Method and system for identifying non-working areas based on images

Through image recognition technology, the problem of large manpower and material consumption of mobile robots and limited lawn shape when calibrating working areas is solved, and accurate identification and obstacle avoidance operations for non-working areas are achieved, improving the performance and work efficiency of robots .

CN115147712BActive Publication Date: 2024-12-06SKYBEST ELECTRIC APPLIANCE (SUZHOU) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110275606.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-03-15
Publication Date
2024-12-06
Estimated Expiration
2041-03-15

AI Technical Summary

Technical Problem

In the prior art, mobile robots such as mowing robots require a lot of manpower and material resources when calibrating the working area, and the lawn shape is relatively limited, making it difficult to achieve mowing operations with low repetition rate and high coverage rate.

Method used

Using an image recognition method, by acquiring the original image, separating the H-channel image and performing binarization processing, confirming whether there is a non-working area in the image, using the chromaticity similarity degree and rectangular contour attribute parameters to determine the similar contour, and then determining the front of the robot non-working areas and drive the robot to perform obstacle avoidance logic.

Benefits of technology

It realizes accurate judgment of non-working areas through image recognition, saves costs, improves robot performance and work efficiency, reduces calculation amount, and improves calculation accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115147712B_ABST
    Figure CN115147712B_ABST
Patent Text Reader

Abstract

The present invention provides a method and system for identifying a non-working area based on an image, the method comprising: obtaining an original image; separating an H channel image from the original image; binarizing the original image to form a binarized image; the binarized image comprises at least one predicted working area with a first pixel value and / or comprises at least one predicted non-working area with a second pixel value; according to the chromatic similarity of each predicted non-working area corresponding to the H channel, confirming whether there is a similar contour in the current image, and when confirming that there is a similar contour, confirming that there is a real non-working area in front of the robot. The present invention can accurately identify the non-working area through image recognition, save costs, and improve the performance of the robot.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent control, and in particular to a method and system for identifying a non-working area based on an image. Background Art

[0002] Low repetition rate and high coverage rate are the goals pursued by traversal robots such as vacuuming, mowing and pool cleaning. Taking the mobile robot as an intelligent mowing robot as an example, the mowing robot uses the lawn surrounded by the boundary as the working area for mowing operations, and the area outside the lawn is defined as the non-working area.

[0003] In the prior art, the boundaries of the lawn working area are usually calibrated by burying boundary lines. This method requires a lot of manpower and material resources, which increases the cost of using the mobile robot. In addition, this method has certain requirements for wiring, for example: the angle of the corner cannot be less than 90 degrees, thus limiting the shape of the lawn working area to a certain extent. Summary of the invention

[0004] In order to solve the above technical problems, an object of the present invention is to provide a method and system for identifying non-working areas based on images.

[0005] In order to achieve one of the above-mentioned objects of the invention, an embodiment of the present invention provides a method for identifying a non-working area based on an image, the method comprising: acquiring an original image;

[0006] Separate the H channel image from the original image;

[0007] Binarization is performed on the original image to form a binary image; the binary image includes at least one predicted working area with a first pixel value and / or includes at least one predicted non-working area with a second pixel value;

[0008] According to the chromaticity similarity of each predicted non-working area on the H channel, it is confirmed whether there is a similar contour in the current image, and when it is confirmed that there is a similar contour, it is confirmed that there is a real non-working area in front of the robot.

[0009] Through the above method, it is possible to accurately determine whether there is a non-working area in front of the robot through image recognition, thereby saving costs and improving the performance of the robot.

[0010] As a further improvement of an embodiment of the present invention, according to the chromaticity similarity of each of the predicted non-working areas corresponding to the H channel, confirming whether there is a similar contour in the current image includes:

[0011] Based on the binary image, respectively obtaining the smallest rectangular outline enclosing each predicted non-working area in the binary image;

[0012] Acquire attribute parameter values ​​representing the size of each rectangular outline based on the binary image, wherein the attribute parameter values ​​include: at least one of the area corresponding to each rectangular outline, the length of the diagonal line, the width of the rectangular outline, the height of the rectangular outline, and the number of pixels in the rectangular outline that predicts a non-working area;

[0013] The rectangular contours whose attribute parameter values ​​are greater than the preset parameter threshold are counted and represented as the first contour;

[0014] According to the chromaticity similarity of the predicted non-working areas respectively covered by the first contours on the H channel, it is determined whether there is a similar contour in the current image.

