WO2019000119A1 - Lighting correction method and apparatus - Google Patents

Abstract

A lighting correction method, the method comprising: collecting an image of a detection object under light source illumination (S11); at least using the image of the detection object to position the detection object in order to acquire the spatial position of the detection object (S12); using the spatial position of the detected object and pre-acquired light source light field information to acquire the light field distribution on the visible surface of the detected object (S13); and on the basis of the light field distribution, performing lighting correction of the image of the detected object (S14). Also disclosed is a lighting correction apparatus. The present method can reduce the impact of uneven lighting on an image, such that the error between the image and the actual detection object is reduced, thus improving the accuracy of industrial visual detection.

Description

Light correction method and device [Technical Field]

The present invention relates to the field of industrial vision technology, and in particular, to a light correction method and apparatus.

【Background technique】

Industrial visual inspection is an emerging detection method that achieves the required detection purpose by analyzing and calculating the characteristics of pixels, brightness, and color of the image of the object to be detected collected by the machine vision device. Industrial vision systems typically include a light source, an image acquisition device, an image processing device, a monitor, and the like.

The light source is an important factor affecting the industrial visual inspection effect, which directly affects the quality and effect of the image acquired by the image acquisition device. The ideal light source should be evenly illuminated on the surface of the test object. However, in practical applications, the ideal light source does not exist, and it can only be moved closer to the ideal light source by the shape and layout of the light source. That is to say, the actual light source is unevenly illuminated on the surface of the detection object, which affects the quality and effect of the acquired image, so that there is an error between the acquired image and the actual detected object, thereby reducing the accuracy of industrial visual inspection. .

[Summary of the Invention]

In view of the above, the present invention provides a lighting correction method and apparatus, which can solve the problem that the accuracy of industrial vision detection is reduced due to uneven illumination of the light source on the surface of the detection object in the prior art.

In order to solve the above problems, the present invention provides a lighting correction method, the method comprising: collecting an image of a detection object under illumination by a light source; and positioning the detection object by using at least an image of the detection object to obtain a spatial position of the detection object; The spatial position of the detection object and the light field information of the light source acquired in advance acquire the light field distribution of the visible surface of the detection object; and the image of the detection object is polished according to the light field distribution.

The method for acquiring the light field information of the pre-acquired light source includes: collecting an image of the calibration plate under the illumination of the light source; and acquiring the incident light of the spatial position where the reflective region is located according to the image of the calibration plate and the reflectivity of the reflective area on the calibration plate. Strong; at least the light field information of the light source is obtained by using the incident light intensity.

The incident light intensity of obtaining the spatial position of the reflective area according to the image of the calibration plate and the reflectivity of the reflective area on the calibration plate includes: positioning the reflective area according to the image of the calibration plate to obtain a spatial position where the reflective area is located; according to the calibration plate The grayscale value of the reflection area in the image acquires the reflected light intensity of the reflection area; and the incident light intensity of the spatial position where the reflection area is located is obtained according to the reflected light intensity and the reflectance of the reflection area.

The positioning of the reflective area according to the image of the calibration plate to obtain the spatial position of the reflective area includes: positioning the calibration plate according to the image of the calibration plate to obtain spatial position information of the calibration plate; and distributing according to the reflective area on the calibration plate. The information and the spatial position information of the calibration plate determine the spatial location of the reflective area.

Wherein, obtaining the light field information of the light source by using at least the incident light intensity comprises: acquiring the light field information of the light source by using the incident light intensity and the radiation model corresponding to the light source.

Wherein, at least obtaining the light field information of the light source by using the incident light intensity further comprises: establishing a corresponding radiation model for the light source.

Wherein, the light source comprises a line light source and/or a surface light source, and the corresponding radiation model for the light source comprises: equalizing the line source/area source into a plurality of point sources; establishing a corresponding radiation model for each equivalent point source; The set of radiation models for all equivalent point sources is used as the radiation model for the line source/area source.

Wherein, the line source/area source is equivalent to a plurality of point sources including: collecting an image of the line source/area source; and confirming the outgoing light intensity distribution of the line source/area source according to the image of the line source/area source; according to the outgoing light intensity The distribution equalizes the line source/area source to multiple point sources.

Wherein, the light field information includes at least the intensity of the outgoing light in each visible direction of each light source.

