment in one or more embodiments of the specification, the illumination environment in the shooting scene can be automatically constructed by controlling the starting of the light source in the shooting scene and adjusting the working parameters of the light source; the shot object and/or the shot scene are/is preprocessed, so that the shot object and/or the shot scene meet the preset shooting condition, and therefore shooting preparation can be automatically made before shooting without manual participation; then, the shooting object is shot under the condition that the shooting object and/or the shooting scene meet the preset shooting conditions, a first image of the shooting object is obtained, and the first image is uploaded to a cloud end to be stored. Therefore, the technical scheme realizes full-automatic image acquisition, and the whole image acquisition process does not need manual participation, so that a large amount of human resources are saved, and the image acquisition efficiency is improved.

Fig. 2 is a schematic block diagram of an image acquisition apparatus according to another embodiment of the present description. As shown in fig. 2, the image capturing apparatus includes a controllable light source 110, a processor 120, a camera 130, a network communication device 140, and a memory 150. The processor 120 includes a motion control device 121 and an image recognition device 122. The respective components will be described in detail below.

And the motion control device 121 is used for controlling the shooting object and/or the shooting device 130 to move in the shooting scene until the shooting object and the shooting device 130 meet the preset position relationship.

Wherein the moving operation comprises a translation operation and/or a rotation operation.

The preset position relation can be set according to the acquisition requirement of the sample image. For example, if a front image of the subject needs to be acquired as the sample image, the preset positional relationship may be a relationship between the photographing device 130 and the front of the subject; if the left side image of the object needs to be collected as the sample image, the preset position relationship may be a relationship that the photographing device 130 is located on the left side of the object. When the photographing device 130 includes a plurality of cameras, a preset positional relationship between each camera and a photographing object may be set, respectively.

In one embodiment, a rotatable and movable motion platform may be provided in the imaging environment, for example, the motion platform may be a stepper motor, which supports up to 6 axes of motion, and the direction, position and speed of motion may be controlled by the motion controller 121. Then, the photographic subject is placed on the motion platform, so that the motion control device 121 achieves the purpose of controlling the rotation and/or translation of the photographic subject by controlling the rotation and/or translation of the motion platform.

In the present embodiment, the photographing object and/or the photographing device 130 is controlled to move in the photographing scene so that the photographing object and the photographing device 130 can satisfy the preset positional relationship, so that the preparation before photographing can be automatically completed without manually adjusting the position of the photographing object and/or the photographing device 130.

Image recognition means 122 for locating a photographic subject from a photographic scene; carrying out image segmentation processing on the shooting object and other objects except the shooting object in the shooting scene to obtain an image of a first object; the color of the image of the first object is identified as the designated color.

Wherein the first object includes a shooting background. When the first object is the shooting background, the image recognition device 122 performs image segmentation processing on the shooting object and other objects in the shooting scene to obtain an image of the shooting background. And, the color of the image of the shooting background is recognized as the designated color. In order to enable a clear distinction between the photographic subject and the photographic background, the designated color may be a single color, such as green, black, or the like. The image recognition device 122 may perform image segmentation processing on the shot object and other objects by using any image segmentation algorithm, such as a superpixel segmentation algorithm, a matlab image segmentation algorithm, and so on. The specific image segmentation algorithm belongs to the prior art, and is not described in detail.

In this embodiment, the shot object is positioned from the shooting scene, and the shot object and the shooting background are subjected to image segmentation processing, so that the shot object can be segmented from the shooting background, and even if the color of the shooting background is more complex, the shooting background can be identified as the designated color, and the shot object can be identified quickly and accurately.

In an embodiment, the processor 120 is further configured to determine a first shooting parameter corresponding to the current shooting environment according to a preset correspondence between the shooting environment and the shooting parameter of the shooting device 130 before shooting the shooting object in the shooting scene, and further adjust the current shooting parameter of the shooting device 130 to the first shooting parameter.

In this embodiment, the processor 120 can correspondingly adjust the shooting parameters of the shooting device 130 according to the current shooting environment, thereby achieving the effect of automatically adjusting the shooting device 130 and making the image obtained by shooting better.

In one embodiment, if the camera 130 is a camera, the shooting parameters may include various parameters such as aperture, focal length, white balance, etc. of the camera. If the photographing device 130 includes a plurality of cameras, the photographing parameters of the cameras can be preset respectively.

