Image processing method, system, automatic walking device and readable storage medium

Abstract

The present invention discloses an image processing method, system, automatic walking device and readable storage medium, wherein the image processing method comprises the following steps: preprocessing the original image to identify each pixel as a bright area pixel or a dark area pixel, and extracting the initial H channel eigenvalue, initial S channel eigenvalue and initial V channel eigenvalue of each pixel; calculating the average pixel brightness intensity ValueB of the bright area and the average pixel brightness intensity ValueS of the dark area; obtaining the brightness compensation value OffsetValue according to the average pixel brightness intensity of the bright area and the average pixel brightness intensity of the dark area; compensating the initial V channel eigenvalue according to the brightness compensation value to obtain the compensated V channel eigenvalue; synthesizing and converting the initial H channel eigenvalue, the initial S channel eigenvalue and the compensated V channel eigenvalue to obtain an image without shadow boundaries. The present invention adjusts the V channel eigenvalue by the brightness compensation value to eliminate the shadow boundary of the image, and avoids the boundary system misjudgment caused by the shadow boundary of the image.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an image processing method, system, automatic walking device and readable storage medium capable of eliminating the shadow boundary of an image. Background Art

[0002] Autonomous vehicles (such as lawn mowers and vacuum cleaners) recognize boundaries through images. However, due to lighting conditions, trees and houses will form shadow boundaries of varying degrees on the grass. Shadow boundaries are interference information for image recognition. Autonomous vehicles can easily misjudge shadow boundaries as boundaries, making it impossible for them to enter or exit the shadow area to complete their operations.

[0003] To a certain extent, shadow removal can be achieved through image enhancement, such as homomorphic filtering, histogram equalization, image enhancement based on Laplace operator, image enhancement based on logarithmic transformation, and image enhancement based on gamma transformation. For example, Chinese patent application CN201310689070.8 discloses an all-weather traffic image enhancement method based on brightness reference drift, which fully considers the relationship between the monitoring image and the light intensity and shooting time, analyzes the overall change and real-time change of the light, obtains the brightness reference curve and the brightness real-time feedback respectively, and weights to obtain the brightness reference value at the current moment. Before enhancing the traffic monitoring image, the image is first converted from the RGB color space to the HSV color space. On the basis of keeping the image chromaticity information unchanged, the brightness component is segmented using the brightness reference value to obtain the low brightness area and the high brightness area, and the drift parameters of each brightness level are obtained respectively. Each brightness level is multiplied by the drift parameter of the corresponding brightness level to obtain the enhanced brightness level, and finally the image is converted to the RGB color space to obtain the enhanced picture.

[0004] However, the threshold used for brightness area division in Chinese patent application CN201310689070.8 is a brightness reference value obtained by a brightness reference curve L(t). The algorithm of the brightness reference curve L(t) has a large amount of calculation, which affects the image processing speed. Summary of the invention

[0005] The present invention provides an image processing method, system, automatic walking equipment and readable storage medium to avoid misjudgment of a boundary system due to a shadow boundary of an image.

[0006] The present invention provides an image processing method; the method comprises the following steps:

[0007] The original image is preprocessed to identify each pixel as a bright area pixel or a dark area pixel, and an initial H channel eigenvalue, an initial S channel eigenvalue and an initial V channel eigenvalue of each pixel are extracted;

[0008] The average pixel brightness intensity ValueB in the bright area is calculated based on the initial V channel characteristic value of the pixel point in the bright area, and the average pixel brightness intensity ValueS in the dark area is calculated based on the initial V channel characteristic value of the pixel point in the dark area;

[0009] Obtain the brightness compensation value OffsetValue according to the average brightness intensity of pixels in the bright area and the average brightness intensity of pixels in the dark area;

[0010] Performing compensation processing on the initial V channel characteristic value according to the brightness compensation value to obtain a compensated V channel characteristic value;

[0011] The initial H channel eigenvalue, the initial S channel eigenvalue and the compensated V channel eigenvalue are synthesized and converted to obtain an image with the shadow boundary removed.