[0015] Through the above preferred implementation, the scope of the area for similar contour comparison is narrowed, the amount of calculation is reduced, and the accuracy is improved.

[0016] As a further improvement of an embodiment of the present invention, according to the chromaticity similarity of the predicted non-working areas respectively covered by each first contour on the H channel, confirming whether there is a similar contour in the current image includes:

[0017] Respectively obtain the chromaticity value corresponding to the predicted non-working area covered by each first contour, the chromaticity value being the average chromaticity value corresponding to the predicted non-working area on the H channel;

[0018] Each first contour is traversed, and if the chromaticity value difference corresponding to the predicted non-working areas covered by any two first contours is less than a preset chromaticity threshold, it is confirmed that a similar contour exists in the current image.

[0019] Through the above preferred implementation manner, similar contour confirmation is described in detail to improve calculation accuracy.

[0020] As a further improvement of an embodiment of the present invention, according to the chromaticity similarity of the predicted non-working areas respectively covered by each first contour on the H channel, confirming whether there is a similar contour in the current image includes:

[0021] Taking the current first contour as the basic contour, it is determined in turn whether the difference between the chromaticity value of the predicted non-working area covered by each other first contour and the chromaticity value of the predicted non-working area covered by the current basic contour is less than a preset chromaticity threshold,

[0022] If yes, mark the two first contours currently being compared as similar contours, accumulate the total number of similar contours corresponding to the basic contour, and do not traverse the confirmed similar contours and the first contour traversed as the basic contour repeatedly;

[0023] If not, continue to use the next first contour as the basic contour to confirm similar contours until all first contours are judged;

[0024] When the similar contour confirmation for all first contours is completed, if the number of first contours for which similar contours are not identified is different from the total number of first contours, it is confirmed that similar contours exist in the current image.

[0025] Through the above preferred implementation manner, similar contour confirmation is described in detail to improve calculation accuracy.

[0026] As a further improvement of an embodiment of the present invention, if it is confirmed that there is a similar contour in the current image, the method further includes:

[0027] All first contours that form similar contours are obtained. If the coordinate parameter value of any first contour is greater than the preset coordinate value, the robot is driven to execute obstacle avoidance logic.

[0028] In the above implementation mode, the robot is confirmed to have encountered an obstacle through image recognition, and an obstacle avoidance operation is performed to improve work efficiency.

[0029] In order to achieve one of the above-mentioned objects of the invention, an embodiment of the present invention provides a system for identifying a non-working area based on an image, the system comprising: an acquisition module for acquiring an original image;

[0030] A conversion module, used for separating an H channel image from an original image;

[0031] Binarization is performed on the original image to form a binary image; the binary image includes at least one predicted working area with a first pixel value and / or includes at least one predicted non-working area with a second pixel value;

[0032] The parsing module is used to confirm whether there is a similar contour in the current image according to the chromaticity similarity of each predicted non-working area on the H channel, and when it is confirmed that there is a similar contour, confirm that there is a real non-working area in front of the robot.

[0033] Through the above system, it is possible to accurately determine whether there is a non-working area in front of the robot through image recognition, saving costs and improving the robot's performance.

[0034] As a further improvement of an embodiment of the present invention, the parsing module is used for:

[0035] Based on the binary image, respectively obtaining the smallest rectangular outline enclosing each predicted non-working area in the binary image;

[0036] Acquire attribute parameter values ​​representing the size of each rectangular outline based on the binary image, wherein the attribute parameter values ​​include: at least one of the area corresponding to each rectangular outline, the length of the diagonal line, the width of the rectangular outline, the height of the rectangular outline, and the number of pixels in the rectangular outline that predicts a non-working area;

[0037] The rectangular contours whose attribute parameter values ​​are greater than the preset parameter threshold are counted and represented as the first contour;

[0038] According to the chromaticity similarity of the predicted non-working areas respectively covered by the first contours on the H channel, it is determined whether there is a similar contour in the current image.