In one embodiment, the processor 120 is further configured to determine corresponding pixel information of the photographic object in the first image before uploading the first image to the cloud for storage, and then label a mapping relationship between the pixel information and key information of the photographic object in the first image. The key information comprises the name and/or the keyword of the shooting object.

In this embodiment, the first image includes both the photographic subject and the photographic background. The corresponding pixel information of the shot object in the first image can accurately describe the outline of the shot object in the first image. Therefore, the mapping relation between the pixel information corresponding to the shooting object and the key information of the shooting object is marked in the first image, so that the automation of image marking is realized, and the subsequent training and learning of the sample image are facilitated.

In one embodiment, the processor 120 is further configured to, after capturing/obtaining a first image of a subject in a capturing scene, perform image processing on the first image to obtain a second image; the image processing includes any one or more image processing modes such as image cropping, light effect processing, color processing and the like. Based on this, the network communication device 140 is further configured to upload the second image to the cloud for storage.

In this embodiment, the processor 120 processes the first image into the second image, and then uploads the second image to the cloud for storage, so that the quality of the sample image obtained by the cloud is better, and the subsequent training and learning on the sample image are facilitated.

A memory 150 for locally storing the first image or the second image. The memory 150 locally stores the first images or the second images, and can upload the plurality of first images or second images to the cloud in batch after storing a certain number of first images or second images, so that the number of times of interaction between the memory 150 and the cloud is reduced to a certain extent, and the efficiency of uploading the sample images to the cloud is improved.

FIG. 3 is a schematic block diagram of an image acquisition system in accordance with an embodiment of the present description. As shown in fig. 3, the image acquisition system 300 includes:

an image capture device 310 for providing illumination in a shooting scene; controlling the controllable light source to start and adjusting the working parameters of the controllable light source so as to enable the working parameters of the controllable light source to accord with preset working parameters; wherein the working parameters comprise at least one of illumination intensity, illumination color and color temperature; preprocessing a shooting object and/or a shooting scene to enable the shooting object and/or the shooting scene to meet preset shooting conditions; shooting a shooting object in a shooting scene to obtain a first image of the shooting object; the first image is uploaded to the cloud processing device 320.

The cloud processing device 320 is configured to receive a first image sent by the image acquisition device 310; and storing the first image.

It should be understood by those skilled in the art that for the components of the image capturing system in fig. 3, the detailed description thereof should be similar to the description of the image capturing device, and in order to avoid complexity, the detailed description thereof is omitted here.

Fig. 4 is a schematic flow chart of an image capturing method according to an embodiment of the present specification, and as shown in fig. 4, the method is applied to the image capturing apparatus described in the above embodiment, and includes:

s402, controlling the controllable light source in the shooting scene to start and adjusting the working parameters of the controllable light source so that the working parameters of the controllable light source accord with preset working parameters.

S404, preprocessing the shooting object and/or the shooting scene to enable the shooting object and/or the shooting scene to meet the preset shooting condition.

Wherein the preset shooting condition may include at least one of: the shooting object and the shooting device meet the preset position relationship, and the color of the first object in the shooting scene is the designated color. How to pre-process the shooting object and/or the shooting scene to satisfy the preset shooting condition will be described in detail below.

S406, shooting the shooting object in the shooting scene to obtain a first image of the shooting object.

In this step, since the photographing device may include a plurality of cameras, and the plurality of cameras may be disposed at different orientations of the photographic subject, after the photographic subject is photographed by the photographing device, a plurality of first images of the photographic subject at different orientations may be obtained.

S408, uploading the first image to a cloud for storage.

In one embodiment, the preset photographing condition includes that a preset positional relationship between the photographing object and the photographing device is satisfied. The preset position relation can be set according to the acquisition requirement of the sample image. For example, if a front image of the photographic subject needs to be acquired as a sample image, the preset positional relationship may be a relationship between the photographic device and the front of the photographic subject; if the left side image of the shooting object needs to be collected as the sample image, the preset position relationship may be a relationship that the shooting device is located on the left side of the shooting object.

Therefore, when the shooting object and/or the shooting scene are preprocessed, the shooting object and/or the shooting device can be controlled to move in the shooting scene until the shooting object and the shooting device meet the preset position relation. Wherein the moving operation comprises a translation operation and/or a rotation operation.