[0012] Optionally, the process of preprocessing the original image includes the following steps:

[0013] Get RGB image;

[0014] Convert the RGB image to an HSV image, and extract the characteristic value of each pixel in the HSV image, wherein the characteristic value includes an initial H channel characteristic value, an initial S channel characteristic value, and an initial V channel characteristic value;

[0015] Obtain an initial V channel image according to the initial V channel feature value of each pixel in the HSV image;

[0016] Binarize the initial V channel image to obtain a binary image;

[0017] It is determined whether the brightness intensity value of the pixel in the binary image is greater than a preset threshold value to identify each pixel as a bright area pixel or a dark area pixel. If the brightness intensity value of the pixel in the binary image is greater than the preset threshold value, it is a bright area pixel, and if the brightness intensity value of the pixel in the binary image is not greater than the preset threshold value, it is a dark area pixel.

[0018] Optionally, after identifying the bright area pixel points or the dark area pixel points, the method further includes:

[0019] Determine whether all pixels are bright area pixels or dark area pixels; if so, end this process; if not, continue to execute the subsequent compensation process.

[0020] Optionally, after identifying the bright area pixel points or the dark area pixel points, the method further includes:

[0021] Preprocessed pixel points are screened out according to the S channel characteristic value, wherein all bright area pixel points in the preprocessed pixel points are a first pixel point combination, and all dark area pixel points in the preprocessed pixel points are a second pixel point combination;

[0022] In the subsequent process, the bright area pixels used to calculate the average pixel brightness intensity of the bright area are the bright area pixels of the first pixel combination; the dark area pixels used to calculate the average pixel brightness intensity of the dark area are the dark area pixels of the second pixel combination.

[0023] Optionally, a plurality of brightness intensity difference segment intervals are preset, and the process of obtaining the brightness compensation value includes:

[0024] Calculate the brightness intensity difference DiffValue between the average pixel brightness intensity ValueB in the bright area and the average pixel brightness intensity ValueS in the dark area = ValueB-ValueS;

[0025] Identify the brightness intensity difference segmentation interval corresponding to the brightness intensity difference DiffValue, and select the corresponding adjustment parameter K according to the brightness intensity difference segmentation interval;

[0026] The brightness compensation value OffsetValue is obtained according to the brightness intensity difference DiffValue, the adjustment parameter K and a preset algorithm, and the preset algorithm is: OffsetValue=K*DiffValue.

[0027] Optionally, the initial V-channel characteristic values ​​of the bright area pixels and / or the dark area pixels are compensated according to the brightness compensation value, and the initial V-channel characteristic values ​​of the bright area pixels are weakened and compensated according to the brightness compensation value: the compensated V-channel characteristic value = the initial V-channel characteristic value - the brightness compensation value, and the initial V-channel characteristic value of the dark area pixels is enhanced and compensated according to the brightness compensation value: the compensated V-channel characteristic value = the initial V-channel characteristic value + the brightness compensation value.

[0028] Optionally, the synthesis processing is to obtain an HSV image with removed shadow boundaries based on H channel eigenvalues, S channel eigenvalues, and compensated V channel eigenvalues; and the conversion processing is to convert the removed shadow HSV image into an RGB image with removed shadow boundaries.

[0029] The present invention also provides an image processing system, comprising:

[0030] A preprocessing module is used to preprocess the original image to identify each pixel as a bright area pixel or a dark area pixel, and to extract an initial H channel eigenvalue, an initial S channel eigenvalue, and an initial V channel eigenvalue of each pixel;

[0031] A brightness compensation module is used to calculate the average pixel brightness intensity ValueB in the bright area according to the V channel characteristic value of the pixel point in the bright area, and calculate the average pixel brightness intensity ValueS in the dark area according to the V channel characteristic value of the pixel point in the dark area; and obtain a brightness compensation value OffsetValue according to the average pixel brightness intensity in the bright area and the average pixel brightness intensity in the dark area; and compensate the initial V channel characteristic value according to the brightness compensation value to obtain the compensated V channel characteristic value;

[0032] The image generation module is used to perform synthesis and conversion processing according to the initial H channel characteristic value, the initial S channel characteristic value and the compensated V channel characteristic value to obtain an image with the shadow boundary removed.