Wherein, before acquiring the incident light intensity of the spatial position where the reflective region is located according to the image of the calibration plate and the reflectance of the reflective region on the calibration plate, the method further includes: acquiring a reflectance in at least one direction of the reflective region.

The obtaining the reflectance in the at least one direction of the reflective region includes: detecting a bidirectional reflection distribution function of the reflective region to obtain an isotropic reflectance of the reflective region.

The performing the lighting correction on the image of the detection object according to the light field distribution includes: adjusting the grayscale value of the pixel corresponding to the detection object in the image according to the light field distribution, so that the light field corresponding to the adjusted grayscale value is adjusted Evenly distributed.

Wherein, at least the positioning of the detection object by the image of the detection object to acquire the spatial position of the detection object includes acquiring the spatial position of the detection object by using the depth image of the detection object and/or the stereo model information in combination with the image of the detection object.

The present invention also provides a light-lighting correction apparatus, the apparatus comprising: a processor and a memory, the memory storing instructions for executing the instructions to implement any of the methods provided above.

The present invention also provides a readable storage medium storing instructions that, when executed, implement any of the methods provided above.

With the above solution, the beneficial effects of the present invention are: different from the prior art, the present invention uses the spatial position of the detection object and the light field information of the light source obtained in advance to acquire the light field distribution of the visible surface of the detection object; The image of the object is polished to reduce the influence of uneven illumination on the image, so that the error between the image and the actual detected object is reduced, thereby improving the accuracy of industrial visual inspection.

[Description of the Drawings]

In order to explain the technical solution in the embodiment of the present invention more clearly, the following describes the embodiment. BRIEF DESCRIPTION OF THE DRAWINGS The drawings used in the following description are briefly introduced. It is obvious that the drawings in the following description are only some embodiments of the present invention, and those skilled in the art can also perform without creative work. Other figures are obtained from these figures. among them:

1 is a schematic flow chart of a first embodiment of a lighting correction method of the present invention;

2 is a schematic flow chart of a second embodiment of the polishing correction method of the present invention;

3 is a schematic flow chart of a third embodiment of the lighting correction method of the present invention;

4 is a schematic flow chart of positioning a reflective area in an embodiment of the lighting correction method of the present invention;

5 is a schematic flow chart of a fourth embodiment of the lighting correction method of the present invention;

6 is a schematic flow chart of a fifth embodiment of the lighting correction method of the present invention;

7 is a schematic flow chart of a sixth embodiment of the lighting correction method of the present invention;

FIG. 8 is a schematic diagram of calibration of a reflective area in an embodiment of the lighting correction method of the present invention; FIG.

Figure 9 is a schematic structural view of a first embodiment of the lighting correction device of the present invention;

Figure 10 is a block diagram showing the structure of a second embodiment of the lighting correction device of the present invention.

【Detailed ways】

The technical solutions in the embodiments of the present invention will be clearly and completely described in the following with reference to the accompanying drawings. Any of the following embodiments that do not conflict with each other can be arbitrarily combined. It will be apparent that the described embodiments are merely a sub-area embodiment of the invention, rather than a full-area embodiment. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without departing from the inventive scope are the scope of the present invention.

As shown in FIG. 1, the first embodiment of the lighting correction method of the present invention includes:

S11: Acquire an image of the detection object under illumination of the light source.

Controlling an image capturing device, such as a camera, a camera, etc., to collect a detected object under illumination of a light source image. The image capture device can perform photographing to capture an image of the detected object when the detected object enters its own field of view.

S12: Position the detection object by using at least the image of the detection object to obtain the spatial position of the detection object.

Since the spatial position of the detection object is for the subsequent illumination correction of the surface of the detection object, at least the spatial coordinates of the visible surface of the detection object should be included, which can be represented by the visible surface contour shape of the detection object and the spatial coordinates of the key points. Of course, it can also be expressed by detecting the complete surface contour shape of the object and the spatial coordinates of the key points. The visible surface refers to the surface of the detected object in the acquired image.

The detection object can be identified based on the image of the detection object to acquire the coordinates of the visible surface of the detection object. Since the image of the detection object is a plane image taken from a certain angle, the coordinates obtained by the recognition are only the coordinates in the plane image, and the spatial information on all dimensions of the detection object cannot be completely reflected, and it may be necessary to obtain the detection object in combination with other information. The location of the space.