[0039] Through the above system, the scope of the area for similar contour comparison is narrowed, the amount of calculation is reduced, and the accuracy is improved.

[0040] As a further improvement of an embodiment of the present invention, the parsing module is used to: respectively obtain the chromaticity value corresponding to the predicted non-working area covered by each first contour, and the chromaticity value is the average chromaticity value corresponding to the predicted non-working area on the H channel;

[0041] Each first contour is traversed, and if the chromaticity value difference corresponding to the predicted non-working areas covered by any two first contours is less than a preset chromaticity threshold, it is confirmed that a similar contour exists in the current image.

[0042] Through the above system, similar contour confirmation is described in detail to improve calculation accuracy.

[0043] As a further improvement of an embodiment of the present invention, the parsing module is used to: take the current first contour as the basic contour, and sequentially determine whether the difference between the chromaticity value of the predicted non-working area covered by each other first contour and the chromaticity value of the predicted non-working area covered by the current basic contour is less than a preset chromaticity threshold,

[0044] If yes, mark the two first contours currently being compared as similar contours, accumulate the total number of similar contours corresponding to the basic contour, and do not traverse the confirmed similar contours and the first contour traversed as the basic contour repeatedly;

[0045] If not, continue to use the next first contour as the basic contour to confirm similar contours until all first contours are judged;

[0046] When the similar contour confirmation for all first contours is completed, if the number of first contours for which similar contours are not identified is different from the total number of first contours, it is confirmed that similar contours exist in the current image.

[0047] Through the above system, similar contour confirmation is described in detail to improve calculation accuracy.

[0048] As a further improvement of an embodiment of the present invention, if it is confirmed that similar contours exist in the current image, the parsing module is also used to: obtain all first contours that form similar contours, and if the coordinate parameter value of any first contour is greater than a preset coordinate value, drive the robot to execute obstacle avoidance logic.

[0049] The above system uses image recognition to confirm that the robot encounters an obstacle, performs obstacle avoidance operations, and improves work efficiency.

[0050] Compared with the prior art, the method and system for identifying non-working areas based on image recognition of the present invention can accurately identify non-working areas through image recognition, save costs, and improve the performance of the robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a structural schematic diagram of the lawn mowing robot system provided by the present invention;

[0052] Figure 2 is a flowchart of a method for identifying a non-working area based on an image provided by a first embodiment of the present invention;

[0053] Figure 3 It is a module schematic diagram of the system based on image recognition of non-working areas provided by the present invention. DETAILED DESCRIPTION

[0054] The present invention will be described in detail below in conjunction with the various embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by a person skilled in the art based on these embodiments are all within the scope of protection of the present invention.

[0055] The robot system of the present invention can be a lawn mowing robot system, a sweeping robot system, a snow sweeper system, a leaf vacuum system, a golf course ball picker system, etc. Each system can automatically walk in the working area and perform corresponding work. In the specific example of the present invention, the robot system is a lawn mowing robot system as an example for specific description. Accordingly, the working area can be a lawn.

[0056] like Figure 1 As shown, the lawn mowing robot system of the present invention comprises: a lawn mowing robot (RM).

[0057] The lawn mowing robot comprises: a body 10, a walking unit, an image acquisition unit and a control unit arranged on the body 10. The walking unit comprises: a driving wheel 111, a passive wheel 113 and a motor for driving the driving wheel 111; the motor can be a brushless motor with a reduction gearbox and a Hall sensor; after the motor is started, the driving wheel 111 can be driven to walk through the reduction gearbox, and the driving movements such as forward and backward straight-line running, turning on the spot and circular running can be realized by controlling the speed and direction of the two wheels; the passive wheel 113 can be a universal wheel, which is usually set to one or two, and it mainly plays a role of supporting balance.