In the embodiment, the shooting object and/or the shooting device are controlled to move in the shooting scene, so that the preset position relationship between the shooting object and the shooting device can be met, and the preparation work before shooting can be automatically completed without manually adjusting the position of the shooting object and/or the shooting device.

In one embodiment, the preset photographing condition includes that a color of a first object in the photographing scene is a designated color, wherein the first object includes a photographing background. Therefore, when the shooting object and/or the shooting scene are preprocessed, the shooting object is firstly positioned from the shooting scene; secondly, carrying out image segmentation processing on the shooting object and other objects except the shooting object in the shooting scene to obtain an image of a first object; the color of the image of the first object is then identified as the designated color.

When the first object is the shooting background, the image of the shooting background can be obtained after the image segmentation processing is carried out on the shooting object and other objects in the shooting scene. And, the color of the image of the shooting background is recognized as the designated color. In order to enable a clear distinction between the photographic subject and the photographic background, the designated color may be a single color, such as green, black, or the like. In addition, any image segmentation algorithm in the prior art, such as a superpixel segmentation algorithm, a matlab image segmentation algorithm, and the like, may be used to perform image segmentation processing on the photographic subject and other subjects. The specific image segmentation algorithm belongs to the prior art, and is not described in detail.

In one embodiment, before a shooting object is shot in a shooting scene, a first shooting parameter corresponding to a current shooting environment may be determined according to a preset correspondence between the shooting environment and a shooting parameter of a shooting device, and then the current shooting parameter of the shooting device is adjusted to the first shooting parameter.

In the embodiment, the shooting parameters of the shooting device can be correspondingly adjusted according to the current shooting environment, so that the effect of automatically adjusting the shooting device is realized, and the image obtained by shooting is better in effect.

In one embodiment, if the camera is a camera, the shooting parameters may include various parameters such as aperture, focal length, white balance, etc. of the camera. If the shooting device comprises a plurality of cameras, shooting parameters of the cameras can be preset respectively.

In one embodiment, before the first image is uploaded to the cloud for storage, corresponding pixel information of the shooting object in the first image can be determined, and a mapping relation between the pixel information and key information of the shooting object is marked in the first image. The key information comprises the name and/or the keyword of the shooting object.

In this embodiment, the first image includes both an image of a photographic subject and an image of a photographic background. The corresponding pixel information of the shot object in the first image can accurately describe the outline of the shot object in the first image. Therefore, the mapping relation between the pixel information corresponding to the shooting object and the key information of the shooting object is marked in the first image, so that the automation of image marking is realized, and the subsequent training and learning of the sample image are facilitated.

In one embodiment, after a shooting object is shot in a shooting scene and a first image of the shooting object is obtained, the first image can be subjected to image processing to obtain a second image; the image processing includes any one or more image processing modes such as image cropping, light effect processing, color processing and the like. Therefore, when the image is uploaded to the cloud, the second image obtained after processing can be uploaded to the cloud for storage.

In this embodiment, the first image is processed into the second image, and then the second image is uploaded to the cloud for storage, so that the quality of the sample image obtained by the cloud is better, and the follow-up training and learning of the sample image are facilitated.

In one embodiment, the first image or the second image may be stored locally. Through storing first image or second image in local to can be after having stored a certain amount of first image or second image, upload a plurality of first images or second image to the high in the clouds again in batches, thereby reduced the interactive number of times of image acquisition equipment with the high in the clouds to a certain extent, and then improve the efficiency of uploading the sample image to the high in the clouds.

Fig. 5 is a schematic flow chart of an image capturing method according to an embodiment of the present specification, and as shown in fig. 5, the method is applied to the image capturing apparatus described in the above embodiment, and includes:

s501, controlling a controllable light source in a shooting scene to start, and adjusting working parameters of the controllable light source to enable the working parameters of the controllable light source to accord with preset working parameters.

S502, judging whether the shooting device and the shooting object meet a preset position relation or not; if not, executing S503; if yes, go to S504.

And S503, controlling the shooting device and/or the shooting object to perform moving operation so as to enable the shooting device and the shooting object to meet the preset position relation.

And S504, adjusting the shooting parameters of the shooting device according to the current shooting environment.