[0033] The present invention further provides an automatic walking device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the image processing method when executing the computer program.

[0034] The present invention further provides a readable storage medium having a computer program stored thereon, and the steps of the image processing method are implemented when the computer program is executed by a processor.

[0035] Compared with the prior art, the present invention adjusts the V channel characteristic value through the brightness compensation value to eliminate the shadow boundary of the image, thereby avoiding the boundary system misjudgment caused by the shadow boundary of the image. The present invention can compare the brightness intensity value of the pixel point in the binary image with the preset threshold value, and can identify the bright area pixel point / dark area pixel point, and the value range of the preset threshold value is not limited. The preset algorithm set in the present invention has a small amount of calculation and a fast image processing speed. The present invention sets the brightness intensity difference segmentation interval, and obtains different brightness compensation values ​​by identifying the brightness intensity difference and the brightness intensity difference segmentation interval, thereby achieving an adaptive compensation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flow chart of a first embodiment of an image processing method of the present invention;

[0037] Figure 2 for Figure 1 Detailed flow chart of step S10;

[0038] Figure 3 for Figure 1 Detailed flowchart of step S30 in FIG.

[0039] Figure 4 for Figure 1 Detailed flow chart of step S50;

[0040] Figure 5 is a flow chart of a second embodiment of the image processing method of the present invention;

[0041] Figure 6 is a flowchart of a third embodiment of the image processing method of the present invention;

[0042] Figure 7 is a block diagram of an image processing system of the present invention;

[0043] Figure 8 is the initial V channel image obtained after the original image is preprocessed;

[0044] Fig. 9 For the general Figure 8 Binarized image obtained after preprocessing;

[0045] Fig.10 This is the image without shadow boundary obtained after compensation processing. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0047] See also Figure 1 As shown, the present invention provides an image processing method; the method comprises the following steps:

[0048] Step S10: preprocessing the original image to identify each pixel as a bright area pixel or a dark area pixel, and extracting an initial H channel feature value, an initial S channel feature value, and an initial V channel feature value of each pixel;

[0049] Step S20: Calculate the average pixel brightness intensity ValueB in the bright area according to the initial V channel characteristic values ​​of the pixel points in the bright area, and calculate the average pixel brightness intensity ValueS in the dark area according to the initial V channel characteristic values ​​of the pixel points in the dark area;

[0050] Step S30: Obtaining a brightness compensation value OffsetValue according to the average brightness intensity of pixels in the bright area and the average brightness intensity of pixels in the dark area;

[0051] Step S40: performing compensation processing on the initial V channel characteristic value according to the brightness compensation value to obtain a compensated V channel characteristic value;

[0052] Step S50: Perform synthesis and conversion processing according to the initial H channel characteristic value, the initial S channel characteristic value and the compensated V channel characteristic value to obtain an image with shadow boundaries removed.

[0053] In another embodiment of the present invention, the preprocessing in step S10 includes binarization processing, the original image is binarized to obtain a binarized image, and the brightness intensity value of the pixel in the binarized image is compared with a preset threshold value, and the bright area pixel / dark area pixel is identified according to the comparison result. The brightness intensity value of the pixel in the binarized image is either 0 or 255, and the value range of the preset threshold for identifying the bright area pixel / dark area pixel is not limited, and any value of 0-255 (including 0 and 255) is acceptable. The comparison relationship can be set as needed, for example, to determine whether the brightness intensity value of the pixel is greater than the preset threshold value, to determine whether the brightness intensity value of the pixel is less than the preset threshold value, and to determine whether the brightness intensity value of the pixel is equal to the preset threshold value.