In one embodiment of the present invention, the spatial position of the detected object is acquired by using the image of the detected object in combination with the depth image and/or the stereo model information of the detected object. The depth image is obtained by acquiring a detection object using a depth sensor, and includes detecting a depth value of each part of the object, that is, a distance from the depth sensor. Depending on the depth value of the detected object, the coordinates in the image and depth image, and the position and parameters of the depth sensor and image acquisition device (including the size and resolution of the graphics sensor therein), the spatial position of the detected object can be calculated. The stereo model information generally includes the shape of the detected object and the size information in each dimension. According to the size of the detection object in the image and its actual size, the distance of the detection object relative to the image acquisition device can be calculated according to the parameters of the image acquisition device, and then combined with the position of the image acquisition device and the stereo model information of the detection object, the calculation can be calculated. Detects the spatial location of the object.

In other embodiments, if the distance between the detection object and the image acquisition device is known, If the detection object is transmitted on the marked pipeline, the marker is used to indicate the distance from the image acquisition device, then the distance between the detection object and the image acquisition device and the image acquisition device are detected according to the coordinates of the detection object in the image. The position and parameters can be used to calculate the spatial position of the detected object.

S13: Acquire a light field distribution of the visible surface of the detection object by using the spatial position of the detection object and the light field information of the light source acquired in advance.

In general, detecting the light field distribution of the visible surface of the object includes detecting the intensity of the incident light of portions of the visible surface of the object, and the light field information of the light source includes the intensity of the outgoing light for each visible direction of each light source.

Under the rule state (the light field information of the light source and the visible surface of the detection object can be represented by a function), the light field distribution of the visible surface of the detection object can be calculated according to the light field function of the light source and the visible surface function of the detection object. In an irregular state (at least one of the light field information of the light source and the visible surface of the detection object cannot be represented by a function), the visible surface of the detection object may be divided into a plurality of parts, according to the spatial position of the detection object and the known The position of each light source can calculate the distance between each part of the visible surface of the detection object relative to each light source, and combine the light attenuation coefficient (generally constant) and the light attenuation model of the light propagation medium between the light source and the detection object, and can calculate The intensity of incident light. For example, there is only one light source, and the distance between a certain portion of the visible surface of the detection object relative to the light source is d, the light intensity of the light source in the direction is I ₀ , and the light attenuation coefficient is α, then the incident light of the portion Intensity I = I ₀ *exp(-α*d).

In the acquired image, the visible surface of the detection object is composed of a plurality of pixel points. In order to facilitate subsequent illumination correction, in an irregular state, the visible surface of the detection object may be correspondingly divided according to the distribution of the pixel points. Each of the divided portions corresponds to a plurality of adjacent pixels in the image. Of course, other methods can be used to divide the visible surface of the detected object.

S14: Perform light correction on the image of the detection object according to the light field distribution.

The grayscale value of each pixel corresponding to the detected object in the image reflects the reflection of the visible surface of the detected object. The intensity of the light, the intensity of the reflected light is proportional to the intensity of the incident light. Therefore, according to the light field distribution obtained in S13, the image of the detection object can be corrected accordingly, and the gray scale of at least part of the pixel corresponding to the detection object is adjusted. The value, the uniformity of the light field of the detected object in the image after the light correction is improved.

For example, there are n pixels corresponding to the detection object in the original image, and the gray scale values are {g ₁ , g ₂ , . . . g _n }, and the corresponding light field distribution is {i ₁ , i ₂ , . . . i _n } The adjusted grayscale values are {G ₁ , G ₂ , . . . G _n }, G _j =min{int(I _j *g _j /i _j ), m}, j=1, 2, . . . , n. Wherein I _j represents the light intensity after the adjustment of the jth pixel point, int (·) represents an integer, and m is the maximum value of the gray scale value. The adjusted light field distribution {I ₁ , I ₂ , ... I _n } is higher than the uniformity of the light field distribution of the original image, and generally shows that the variance/standard deviation of {I ₁ , I ₂ , ... I _n } is smaller than The variance/standard deviation of {i ₁ , i ₂ ,...i _n }. If I _i is equal to the same constant for all the pixels of the corresponding detection object, the adjusted light field is evenly distributed. In this example, adjusting the grayscale value by multiplying the coefficient obtained according to the light field distribution is only an indication, and other methods may be used to adjust the grayscale value according to the light field distribution.

