An explosion-proof robot intelligent inspection method, system and medium

Abstract

This application provides an intelligent inspection method, system, and medium for explosion-proof robots. The method includes: acquiring a full-area inspection image; preprocessing the full-area inspection image to generate building distribution information; classifying buildings according to the building distribution information and calculating the correlation between buildings; comparing the correlation between buildings with a preset association threshold to obtain a deviation rate; determining whether the deviation rate is greater than a preset deviation rate threshold; if it is greater, establishing different inspection strategies for the buildings; if it is less, generating a coordinated inspection and performing collaborative inspection through the explosion-proof robot; and realizing intelligent inspection technology by classifying different buildings and establishing different inspection paths according to different classification results.

Description

Technical Field

[0001] This application relates to the field of intelligent inspection of robots, and more specifically, to an intelligent inspection method, system and medium for explosion-proof robots. Background Technology

[0002] In recent years, with the rapid development of science and technology and information, intelligent robot technology has also undergone tremendous changes. Robots are increasingly being used in industry, medicine, military, and daily life. Robots involve many fields, such as computer science, automatic control, mechanics, sensing technology, communication technology, artificial intelligence, and bionics, among other advanced disciplines. Therefore, the development of robots is a crystallization of modern science and technology. Robots can be commanded by humans and can run pre-programmed procedures to conduct area inspections and perform inspection tasks. However, existing robots cannot set different inspection paths based on building classifications, resulting in low inspection efficiency.

[0003] Effective technical solutions are urgently needed to address the above problems. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent inspection method, system, and medium for explosion-proof robots, which can perform collaborative inspections using explosion-proof robots; and to achieve intelligent inspection technology by classifying different buildings and establishing different inspection paths based on different classification results.

[0005] This application also provides an intelligent inspection method for explosion-proof robots, including:

[0006] Acquire full-area inspection images, preprocess the full-area inspection images, and generate building distribution information;

[0007] The buildings are classified based on their distribution information, and the correlation between them is calculated.

[0008] The correlation between the buildings is compared with a preset association threshold to obtain the deviation rate;

[0009] Determine whether the deviation rate is greater than a preset deviation rate threshold;

[0010] If the value is greater than the specified value, different inspection strategies will be established for the building.

[0011] If the value is less than the specified value, a joint inspection is generated, and a collaborative inspection is carried out by an explosion-proof robot.

[0012] Optionally, in the intelligent inspection method for explosion-proof robots described in this application embodiment, the step of acquiring a full-area inspection image and preprocessing the full-area inspection image to generate building distribution information includes:

[0013] Acquire the full-area inspection image, set the inspection range, and divide the full-area inspection image into several sub-images according to the inspection range.

[0014] Image enhancement processing is performed on several sub-images, and feature values ​​of the sub-images are extracted;

[0015] The grayscale value is calculated by inputting grayscale value based on image feature value to obtain the grayscale value of pixels in several sub-images;

[0016] Compare the gray values ​​of the pixels in the sub-image with a preset gray value threshold;

[0017] If the gray value of a pixel in a sub-image is greater than the first preset gray value threshold, then the pixel is determined to be a pixel of a low-speed moving object.

[0018] If the gray value of a pixel in a sub-image is greater than the second preset gray value threshold, then the pixel is determined to be a pixel of a high-speed moving object.

[0019] If the gray value of a pixel in a sub-image is less than the first preset gray value threshold, then the pixel is determined to be a static object pixel.

[0020] The distribution information of buildings is obtained by fusing all the pixels of stationary objects;

[0021] The first preset grayscale threshold is less than the second preset grayscale threshold.

[0022] Optionally, in the intelligent inspection method for explosion-proof robots described in this application embodiment, the step of acquiring a full-area inspection image and preprocessing the full-area inspection image to generate building distribution information includes:

[0023] Acquire full-area inspection images, and set multiple inspection range thresholds, which are the first inspection threshold, the second inspection threshold, and the Nth inspection threshold, respectively.

[0024] The inspection area is calibrated by moving an explosion-proof robot, and the calibration range threshold is obtained.

[0025] If the calibration range threshold is equal to the first inspection range threshold, stop the explosion-proof robot from moving and generate the first sub-region image;

[0026] When the explosion-proof robot continues to move until the calibration range threshold is greater than the first inspection range threshold and less than the second inspection threshold, an expanded area image is generated.

[0027] Determine whether the grayscale value of the image pixel in the expanded region is greater than the preset grayscale value;

[0028] If the value is greater than the first sub-region image, the expanded region image will be stitched together with the first sub-region image to form a complete first sub-region image.

[0029] If it is smaller than, then the first sub-region image is calibrated and recorded;

[0030] The entire area inspection image is sequentially divided into M sub-area images.