[0058] The image acquisition unit is used to acquire scenes within its viewing angle within a certain range. In a specific embodiment of the present invention, it is a camera 12. The camera 12 is installed on the upper part of the main body 10 and forms a certain angle with the horizontal direction. It can capture scenes within a certain range of the lawn mower robot; the camera 12 usually captures scenes within a certain range in front of the lawn mower robot.

[0059] The control unit is a main controller 13 for performing image processing, such as an MCU or a DSP.

[0060] Furthermore, the lawn mowing robot also includes: a working mechanism for working, and a power supply 14; in this embodiment, the working mechanism is a lawn mowing disc, and various sensors for sensing the walking state of the walking robot, such as: tipping, lifting off the ground, collision sensors, geomagnetism, gyroscopes, etc., which are not described in detail here.

[0061] like Figure 2 As shown, the first embodiment of the present invention provides a method for identifying a working position (non-working area) based on an image, and the method comprises the following steps:

[0062] S1, obtain the original image;

[0063] S2, separating the H channel image from the original image;

[0064] Binarization is performed on the original image to form a binary image; the binary image includes at least one predicted working area with a first pixel value and / or includes at least one predicted non-working area with a second pixel value;

[0065] S3. According to the chromaticity similarity of each predicted non-working area on the H channel, confirm whether there is a similar contour in the current image, and when it is confirmed that there is a similar contour, confirm that there is a real non-working area in front of the robot.

[0066] In a specific implementation of the present invention, for step S1, a camera installed on the mowing robot captures the scene in front of the robot in real time to form an original image; the scene is an image of the ground in the robot's forward direction; further, after the main controller receives the original image, it parses the original image; thus, the robot can be judged through the original image to obtain the working position of the robot when the original image is captured, which will be described in detail in the following content. In this specific example, the format of the original image is not specifically limited, for example: a color image in RGB format or HSV format.

[0067] For step S2, if the original image is in RGB format, the format of the original image in RGB format is converted to form an HSV image. If the original image is in HSV format, no conversion is required, and the H channel image is directly separated from the HSV image. This implementation method is all existing technology, and there are many implementation methods, which will not be repeated here.

[0068] The original image is binarized to form a first binarized image. It can be seen that the binarized image is an image in which pixels have only two grayscale values, for example, the two grayscale values ​​are 0 and 255, respectively. The binarization process is a process of presenting an obvious black and white effect on the entire original image.

[0069] There are many ways to implement binarization of an original image to form a first binary image. In a specific implementation of the present invention, P1, image segmentation is performed on the original image to obtain a chromaticity segmentation threshold [lowValue, highValue], pixels in the original image within the segmentation threshold are converted to the same pixel, and pixels outside the segmentation threshold are converted to another pixel to form a first binary image. In the first binary image, one pixel value represents a working area, and the other pixel value represents a non-working area.

[0070] The image segmentation method includes, for example, a color dynamic segmentation method, an edge texture segmentation method, a fixed threshold method segmentation method, an Otsu threshold method segmentation method, and the like.

[0071] The threshold matching method is to transform each pixel point by setting a threshold range. In a specific example of the present invention, the pixel value of the pixel point within the threshold range is adjusted to 255, that is, the working area is adjusted to white; the pixel value of the pixel point outside the threshold range is adjusted to 0, that is, the non-working area is adjusted to black.

[0072] P2. Perform opening, closing and inverting operations on the first binary image in sequence to form the binary image described in step S1 of the present invention. In the adjusted binary image, the working area is black and the non-working area is white.

[0073] The opening, closing and inverting operations are all conventional image processing methods, which are also prior art and will not be further elaborated here. It can be seen here that after the opening, closing and inverting processing of the first binary image, the working area in the binary image formed and the non-working area in the first binary image are not exactly the same.

[0074] For step S3, in a preferred embodiment of the present invention, based on the binary image, a minimum rectangular outline enclosing each predicted non-working area in the binary image is obtained respectively;

[0075] Acquire attribute parameter values ​​representing the size of each rectangular outline based on the binary image, wherein the attribute parameter values ​​include: at least one of the area corresponding to each rectangular outline, the length of the diagonal line, the width of the rectangular outline, the height of the rectangular outline, and the number of pixels in the rectangular outline that predicts a non-working area;

[0076] The rectangular contours whose attribute parameter values ​​are greater than the preset parameter threshold are counted and represented as the first contour;

[0077] According to the chromaticity similarity of the predicted non-working areas respectively covered by the first contours on the H channel, it is determined whether there is a similar contour in the current image.