Through the implementation of the above embodiment, the light field distribution of the visible surface of the detection object is acquired by using the spatial position of the detection object and the light field information of the light source acquired in advance, and the image of the detection object is corrected according to the light field distribution, and the light correction is not only corrected. It can resist the unevenness of the light field of the visible surface of the detected object in a single image, and can also resist the difference of the light field when the detected object is located at different positions in different images, and reduce the influence of the uneven illumination on the image, so that the image and the actual detected object The error between the two is reduced, thereby improving the accuracy of industrial visual inspection.

As shown in FIG. 2, the second embodiment of the lighting correction method of the present invention is based on the first embodiment of the lighting correction method of the present invention, and the method for acquiring the light field information of the light source includes:

S21: Acquire an image of the calibration plate under illumination of the light source.

The image capturing device is controlled to collect an image of the calibration plate under illumination by the light source. The image capturing device in this step is the same as the image capturing device used in step S11, and the light source is the light source in step S11. Figure The same as the acquisition device generally means that the image acquisition devices used twice are of the same or the same type and are installed at the same position and angle.

The calibration plate has at least one reflective area, and the reflective area can reflect the incident light, and the color thereof is not pure black. To avoid the influence of the ambient color temperature, the color of the reflective area is generally white or gray. In order to distinguish from the environment to reduce the difficulty of recognition, the calibration plate may have a black non-reflective area in addition to the reflective area. The reflective area and the non-reflective area may be combined to form a specific pattern for positioning, such as a black-and-white/black-gray/black-and-white gray interlaced grid pattern. If there are more than one reflective area on the calibration plate, non-reflective areas may be provided between the different reflective areas for spacing.

S22: Obtain an incident light intensity at a spatial position where the reflective region is located according to an image of the calibration plate and a reflectance of the reflective region on the calibration plate.

Before performing this step, you need to obtain the reflectance in at least one direction of the reflective area on the calibration plate. If the reflectivity of the reflective region is isotropic, that is, the reflectance is independent of the incident light angle, then the incident light intensity is not required to take into account the angle of the incident light; if the reflectivity of the reflective region is not isotropic, then the calculation is performed. When the incident light intensity is taken, the angle of the incident light needs to be considered, and the angle of the incident light can be calculated according to the spatial position of the reflective region and the spatial position of the light source.

S23: Acquire at least the light field information of the light source by using the incident light intensity.

The light field information of the resulting light source needs to be stored for subsequent illumination correction of the image of the detected object.

If the calibration plate can be moved such that its reflective area covers each portion of the field of view of the image capture device and the first two steps are repeated each time the calibration plate is moved, the incident light intensity of each portion of the field of view can be taken as Light field information of the light source. Because of the sheer volume of data, consider modeling the relationship between incident light intensity and spatial location to reduce the amount of storage space. Moving the calibration plate includes translating and/or rotating the calibration plate to change the spatial position of the calibration plate.

The above method requires a very large workload. In order to reduce the workload, in one embodiment of the invention, the light field information of the light source is obtained by using the radiation model corresponding to the light source and the acquired incident light intensity. The radiation model corresponding to the light source may be its theoretical radiation model or a radiation model established according to the characteristics of the actual light source.

The radiation model corresponding to the light source generally includes at least the relationship between the intensity of the outgoing light of the light source and the direction, and may also include an attenuation model of the outgoing light during propagation. The calibration plate is moved and the first two steps are repeated several times. The unknown parameters in the radiation model of the light source are calculated according to the incident light intensity at different spatial positions, and the intensity of the light emitted by the light source in each visible direction can be obtained. The light field information of the light source includes at least the intensity of the emitted light in each visible direction, and may also include an attenuation model of the outgoing light during the propagation. If the number of light sources is greater than one, in order to simplify the model and reduce the amount of calculation, you can choose to measure independently for each light source.

Through the implementation of the above embodiment, the light field of the light source is calibrated using a calibration plate of the reflectance of the known reflection region, and the light field information of the light source can be acquired for subsequent illumination correction.

As shown in FIG. 3, the third embodiment of the lighting correction method of the present invention is based on the second embodiment of the lighting correction method of the present invention, and step S22 includes:

S221: Position the reflective area according to the image of the calibration plate to obtain the spatial position where the reflective area is located.