The different shooting environments and the shooting parameters of the shooting device have mapping relations, and the mapping relations can be stored in the image acquisition equipment in advance. When the shooting parameters of the shooting device are adjusted, the first shooting parameters corresponding to the current shooting environment can be determined according to the pre-stored mapping relation, and then the shooting parameters of the shooting device are adjusted according to the first shooting parameters.

And S505, positioning the shooting object from the shooting scene, and performing image segmentation processing on the shooting object and the shooting background to obtain an image of the shooting background.

S506, recognizing the image of the shooting background as a specified color.

In order to make a clear distinction between the subject and the background, the designated color may be a single color, such as green, black, or the like.

And S507, on the basis of identifying the shooting background as the designated color, shooting the shooting object to obtain a first image of the shooting object.

The first image includes both the image of the shooting object and the image of the shooting background.

And S508, performing image processing on the first image to obtain a second image.

The image processing includes any one or more image processing modes such as image cropping, light effect processing, color processing and the like.

S509, the corresponding pixel information of the shooting object in the second image is determined, and the mapping relation between the pixel information and the name of the shooting object is marked in the second image.

And S510, uploading the marked second image to a cloud for storage.

Therefore, the technical scheme of the embodiment can not only fully automatically prepare for shooting before shooting, including adjusting the positions of the shot object and the shooting device, adjusting the shooting parameters of the controllable light source and the like, but also fully automatically label the collected image, so that the technical scheme realizes full-automatic image collection and labeling, the whole image collection and labeling process does not need manual participation, a large amount of human resources are saved, and the efficiency of image collection and labeling is improved.

In summary, particular embodiments of the present subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may be advantageous.

Fig. 6 is a schematic block diagram of an image acquisition apparatus according to an embodiment of the present disclosure. As shown in fig. 6, the image capturing apparatus 600 is applied to an image capturing device including:

the control module 610 is configured to control a controllable light source in a shooting scene to start and adjust working parameters of the controllable light source, so that the working parameters of the controllable light source conform to preset working parameters; wherein the working parameters comprise at least one of illumination intensity, illumination color and color temperature;

the processing module 620 is configured to pre-process the photographic object and/or the photographic scene so that the photographic object and/or the photographic scene meet a preset shooting condition;

a shooting module 630, configured to shoot a shooting object in a shooting scene to obtain a first image of the shooting object;

the uploading module 640 is configured to upload the first image to a cloud for storage.

In one embodiment, the preset shooting condition includes that a preset positional relationship is satisfied between the shooting object and the shooting device;

accordingly, the processing module 620 includes:

the control unit is used for controlling the shooting object and/or the shooting device to move in the shooting scene until the shooting object and the shooting device meet the preset position relation; wherein the moving operation comprises a translation operation and/or a rotation operation.

In one embodiment, the preset photographing condition includes that a color of a first object in the photographing scene is a designated color; the first object includes a shooting background;

accordingly, the processing module 620 includes:

a positioning unit for positioning a photographic subject from a photographic scene;

the image segmentation unit is used for carrying out image segmentation processing on the shooting object and other objects except the shooting object in the shooting scene to obtain an image of a first object;

an identifying unit for identifying a color of the image of the first object as a designated color.

In one embodiment, the apparatus 600 further comprises:

the device comprises a first determining module, a second determining module and a shooting module, wherein the first determining module is used for determining a first shooting parameter corresponding to the current shooting environment according to the corresponding relation between the preset shooting environment and the shooting parameter of the shooting device before shooting a shooting object in a shooting scene;

In one embodiment, the apparatus 600 further comprises:

the second determining module is used for determining the corresponding pixel information of the shooting object in the first image before uploading the first image to the cloud for storage;

the marking module is used for marking the mapping relation between the pixel information and the key information of the shooting object in the first image; the key information comprises the name and/or the keyword of the shooting object.

In one embodiment, the apparatus 600 further comprises:

the image processing module is used for shooting a shooting object in a shooting scene, obtaining a first image of the shooting object, and then carrying out image processing on the first image to obtain a second image; wherein the image processing comprises at least one of image cutting, light effect processing and color processing;

correspondingly, the uploading module comprises:

and the uploading unit is used for uploading the second image to the cloud for storage.