[0078] Here, when the attribute parameter value is the area corresponding to the rectangular outline, the preset parameter threshold is also the corresponding area threshold; correspondingly, when the attribute parameter value is at least one of the diagonal length, the rectangular outline width, the rectangular outline height, and the number of pixels in the rectangular outline that predicts the non-working area, the preset parameter threshold also changes accordingly. Specifically, the preset parameter threshold is one of the diagonal length threshold, the rectangular outline width threshold, the rectangular outline height threshold, and the number of pixels in the rectangular outline that predicts the non-working area;

[0079] In a specific example of the present invention, the configuration area threshold is 1%*the area of ​​the original image, the diagonal length threshold is 10%*the diagonal length of the original image, the pixel number threshold for predicting the non-working area in the rectangular outline is 1%*the number of pixels in the original image; the rectangular outline width threshold is 0.8*the width of the original image, and the rectangular outline height is 0.6% the height of the original image.

[0080] Correspondingly, taking the area corresponding to the rectangular contour as an example, when the area of ​​any rectangular contour is greater than 1%*the area of ​​the original image, the current rectangular contour is marked as the first contour; taking the rectangular contour width and the rectangular contour height as an example, when any rectangular contour satisfies at the same time: the width is greater than 0.8*the width of the original image, and the height is greater than 0.6% of the height of the original image, the current rectangular contour is marked as the first contour.

[0081] Further, for step S3, in the first embodiment of the present invention, according to the chromaticity similarity of the predicted non-working areas respectively covered by each first contour on the H channel, confirming whether there is a similar contour in the current image includes:

[0082] Respectively obtain the chromaticity value corresponding to the predicted non-working area covered by each first contour, the chromaticity value being the average chromaticity value corresponding to the predicted non-working area on the H channel;

[0083] Each first contour is traversed, and if the chromaticity value difference corresponding to the predicted non-working areas covered by any two first contours is less than a preset chromaticity threshold, it is confirmed that a similar contour exists in the current image.

[0084] In the second embodiment of the present invention, according to the chromaticity similarity of the predicted non-working areas respectively covered by the first contours on the H channel, confirming whether there is a similar contour in the current image includes:

[0085] Taking the current first contour as the basic contour, determine in turn whether the difference between the chromaticity value of the predicted non-working area covered by each other first contour and the chromaticity value of the predicted non-working area covered by the current basic contour is less than the preset chromaticity threshold value. If so, mark the two first contours currently being compared as similar contours, accumulate the total number of similar contours corresponding to the basic contours, and do not repeat the traversal of the confirmed similar contours and the first contour traversed as the basic contour; if not, continue to confirm the similar contours with the next first contour as the basic contour until all first contours are judged;

[0086] When the similar contour confirmation for all first contours is completed, if the number of first contours for which similar contours are not identified is different from the total number of first contours, it is confirmed that similar contours exist in the current image.

[0087] Taking a specific example, if the number of first contours is N, the serial number is represented by i, i∈(1, 2...N), during the traversal process, taking the i-th first contour as the basic contour, it is determined whether the chromaticity value difference between it and the N-1 first contours is less than the preset chromaticity threshold. If so, the similar contours corresponding to the i-th first contour are accumulated by 1. Here, the number of similar contours corresponding to the i-th first contour (including the i-th first contour) is recorded as HS i , traverse all first contours, and the first contours marked as similar contours are not marked repeatedly; after the traversal is completed, the total number HD of first contours that are not marked as similar contours can be obtained, HD = N-(HS1+…+HS i ); At this time, if HD=N, it means that there is no similar contour in the current image. If HD≠N, it is confirmed that there is a similar contour in the current image, and then it is confirmed that there is a real non-working area in front of the robot.