The coordinates of the reflection area can be identified according to the image of the calibration plate. Combined with the actual size of the reflection area, the position and parameters of the image acquisition device, the spatial coordinates of the spatial position where the reflection area is located can be calculated to realize the positioning of the reflection area.

The reflective area can be directly positioned, or the calibration plate can be positioned first and then the spatial position of the reflective area can be confirmed according to the spatial position of the calibration plate. If the number of reflective regions is greater than one, you can also choose to locate one of the reflective regions first, and then combine the distribution of the reflective regions to determine other The spatial location of the reflective area.

As shown in FIG. 4, in an embodiment of the lighting correction method of the present invention, step S221 specifically includes:

S2211: Position the calibration plate according to the image of the calibration plate to obtain spatial position information of the calibration plate.

S2212: Determine a spatial position where the reflective area is located according to the distribution information of the reflective area on the calibration plate and the spatial position information of the calibration plate.

In this embodiment, the calibration plate is first positioned, and then the spatial position of the reflective region is determined according to the spatial position of the calibration plate and the distribution information of the known reflective region on the calibration plate. When the number of reflective regions is greater than one, The identification and positioning process of different reflective regions can be omitted, especially in the case where the number of reflective regions is large, the calculation amount can be effectively reduced.

S222: Acquire a reflected light intensity of the reflective area according to a grayscale value of the reflective area in the image of the calibration plate.

The magnitude of the grayscale value reflects the reflected light intensity of the reflective area under illumination from the source. The gray scale value can be directly used to indicate the reflected light intensity, and the gray scale value can be processed to some extent, for example, after the normalization process to represent the reflected light intensity.

S223: Acquire an incident light intensity at a spatial position where the reflective region is located according to the reflected light intensity and the reflectance of the reflective region.

The reflected light intensity is I _R and the reflectance is r, then the incident light intensity I _i =I _R /r. If the reflectance of the reflective region is isotropic, the reflectance r is constant. If the reflectance of the reflective region is not isotropic, the reflectance r is related to the angle of the incident light, and the angle of the incident light is calculated to obtain the angle. Reflectivity. You can calculate the connection between the two based on the spatial coordinates of the light source (if it is the line source/surface source, its center point) and the coordinates of the specified point (such as the center point) in the reflection area, such as the horizontal plane / The angle θ _{1 of the} vertical plane can calculate the angle θ ₂ of the reflection area with respect to the plane according to the spatial position of the reflection area, and the incident light angle (the angle between the incident light and the reflection area) θ ₃ =| θ ₁ -θ ₂ |.

As shown in FIG. 5, the fourth embodiment of the lighting correction method of the present invention is based on the second embodiment of the lighting correction method of the present invention. When acquiring the light field information of the light source, the radiation model of the light source is required. Further before S22, it includes:

S24: Establish a corresponding radiation model for the light source.

The types of light sources generally include point light sources, line light sources, surface light sources and combinations thereof. The theoretical radiation model of point light source/line light source/surface light source is based on the uniform distribution of the emitted light on the light-emitting point/line/surface. In practical applications, due to the non-uniformity of the light-emitting elements and/or the light-mixing materials, the outgoing light of the point source/line source/area source is often not uniformly distributed. In order to further improve the accuracy of the light source light field information, it is possible to select a corresponding radiation model for the light source. In the subsequent steps, the actual radiation model established in this step can be used to combine the incident light intensity of the reflection region to obtain the light field information of the light source.

As shown in FIG. 6 , the fifth embodiment of the lighting correction method of the present invention is based on the fourth embodiment of the lighting correction method of the present invention. The light source includes a line source and/or a surface light source, and step S24 specifically includes:

S241: Acquire an image of a line source/area source.

The camera is facing the line/surface of the line source/area source to capture its image. The camera used here is not necessarily the same as the image acquisition device previously used to acquire the detected object/calibration plate image.

S242: Confirm the output light intensity distribution of the line light source/surface light source according to the image of the line light source/surface light source.

The emission light intensity distribution is confirmed according to the gray scale value distribution of the pixel points of the corresponding line light source/surface light source in the image. In general, the larger the grayscale value, the higher the corresponding light intensity.

S243: The line source/area source is equivalent to a plurality of point sources according to the output intensity distribution.