[0054] See also Figure 2 As shown, in another embodiment of the present invention, the step S10 further includes the following steps:

[0055] Step S110: Acquire an RGB image;

[0056] Step S120: converting the RGB image into an HSV image, extracting the characteristic value of each pixel in the HSV image, wherein the characteristic value includes an initial H channel characteristic value, an initial S channel characteristic value, and an initial V channel characteristic value;

[0057] Step S130: Obtain an initial V channel image (such as Figure 8 shown);

[0058] Step S140: Binarize the initial V channel image to obtain a binary image (such as Fig. 9 As shown), for example, the initial V channel image can be binarized by using the OTSU algorithm (i.e., the Otsu algorithm, also known as the maximum inter-class difference method);

[0059] Step S150: determining whether the brightness intensity value of the pixel in the binary image is greater than a preset threshold; if the brightness intensity value of the pixel in the binary image is greater than the preset threshold, executing step S160; if the brightness intensity value of the pixel in the binary image is not greater than the preset threshold, executing step S170;

[0060] The brightness intensity value of the pixel in the binary image is either 0 or 255, and the range of the preset threshold for identifying bright area pixel / dark area pixel is not limited, and any value of 0-255 (including 0 but excluding 255) is acceptable. Two-dimensional coordinates are defined in the binary image, and each pixel has a unique coordinate value. The binary image with coordinate values ​​is traversed in a predetermined order until all the pixels in the binary image are judged.

[0061] Step S160: identifying the pixel point as a bright area pixel point, and obtaining an initial V channel feature value of the initial V channel image according to the coordinate value of the pixel point;

[0062] Step S170: Identify the pixel point as a dark area pixel point, and obtain an initial V channel feature value of the initial V channel image according to the coordinate value of the pixel point.

[0063] In another embodiment of the present invention, a plurality of brightness intensity difference segment intervals are preset, and different brightness compensation values ​​are obtained by identifying the brightness intensity difference and the brightness intensity difference segment intervals, thereby achieving an adaptive compensation effect. The different brightness compensation values ​​can be obtained by setting a plurality of preset brightness compensation values ​​(fixed values), or can be obtained according to a preset algorithm based on the brightness intensity difference. Please refer to Figure 3 As shown, in another embodiment of the present invention, a plurality of brightness intensity difference segment intervals are preset, and the step S30 further includes the following steps:

[0064] Step S310: Calculate the brightness intensity difference DiffValue=ValueB-ValueS between the average brightness intensity of pixels in the bright area ValueB and the average brightness intensity of pixels in the dark area ValueS;

[0065] Step S320: identifying the brightness intensity difference segmentation interval corresponding to the brightness intensity difference DiffValue, and selecting a corresponding adjustment parameter K according to the brightness intensity difference segmentation interval;

[0066] Step S330: Obtain a brightness compensation value OffsetValue according to the brightness intensity difference DiffValue, an adjustment parameter K and a preset algorithm, and the preset algorithm is: OffsetValue=K*DiffValue.

[0067] The preset algorithm sets an adjustment parameter K, and multiple adjustment parameters K1 and K2 can also be set as needed. The preset algorithm is: OffsetValue=K1*DiffValue+K2. The adjustment parameter K1 is associated with DiffValue, and the adjustment parameter K2 is a fixed value parameter. Through the combination of multiple adjustment parameters and DiffValue, better compensation effect can be achieved.

[0068] As shown in Table 1, the segmented interval of the brightness intensity difference can be set as needed. Through the segmented interval of the brightness intensity difference, segmented compensation is carried out. According to the size of DiffValue, the corresponding adjustment parameter K is automatically selected, which has an adaptive compensation effect. Among them, the value of the adjustment parameter K is not limited to the following data.

[0069] DiffValue K OffsetValue DiffValue≤valueA 0.5 OffsetValue=0.5*DiffValue ValueA <DiffValue≤valueB 1 OffsetValue=1*DiffValue ValueB<DiffValue≤valueC 1.2 OffsetValue=1.2*DiffValue ValueC<DiffValue 0.5 OffsetValue=0.5*DiffValue

[0070] Table 1

[0071] The number of segmented intervals of the brightness intensity difference and the end point values of the intervals can be set as needed. For example, Table 1 sets four segmented intervals of the brightness intensity difference with valueA, valueB, valueC, and valueD as the end points. When DiffValue is recognized as one of the segmented intervals of the brightness intensity difference, the corresponding K of this segmented interval of the brightness intensity difference can be obtained. For example, when ValueB < DiffValue ≤ valueC, K = 1.2 is selected, and then the brightness compensation value is obtained by a preset algorithm.