[0088] Preferably, when HD≠N, if HD<N, it is confirmed that there is a similar contour in the current image. If HD>N, then a program error occurs and an alarm mechanism can be set, which will not be elaborated here.

[0089] Furthermore, after step S3, if it is confirmed that there is a similar contour in the current image, the method further includes: obtaining all first contours that form the similar contour, and if the coordinate parameter value of any first contour is greater than a preset coordinate value, driving the robot to execute obstacle avoidance logic.

[0090] The obstacle avoidance logic, for example, reverse steering, will not be described in detail here.

[0091] Here, the coordinate parameter value may be the y-axis coordinate of the lower right corner of the rectangular outline, the center position coordinate of the rectangular outline, or the average Y value of the pixel coordinate in the first outline, etc., which will not be further elaborated here.

[0092] Combination Figure 3 As shown, a system for identifying non-working areas based on images is provided, and the system includes: an acquisition module 100, a conversion module 200 and a parsing module 300.

[0093] The acquisition module 100 is used to acquire the original image; the conversion module 200 is used to separate the H channel image from the original image; the original image is binarized to form a binary image; the binary image includes at least one predicted working area with a first pixel value and / or includes at least one predicted non-working area with a second pixel value; the analysis module 300 is used to confirm whether there is a similar contour in the current image according to the chromatic similarity of each of the predicted non-working areas corresponding to the H channel, and when it is confirmed that there is a similar contour, confirm that there is a real non-working area in front of the robot.

[0094] Specifically, the acquisition module 100 is used to implement step S1; the conversion module 200 is used to implement step S2; the analysis module 300 is used to implement step S3, and execute the calculation of the obstacle avoidance logic for driving the robot; technicians in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the system described above can refer to the corresponding process in the aforementioned method implementation method, and will not be repeated here.

[0095] In summary, the method and system for identifying non-working areas based on image recognition of the present invention can accurately identify non-working areas through image recognition, save costs, and improve the performance of the robot.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed modules, systems and methods can be implemented in other ways. The system implementation described above is only illustrative, and the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0097] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or may be distributed on multiple network modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of this implementation scheme.

[0098] In addition, each functional module in each embodiment of the present application can be integrated into one analysis module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0099] Finally, it should be noted that the above implementation modes are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned implementation modes, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned implementation modes, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various implementation modes of the present application.

Claims

1. A method for identifying a non-working area based on an image, characterized in that: The method comprises: Get the original image; Separate the H channel image from the original image; Binarization is performed on the original image to form a binary image; the binary image includes at least one predicted working area with a first pixel value and / or includes at least one predicted non-working area with a second pixel value; According to the chromaticity similarity of each predicted non-working area on the H channel, confirm whether there is a similar contour in the current image, and when confirming that there is a similar contour, confirm that there is a real non-working area in front of the robot; Wherein, according to the chromaticity similarity of each of the predicted non-working areas corresponding to the H channel, confirming whether there is a similar contour in the current image includes: Based on the binary image, respectively obtain the smallest rectangular outline that encloses each predicted non-working area in the binary image; Acquire attribute parameter values ​​representing the size of each rectangular outline based on the binary image, wherein the attribute parameter values ​​include: at least one of the area corresponding to each rectangular outline, the length of the diagonal line, the width of the rectangular outline, the height of the rectangular outline, and the number of pixels of the predicted non-working area in the rectangular outline; The rectangular contours whose attribute parameter values ​​are greater than the preset parameter threshold are counted and represented as the first contour; According to the chromaticity similarity of the predicted non-working areas respectively covered by the first contours on the H channel, it is determined whether there is a similar contour in the current image.

2. The method for identifying non-working areas based on images according to claim 1, characterized in that: According to the chromaticity similarity of the predicted non-working areas respectively covered by the first contours on the H channel, confirming whether there is a similar contour in the current image includes: Respectively obtain the chromaticity value corresponding to the predicted non-working area covered by each first contour, the chromaticity value being the average chromaticity value corresponding to the predicted non-working area on the H channel; Each first contour is traversed, and if the chromaticity value difference corresponding to the predicted non-working areas covered by any two first contours is less than a preset chromaticity threshold, it is confirmed that a similar contour exists in the current image.