The line source/area source can be divided into multiple parts according to the output intensity distribution, and the degree of dispersion of the outgoing light intensity in the same part (which can be expressed by the variance or standard deviation of the gray scale value) should be less than the preset first threshold. The difference between the average values of the outgoing light intensities of the adjacent portions is greater than a preset second threshold. For each part that is divided, you can choose to directly equivalent it to a little light source; you can also choose to make it according to its area. Dividing again, that is, the portion whose area is less than or equal to the third threshold is directly equivalent to the point source, and the portion having the area larger than the third threshold is again divided into at least two sub-sections whose area is less than or equal to the third threshold, and each sub-section is Equivalent to a point source.

S244: Establish a corresponding radiation model for each equivalent point source.

The theoretical model of the point source can be used as its corresponding radiation model, and the corresponding radiation model can be established according to the light intensity distribution of the point source obtained in S202.

S245: A set of radiation models of all equivalent point sources is used as a radiation model of the line source/area source.

For a line source/area source equivalent to a plurality of point sources, when the light field information of the line source/area source is acquired in combination with the incident light intensity of the reflection area, the line source/area source may be selected to be integrally controlled, or may be selected. Independently controlling each of the line source/area source sources, for example, adding an optical device to the line source/area source according to an equivalent result, the device partially transmits light, and the remaining portion is shielded from light, and the device is controlled to transmit light. The position and size of the part correspond to the currently controlled equivalent point source.

In this embodiment, the line source/area source is equivalent to a plurality of point sources according to the outgoing light intensity distribution of the line source/area source. In other embodiments, it is also possible to simply divide the line source/area source into a plurality of sections, each section being equivalent to a point source. Compared with the two, the radiation model of the point source equivalent in this embodiment is closer to the ideal model, and the actual model of the equivalent point source can also be used, and the radiation model of the obtained line source/area source is more accurate.

As shown in FIG. 7, the sixth embodiment of the lighting correction method of the present invention is based on the second embodiment of the lighting correction method of the present invention. Before step S22, the method further includes:

S25: Detect a bidirectional reflection distribution function of the reflection area to obtain an isotropic reflectance of the reflection area.

This process can also be referred to as the calibration of the reflective area on the calibration plate. Bidirectional Reflectance Distribution Function (BRDF) defines a given incident direction How the irradiance affects the radiance in a given exit direction, ie how the incident ray is distributed in each direction of the exit after being reflected by a surface. According to the BRDF, the reflectivity of the reflective region can be obtained. For example, as shown in FIG. 8 , the reflection area in the lower right corner of the calibration plate in the left half of the figure is calibrated, and the reflection light is irradiated from various angles with incident light of a known light intensity to measure the reflected light intensity and the reflected light intensity. Dividing the incident light intensity as the reflectance at the current angle, an image of the reflectance-angle in the lower right corner of the figure can be drawn, and the image can represent the reflectance of the reflective region.

Since the calibration process of the reflective area on the calibration plate is very cumbersome, the reflective area of the specular or diffuse material can be used. Since the BRDF model of the specular/diffuse material is known, a few measurements can determine the reflection of the reflected area. Rate, which simplifies the process. In addition, if the number of reflective regions on the calibration plate is greater than one and the uniformity of different reflective regions is good, only one reflective region can be calibrated, and the obtained reflectances are used as the reflectances of all reflective regions.

This step can be performed completely every time the light source field is calibrated; it can also be selected to be performed only once (for example, at the factory or during the initial calibration of the source light field), and used directly in the calibration source light field. The obtained isotropic reflectance, or select several angles for sampling, and verify that the obtained isotropic reflectance is correct before use.

As shown in FIG. 9, the first embodiment of the lighting correction device of the present invention comprises a processor 110 and a memory 120, and the processor 110 is connected to the memory 120.

The memory 120 is used for instructions and data required for the operation of the processor 110.

The processor 110 controls the operation of the lighting correction device, and the processor 110 may also be referred to as a CPU (Central Processing Unit). Processor 110 may be an integrated circuit chip with signal processing capabilities. The processor 110 can also be a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, and discrete hardware components. . A general purpose processor can be a microprocessor or The processor can also be any conventional processor or the like.

The processor 110 is operative to execute instructions stored in the memory 120 to implement any of the embodiments of the present illumination correction method and the methods provided by the non-conflicting combination.

The lighting correction device may be a separate device in the industrial vision system, disposed between the image acquisition device and the image processing device, or may be integrated with the image processing device.