[0072] In another embodiment of the present invention, in step S40, the initial V-channel characteristic values of the bright area pixel points and / or the dark area pixel points are compensated according to the brightness compensation value. For example, only the initial V-channel characteristic values of the bright area pixel points can be compensated, or only the initial V-channel characteristic values of the dark area pixel points can be compensated, or the initial V-channel characteristic values of both the bright area pixel points and the dark area pixel points are compensated respectively.

[0073] Bright area pixel points: The initial V-channel characteristic values of the bright area pixel points are compensated by weakening according to the brightness compensation value: the V-channel characteristic value after compensation = the initial V-channel characteristic value - the brightness compensation value.

[0074] Dark area pixel points: The initial V-channel characteristic values of the dark area pixel points are compensated by strengthening according to the brightness compensation value: the V-channel characteristic value after compensation = the initial V-channel characteristic value + the brightness compensation value.

[0075] Please refer to Figure 4 As shown, in another embodiment of the present invention, step S50 further includes:

[0076] Step S510: Perform a synthesis process according to the H-channel characteristic value, the S-channel characteristic value, and the compensated V-channel characteristic value to obtain an HSV image without a shadow boundary (as Fig.10 shown);

[0077] Step S520: Perform a conversion process on the HSV image without a shadow to obtain an RGB image without a shadow boundary.

[0078] See also Figure 5 As shown, in another embodiment of the present invention, between step S10 and step S20, further comprising:

[0079] Step S15: determine whether all pixels are bright area pixels or dark area pixels; if so, end this process; if not, execute step S20.

[0080] The situations that need compensation and those that do not need compensation are screened in step S15, thereby optimizing the compensation process.

[0081] See also Figure 6 As shown, in another embodiment of the present invention, the present invention provides an image processing method; the method comprises the following steps:

[0082] Step S10: preprocessing the original image to identify each pixel as a bright area pixel or a dark area pixel, and extracting an initial H channel feature value, an initial S channel feature value, and an initial V channel feature value of each pixel;

[0083] Step S16: pre-processed pixel points are screened out according to the S channel characteristic value, wherein all bright area pixel points in the pre-processed pixel points are a first pixel point combination, and all dark area pixel points in the pre-processed pixel points are a second pixel point combination;

[0084] Step S20A: calculating the average pixel brightness intensity ValueB of the bright area according to the initial V channel characteristic values ​​of the bright area pixels of the first pixel combination, and calculating the average pixel brightness intensity ValueS of the dark area according to the initial V channel characteristic values ​​of the dark area pixels of the second pixel combination;

[0085] Step S30: Obtaining a brightness compensation value OffsetValue according to the average brightness intensity of pixels in the bright area and the average brightness intensity of pixels in the dark area;

[0086] Step S40: performing compensation processing on the initial V channel characteristic value according to the brightness compensation value to obtain a compensated V channel characteristic value;

[0087] Step S50A: Perform synthesis processing and conversion processing according to the initial H channel characteristic value, the initial S channel characteristic value, the initial V channel characteristic value and the compensated V channel characteristic value to obtain an image with the shadow boundary removed.

[0088] The screening condition can be set as needed. If the S channel characteristic value of the pixel point is greater than the preset S value satValue (satValue=80), compensation processing is required. If the S channel characteristic value of the pixel point is not greater than the preset S value satValue (satValue=80), compensation processing is not required. Through step S16 screening processing, the V channel characteristic value in the partial image is not affected by the compensation processing, that is, before and after the compensation processing, the partial image still retains the initial V channel characteristic value. By selectively performing compensation processing, the information loss of the partial image is avoided.

[0089] Assuming that part of the original image is the car body, the filtering conditions are set according to the characteristics of the S channel eigenvalue of the car body. After the filtering process, the pixels outside the car body will be used as pre-processed pixels, and the car body part will be filtered out, that is, the compensation process will not compensate for the car body information in the image, and the pixel features of the car body remain unchanged. Therefore, the car body in the image remains unchanged before and after shadow removal.