By adopting the device of one or more embodiments of the specification, the illumination environment in the shooting scene can be automatically constructed by controlling the starting of the light source in the shooting scene and adjusting the working parameters of the light source; the shot object and/or the shot scene are/is preprocessed, so that the shot object and/or the shot scene meet the preset shooting condition, and therefore shooting preparation can be automatically made before shooting without manual participation; then, the shooting object is shot under the condition that the shooting object and/or the shooting scene meet the preset shooting conditions, a first image of the shooting object is obtained, and the first image is uploaded to a cloud end to be stored. Therefore, the technical scheme realizes full-automatic image acquisition, and the whole image acquisition process does not need manual participation, so that a large amount of human resources are saved, and the image acquisition efficiency is improved.

It should be understood by those skilled in the art that the image capturing apparatus can be used to implement the image capturing method described above, wherein the detailed description is similar to the above method, and is not repeated herein to avoid complexity.

Based on the same idea, one or more embodiments of the present specification further provide an image capturing apparatus, as shown in fig. 7. The image capturing devices may vary greatly in configuration or performance, and may include one or more processors 701 and memory 702, where the memory 702 may store one or more stored applications or data. Memory 702 may be, among other things, transient storage or persistent storage. The application program stored in memory 702 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for the image acquisition device. Still further, the processor 701 may be configured to communicate with the memory 702 to execute a series of computer-executable instructions in the memory 702 on the image capture device. The image capture device may also include one or more power supplies 703, one or more wired or wireless network interfaces 704, one or more input-output interfaces 705, and one or more keyboards 706.

In particular, in this embodiment, the image capture device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the image capture device, and the one or more programs configured for execution by the one or more processors include computer-executable instructions for:

and uploading the first image to a cloud for storage.

Optionally, the preset shooting condition includes that the shooting object and the shooting device meet a preset position relationship;

accordingly, the computer executable instructions, when executed, may further cause the processor to:

Optionally, the preset shooting condition includes that the color of the first object in the shooting scene is a designated color; the first object includes a shooting background;

positioning the photographic object from the photographic scene;

identifying a color of an image of the first object as the specified color.

Optionally, the computer executable instructions, when executed, may further cause the processor to:

and uploading the second image to a cloud for storage.

One or more embodiments of the present specification also propose a computer-readable storage medium storing one or more programs, the one or more programs including instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the above-mentioned image acquisition method, and in particular to perform:

and uploading the first image to a cloud for storage.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the various elements may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.

One skilled in the art will recognize that one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

One or more embodiments of the present specification are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only one or more embodiments of the present disclosure, and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of claims of one or more embodiments of the present specification.

Claims

1. An image acquisition apparatus comprising:

a controllable light source for providing illumination in a shooting scene;

the processor is further configured to pre-process a photographic object and/or the photographic scene so that the photographic object and/or the photographic scene meet a preset photographic condition, position the photographic object from the photographic scene, perform background segmentation on the photographic object and a photographic background in the photographic scene, and perform color replacement on the photographic background obtained by segmentation; the preprocessing comprises moving operation, and the preset shooting condition comprises that a shooting object and a shooting device meet a preset position relation; the preset position relation is set according to the acquisition requirement of the sample image;

the shooting device is used for shooting the shooting object in the shooting scene on the basis of identifying the shooting object as a specified color in the shooting background to obtain a first image of the shooting object;

the processor is further used for determining corresponding pixel information of the shooting object in the first image; marking a mapping relation between the pixel information and the key information of the shooting object in the first image;

and the network communication device is used for uploading the marked first image to a cloud for storage.

2. The apparatus of claim 1, the processor comprising:

3. The apparatus of claim 1, the processor comprising:

4. The device of claim 1, the processor further to:

5. The apparatus according to claim 1, wherein the key information includes a name and/or a keyword of the photographic subject.

6. The device of claim 1, the processor further to:

correspondingly, the network communication device is further configured to:

and uploading the second image to a cloud for storage.

7. The apparatus of claim 1, further comprising:

a memory for storing the first image locally.