3. The method for identifying non-working areas based on images according to claim 1, characterized in that: According to the chromaticity similarity of the predicted non-working areas respectively covered by the first contours on the H channel, confirming whether there is a similar contour in the current image includes: Taking the current first contour as the basic contour, determine in turn whether the difference between the chromaticity value of the predicted non-working area covered by each other first contour and the chromaticity value of the predicted non-working area covered by the current basic contour is less than a preset chromaticity threshold, If yes, mark the two first contours currently being compared as similar contours, accumulate the total number of similar contours corresponding to the basic contour, and do not traverse the confirmed similar contours and the first contour traversed as the basic contour repeatedly; If not, continue to use the next first contour as the basic contour to confirm similar contours until all first contours are judged; When the similar contour confirmation for all first contours is completed, if the number of first contours for which similar contours are not identified is different from the total number of first contours, it is confirmed that similar contours exist in the current image.

4. The method for identifying a non-working area based on an image according to any one of claims 1 to 3, characterized in that: If it is confirmed that there is a similar contour in the current image, the method further includes: All first contours that form similar contours are obtained. If the coordinate parameter value of any first contour is greater than the preset coordinate value, the robot is driven to execute obstacle avoidance logic.

5. A system for identifying non-working areas based on images, characterized in that: The system comprises: An acquisition module, used for acquiring the original image; A conversion module, used for separating an H channel image from an original image; Binarization is performed on the original image to form a binary image; the binary image includes at least one predicted working area with a first pixel value and / or includes at least one predicted non-working area with a second pixel value; The parsing module is used to confirm whether there is a similar contour in the current image according to the chromaticity similarity of each predicted non-working area on the H channel, and when it is confirmed that there is a similar contour, confirm that there is a real non-working area in front of the robot; Among them, the parsing module is used to: Based on the binary image, respectively obtain the smallest rectangular outline that encloses each predicted non-working area in the binary image; Acquire attribute parameter values ​​representing the size of each rectangular outline based on the binary image, wherein the attribute parameter values ​​include: at least one of the area corresponding to each rectangular outline, the length of the diagonal line, the width of the rectangular outline, the height of the rectangular outline, and the number of pixels of the predicted non-working area in the rectangular outline; The rectangular contours whose attribute parameter values ​​are greater than the preset parameter threshold are counted and represented as the first contour; According to the chromaticity similarity of the predicted non-working areas respectively covered by the first contours on the H channel, it is determined whether there is a similar contour in the current image.

6. The system for identifying non-working areas based on images according to claim 5, characterized in that: The analysis module is used to: respectively obtain the chromaticity value corresponding to the predicted non-working area covered by each first contour, and the chromaticity value is the average chromaticity value corresponding to the predicted non-working area on the H channel; Each first contour is traversed, and if the chromaticity value difference corresponding to the predicted non-working areas covered by any two first contours is less than a preset chromaticity threshold, it is confirmed that a similar contour exists in the current image.

7. The system for identifying non-working areas based on images according to claim 5, characterized in that: The parsing module is used to: take the current first contour as the basic contour, and sequentially determine whether the difference between the chromaticity value of the predicted non-working area covered by each other first contour and the chromaticity value of the predicted non-working area covered by the current basic contour is less than a preset chromaticity threshold, If yes, mark the two first contours currently being compared as similar contours, accumulate the total number of similar contours corresponding to the basic contour, and do not traverse the confirmed similar contours and the first contour traversed as the basic contour repeatedly; If not, continue to use the next first contour as the basic contour to confirm similar contours until all first contours are judged; When the similar contour confirmation for all first contours is completed, if the number of first contours for which similar contours are not identified is different from the total number of first contours, it is confirmed that similar contours exist in the current image.

8. The system for identifying non-working areas based on images according to any one of claims 5 to 7, characterized in that: If it is confirmed that there is a similar contour in the current image, the parsing module is also used to: obtain all first contours that form the similar contour, and if the coordinate parameter value of any first contour is greater than the preset coordinate value, drive the robot to execute obstacle avoidance logic.