[0090] See also Figure 7 As shown, the present invention also provides an image processing system 1, comprising:

[0091] A preprocessing module 10 is used to preprocess the original image to identify each pixel as a bright area pixel or a dark area pixel, and to extract an initial H channel eigenvalue, an initial S channel eigenvalue, and an initial V channel eigenvalue of each pixel;

[0092] The brightness compensation module 20 is used to calculate the average pixel brightness intensity ValueB in the bright area according to the V channel characteristic value of the pixel point in the bright area, and calculate the average pixel brightness intensity ValueS in the dark area according to the V channel characteristic value of the pixel point in the dark area; and obtain the brightness compensation value OffsetValue according to the average pixel brightness intensity in the bright area and the average pixel brightness intensity in the dark area; and compensate the initial V channel characteristic value according to the brightness compensation value to obtain the compensated V channel characteristic value;

[0093] The image generation module 30 is used to perform synthesis processing and conversion processing according to the initial H channel characteristic value, the initial S channel characteristic value and the compensated V channel characteristic value to obtain an image with shadow boundaries removed.

[0094] The present invention further provides an automatic walking device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the image processing method when executing the computer program. The automatic walking device of the present invention can be an automatic lawn mower, an automatic vacuum cleaner, etc., or other equipment, such as a spraying device, a snow removal device, a monitoring device, etc., which are suitable for unattended operation.

[0095] The present invention further provides a readable storage medium having a computer program stored thereon, and the steps of the image processing method are implemented when the computer program is executed by a processor.

[0096] In summary, the present invention adjusts the V channel characteristic value through the brightness compensation value to eliminate the shadow boundary of the image, thereby avoiding the boundary system misjudgment caused by the shadow boundary of the image. The present invention can compare the brightness intensity value of the pixel point in the binary image with the preset threshold value, and can identify the bright area pixel point / dark area pixel point, and the value range of the preset threshold value is not limited. The preset algorithm set in the present invention has a small amount of calculation and a fast image processing speed. The present invention sets the brightness intensity difference segmentation interval, and obtains different brightness compensation values ​​by identifying the brightness intensity difference and the brightness intensity difference segmentation interval, thereby achieving an adaptive compensation effect.

[0097] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation mode may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

[0098] The series of detailed descriptions listed above are only specific descriptions of feasible implementation methods of the present invention and are not intended to limit the scope of protection of the present invention. All equivalent implementation methods or changes that do not deviate from the technical spirit of the present invention should be included in the scope of protection of the present invention.

Claims

1. An image processing method; characterized in that, The following steps are involved: The original image is preprocessed to identify each pixel as a bright area pixel or a dark area pixel, and an initial H channel eigenvalue, an initial S channel eigenvalue and an initial V channel eigenvalue of each pixel are extracted; The average pixel brightness intensity ValueB in the bright area is calculated based on the initial V channel characteristic value of the pixel point in the bright area, and the average pixel brightness intensity ValueS in the dark area is calculated based on the initial V channel characteristic value of the pixel point in the dark area; Obtain the brightness compensation value OffsetValue according to the average brightness intensity of pixels in the bright area and the average brightness intensity of pixels in the dark area; Performing compensation processing on the initial V channel characteristic value according to the brightness compensation value to obtain a compensated V channel characteristic value; Perform synthesis and conversion processing according to the initial H channel characteristic value, the initial S channel characteristic value and the compensated V channel characteristic value to obtain an image with shadow boundaries removed; After identifying the bright area pixels or dark area pixels, it also includes: Filter out pre-processed pixels according to the S channel characteristic value, if the S channel characteristic value of the pixel is greater than the preset S value, perform compensation processing on it, if the S channel characteristic value of the pixel is not greater than the preset S value, perform no compensation processing on it, wherein all bright area pixels in the pre-processed pixels are a first pixel combination, and all dark area pixels in the pre-processed pixels are a second pixel combination; In the subsequent process, the bright area pixels used to calculate the average pixel brightness intensity of the bright area are the bright area pixels of the first pixel combination; the dark area pixels used to calculate the average pixel brightness intensity of the dark area are the dark area pixels of the second pixel combination.