8. An image acquisition system comprising:

the image acquisition equipment is used for providing illumination in a shooting scene through the controllable light source; controlling the controllable light source to start and adjust the working parameters of the controllable light source through a processor so as to enable the working parameters of the controllable light source to accord with preset working parameters; wherein the working parameter comprises at least one of illumination intensity, illumination color and color temperature; preprocessing a shooting object and/or the shooting scene to enable the shooting object and/or the shooting scene to meet preset shooting conditions, positioning the shooting object from the shooting scene, carrying out background segmentation on the shooting object and a shooting background in the shooting scene, and carrying out color replacement on the shooting background obtained by segmentation; the shooting method comprises the steps that a shooting device shoots a shooting object in a shooting scene on the basis that the shooting object is identified as a specified color in a shooting background, and a first image of the shooting object is obtained; determining corresponding pixel information of the shooting object in the first image; marking a mapping relation between the pixel information and the key information of the shooting object in the first image; uploading the marked first image to a cloud processing device through a network communication device; the preprocessing comprises moving operation, and the preset shooting condition comprises that a shooting object and a shooting device meet a preset position relation; the preset position relation is set according to the acquisition requirement of the sample image;

the cloud processing device is used for receiving the first image which is sent by the image acquisition equipment and is marked; and storing the first image.

9. An image acquisition method is applied to an image acquisition device and comprises the following steps:

preprocessing a shooting object and/or the shooting scene to enable the shooting object and/or the shooting scene to meet preset shooting conditions, positioning the shooting object from the shooting scene, carrying out background segmentation on the shooting object and a shooting background in the shooting scene, and carrying out color replacement on the shooting background obtained by segmentation; the preprocessing comprises moving operation, and the preset shooting condition comprises that a shooting object and a shooting device meet a preset position relation; the preset position relation is set according to the acquisition requirement of the sample image;

on the basis that the shooting object is identified as a specified color in the shooting background, shooting the shooting object in the shooting scene to obtain a first image of the shooting object;

determining corresponding pixel information of the shooting object in the first image; marking a mapping relation between the pixel information and the key information of the shooting object in the first image;

and uploading the marked first image to a cloud for storage.

10. The method of claim 9, the pre-processing the photographic subject and/or the photographic scene, comprising:

11. The method of claim 9, wherein the preset shooting condition comprises that the color of a first object in the shooting scene is a specified color; the first object includes a shooting background;

correspondingly, the positioning the photographic object from the photographic scene, performing background segmentation on the photographic object and a photographic background in the photographic scene, and performing color replacement on the photographic background obtained by segmentation includes:

positioning the photographic object from the photographic scene;

identifying a color of an image of the first object as the specified color.

12. The method of claim 9, prior to photographing the photographic subject in the photographic scene, further comprising:

13. The method according to claim 9, wherein the key information includes a name and/or a keyword of the photographic subject.

14. The method of claim 9, further comprising, after capturing the photographic subject in the capture scene and obtaining the first image of the photographic subject:

correspondingly, the uploading the first image to a cloud for storage includes:

and uploading the second image to a cloud for storage.

15. An image acquisition device is applied to an image acquisition device and comprises:

the processing module is used for preprocessing a shooting object and/or the shooting scene to enable the shooting object and/or the shooting scene to meet preset shooting conditions, positioning the shooting object from the shooting scene, carrying out background segmentation on the shooting object and a shooting background in the shooting scene, and carrying out color replacement on the shooting background obtained by segmentation; the preprocessing comprises moving operation, and the preset shooting condition comprises that a shooting object and a shooting device meet a preset position relation; the preset position relation is set according to the acquisition requirement of the sample image;

the shooting module is used for shooting the shooting object in the shooting scene on the basis of identifying the shooting object as a specified color in the shooting background to obtain a first image of the shooting object;

the processing module is further used for determining corresponding pixel information of the shooting object in the first image; marking a mapping relation between the pixel information and the key information of the shooting object in the first image;

and the uploading module is used for uploading the first image to a cloud for storage after marking.

16. The apparatus of claim 15, the processing module comprising:

17. The apparatus of claim 15, wherein the preset shooting condition comprises that a color of a first object in the shooting scene is a designated color; the first object includes a shooting background;

correspondingly, the processing module comprises:

18. The apparatus of claim 15, further comprising:

19. The apparatus of claim 15, wherein the key information comprises a name and/or a keyword of the photographic subject.

20. The apparatus of claim 15, further comprising:

correspondingly, the uploading module comprises:

21. An image acquisition apparatus comprising:

a processor; and

and uploading the marked first image to a cloud for storage.

22. A storage medium storing computer-executable instructions that, when executed, implement the following:

and uploading the marked first image to a cloud for storage.