As shown in FIG. 10, a first embodiment of the readable storage medium of the present invention includes a memory 210. The memory 210 stores instructions that, when executed, implement the methods provided by any of the embodiments of the lighting correction method of the present invention and combinations that do not conflict.

The memory 210 may include a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk, an optical disk, and the like.

The above is only the embodiment of the present invention, and is not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformations made by the description of the invention and the drawings are directly or indirectly applied to other related technologies. The fields are all included in the scope of patent protection of the present invention.

Claims (15)

A lighting correction method, comprising: Collecting an image of the detection object under illumination by the light source; Positioning the detection object by using at least the image of the detection object to obtain a spatial location of the detection object; Acquiring, by using the spatial position of the detection object and the light field information of the light source acquired in advance, a light field distribution of the surface of the detection object illuminated by the light source; Performing a light correction on the image of the detection object according to the light field distribution. The method according to claim 1, wherein the acquiring the light field information of the pre-acquired light source comprises: Acquiring an image of the calibration plate under illumination by the light source; Acquiring an incident light intensity of a spatial position where the reflective area is located according to an image of the calibration plate and a reflectivity of a reflective area on the calibration plate; The light field information of the light source is acquired using at least the incident light intensity. The method according to claim 2, wherein the obtaining the incident light intensity of the spatial position of the reflective area according to the image of the calibration plate and the reflectance of the reflective area on the calibration plate comprises: Positioning the reflective area according to an image of the calibration plate to obtain a spatial location where the reflective area is located; Obtaining a reflected light intensity of the reflective area according to a grayscale value of the reflective area in an image of the calibration plate; Obtaining a space where the reflective area is located according to the reflected light intensity and the reflectance of the reflective area The incident light intensity at the location. The method of claim 3 wherein: The positioning of the reflective area according to the image of the calibration plate to obtain the spatial location of the reflective area includes: Positioning the calibration plate according to an image of the calibration plate to obtain spatial position information of the calibration plate; Determining a spatial position of the reflective area according to the distribution information of the reflective area on the calibration plate and the spatial position information of the calibration plate. The method of claim 2 wherein: The acquiring the light field information of the light source by using the incident light intensity includes: The light field information of the light source is obtained by using the incident light intensity and a radiation model corresponding to the light source. The method of claim 5 wherein: Before the obtaining the light field information of the light source by using the incident light intensity, the method further includes: Establishing the corresponding radiation model for the light source for acquiring light field information of the light source in combination with the incident light intensity. The method of claim 6 wherein: The light source includes a line source and/or a surface light source, and the establishing the corresponding radiation model for the light source includes: The line source/area source is equivalent to a plurality of point sources; Establishing a corresponding radiation model for each of the equivalent point sources; A set of radiation models of all of the equivalent point sources is used as a radiation model of the line source/area source. The method of claim 7 wherein: The equivalent of the line source/area source to a plurality of point sources includes: Acquiring an image of the line source/area source; Determining, according to the image of the line source/area source, an outgoing light intensity distribution of the line source/area source; The line source/area source is equivalent to a plurality of point sources according to the outgoing light intensity distribution. The method of claim 5 wherein: The light field information includes at least an intensity of the outgoing light in each visible direction of each of the light sources. The method of claim 2 wherein: The obtaining, according to the image of the calibration plate and the reflectance of the reflective area on the calibration plate, the incident light intensity of the spatial position where the reflective area is located, further includes: Obtaining a reflectance in at least one direction of the reflective area. The method of claim 10 wherein: The obtaining the reflectance in the at least one direction of the reflective area comprises: detecting a bidirectional reflection distribution function of the reflective area to obtain an isotropic reflectance of the reflective area. The method according to any one of claims 1 to 11, wherein The performing light correction on the image of the detection object according to the light field distribution includes: And adjusting the grayscale value of the pixel corresponding to the detection object in the image according to the light field distribution, so that the light field corresponding to the adjusted grayscale value is evenly distributed. The method according to any one of claims 1 to 11, wherein The positioning of the detection object by using the image of the detection object to obtain the spatial location of the detection object includes: The spatial position of the detection object is acquired by using the depth image and/or the stereo model information of the detection object in combination with the image of the detection object. A light correction device, comprising: a processor and a memory, the storing The processor stores instructions for executing the instructions to implement the method of any of claims 1-13. A readable storage medium storing instructions, wherein the instructions are executed to implement the method of any of claims 1-13.

Images