2. The image processing method according to claim 1, characterized in that: The process of preprocessing the original image comprises the following steps: Get RGB image; Convert the RGB image to an HSV image, and extract the characteristic value of each pixel in the HSV image, wherein the characteristic value includes an initial H channel characteristic value, an initial S channel characteristic value, and an initial V channel characteristic value; Obtain an initial V channel image according to the initial V channel feature value of each pixel in the HSV image; Binarize the initial V channel image to obtain a binary image; It is determined whether the brightness intensity value of the pixel in the binary image is greater than a preset threshold value to identify each pixel as a bright area pixel or a dark area pixel. If the brightness intensity value of the pixel in the binary image is greater than the preset threshold value, it is a bright area pixel, and if the brightness intensity value of the pixel in the binary image is not greater than the preset threshold value, it is a dark area pixel.

3. The image processing method according to claim 1, characterized in that: After identifying the bright area pixels or dark area pixels, it also includes: Determine whether all pixels are bright area pixels or dark area pixels; if so, end this process; if not, continue to execute the subsequent compensation process.

4. The image processing method according to claim 1, characterized in that: A plurality of brightness intensity difference segment intervals are preset, and the process of obtaining the brightness compensation value includes: Calculate the brightness intensity difference DiffValue between the average pixel brightness intensity ValueB in the bright area and the average pixel brightness intensity ValueS in the dark area = ValueB-ValueS; Identify the brightness intensity difference segmentation interval corresponding to the brightness intensity difference DiffValue, and select the corresponding adjustment parameter K according to the brightness intensity difference segmentation interval; The brightness compensation value OffsetValue is obtained according to the brightness intensity difference DiffValue, the adjustment parameter K and a preset algorithm, and the preset algorithm is: OffsetValue=K*DiffValue.

5. The image processing method according to claim 4, characterized in that: The initial V channel characteristic values ​​of the bright area pixels and / or the dark area pixels are compensated according to the brightness compensation value, and the initial V channel characteristic values ​​of the bright area pixels are weakened and compensated according to the brightness compensation value: the compensated V channel characteristic value = the initial V channel characteristic value - the brightness compensation value, and the initial V channel characteristic value of the dark area pixels is enhanced and compensated according to the brightness compensation value: the compensated V channel characteristic value = the initial V channel characteristic value + the brightness compensation value.

6. The image processing method according to claim 1, characterized in that: The synthesis process is to obtain the HSV image with the shadow boundary removed according to the H channel eigenvalue, the S channel eigenvalue and the compensated V channel eigenvalue; the conversion process is to convert the shadow-removed HSV image into the RGB image with the shadow boundary removed.

7. An image processing system, characterized in that: The system comprises: A preprocessing module is used to preprocess the original image to identify each pixel as a bright area pixel or a dark area pixel, and to extract an initial H channel eigenvalue, an initial S channel eigenvalue, and an initial V channel eigenvalue of each pixel; A brightness compensation module is used to calculate the average pixel brightness intensity ValueB in the bright area according to the V channel characteristic value of the pixel point in the bright area, and calculate the average pixel brightness intensity ValueS in the dark area according to the V channel characteristic value of the pixel point in the dark area; and obtain a brightness compensation value OffsetValue according to the average pixel brightness intensity in the bright area and the average pixel brightness intensity in the dark area; and compensate the initial V channel characteristic value according to the brightness compensation value to obtain the compensated V channel characteristic value; An image generation module is used to perform synthesis processing and conversion processing according to the initial H channel characteristic value, the initial S channel characteristic value and the compensated V channel characteristic value to obtain an image with shadow boundaries removed; The preprocessing module is also used for: Filter out pre-processed pixels according to the S channel characteristic value, if the S channel characteristic value of the pixel is greater than the preset S value, perform compensation processing on it, if the S channel characteristic value of the pixel is not greater than the preset S value, perform no compensation processing on it, wherein all bright area pixels in the pre-processed pixels are a first pixel combination, and all dark area pixels in the pre-processed pixels are a second pixel combination; In the subsequent process, the bright area pixels used to calculate the average pixel brightness intensity of the bright area are the bright area pixels of the first pixel combination; the dark area pixels used to calculate the average pixel brightness intensity of the dark area are the dark area pixels of the second pixel combination.

8. An automatic walking device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the image processing method according to any one of claims 1 to 6 are implemented.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the image processing method according to any one of claims 1 to 6 are implemented.

Images