[0031] Optionally, in the intelligent inspection method for explosion-proof robots described in this application embodiment, the step of acquiring a full-area inspection image and setting multiple inspection range thresholds, wherein the multiple inspection range thresholds are a first inspection threshold, a second inspection threshold to an Nth inspection threshold, includes:

[0032] The inspection area is calibrated by moving an explosion-proof robot, and the calibration range threshold is obtained.

[0033] If the calibration range threshold is equal to the first inspection range threshold, the first sub-region image is generated, and the grayscale value of the first sub-region image is calculated.

[0034] When the mobile explosion-proof robot makes the calibration range threshold greater than the first inspection range threshold and less than the second inspection threshold, it generates an expanded region image and calculates the gray value of the expanded region image.

[0035] The grayscale difference is obtained by subtracting the grayscale value of the first sub-region image from the grayscale value of the expanded region image.

[0036] The grayscale difference is compared with a preset difference to obtain the similarity between the expanded region image and the first sub-region image;

[0037] If the similarity is greater than the preset similarity threshold, the first inspection range threshold and the second inspection threshold are superimposed to obtain a new inspection range threshold, and the set inspection range threshold is updated and reset.

[0038] Optionally, in the intelligent inspection method for explosion-proof robots described in the embodiments of this application, the step of classifying buildings according to building distribution information and calculating the correlation between buildings includes:

[0039] Obtain building distribution information and calculate the building footprint;

[0040] The area difference is obtained by calculating the difference in the floor area of ​​different buildings;

[0041] Determine whether the area difference is less than a first area difference threshold;

[0042] If it is less than, then obtain the building outline, overlap the different building outlines and calculate the distance;

[0043] Determine if the distance between the outlines of different buildings is less than a distance threshold. If it is less, classify the different buildings into the same type of building.

[0044] Optionally, in the intelligent inspection method for explosion-proof robots described in this application embodiment, if the value is greater than a certain threshold, different inspection strategies are established for the building; if the value is less than a certain threshold, a coordinated inspection is generated, and collaborative inspection is performed using explosion-proof robots, including:

[0045] Different types of buildings are inspected separately, and inspection paths are generated based on building distribution information. The inspection movement parameters of the explosion-proof robot are established based on the inspection paths and building distribution information.

[0046] The explosion-proof robot is controlled to move in a predetermined manner according to the inspection movement parameters;

[0047] Similar buildings are inspected collaboratively, and path planning is performed for similar buildings to generate collaborative inspection paths for similar buildings.

[0048] Explosion-proof robots inspect similar buildings according to a collaborative inspection path;

[0049] After the inspection is completed, different types of buildings will be inspected separately.

[0050] Secondly, embodiments of this application provide an intelligent inspection system for explosion-proof robots. This system includes a memory and a processor. The memory includes a program for an intelligent inspection method for explosion-proof robots. When the program for the intelligent inspection method for explosion-proof robots is executed by the processor, it performs the following steps:

[0051] Acquire full-area inspection images, preprocess the full-area inspection images, and generate building distribution information;

[0052] The buildings are classified based on their distribution information, and the correlation between them is calculated.

[0053] The correlation between the buildings is compared with a preset association threshold to obtain the deviation rate;

[0054] Determine whether the deviation rate is greater than a preset deviation rate threshold;

[0055] If the value is greater than the specified value, different inspection strategies will be established for the building.

[0056] If the value is less than the specified value, a joint inspection is generated, and a collaborative inspection is carried out by an explosion-proof robot.

[0057] Optionally, in the explosion-proof robot intelligent inspection system described in this application embodiment, the step of acquiring full-area inspection images, preprocessing the full-area inspection images, and generating building distribution information includes:

[0058] Acquire the full-area inspection image, set the inspection range, and divide the full-area inspection image into several sub-images according to the inspection range.

[0059] Image enhancement processing is performed on several sub-images, and feature values ​​of the sub-images are extracted;

[0060] The grayscale value is calculated by inputting grayscale value based on image feature value to obtain the grayscale value of pixels in several sub-images;

[0061] Compare the gray values ​​of the pixels in the sub-image with a preset gray value threshold;

[0062] If the gray value of a pixel in a sub-image is greater than the first preset gray value threshold, then the pixel is determined to be a pixel of a low-speed moving object.

[0063] If the gray value of a pixel in a sub-image is greater than the second preset gray value threshold, then the pixel is determined to be a pixel of a high-speed moving object.

[0064] If the gray value of a pixel in a sub-image is less than the first preset gray value threshold, then the pixel is determined to be a static object pixel.

[0065] The distribution information of buildings is obtained by fusing all the pixels of stationary objects;

[0066] The first preset grayscale threshold is less than the second preset grayscale threshold.

[0067] Optionally, in the explosion-proof robot intelligent inspection system described in this application embodiment, the step of acquiring full-area inspection images, preprocessing the full-area inspection images, and generating building distribution information includes:

[0068] Acquire full-area inspection images, and set multiple inspection range thresholds, which are the first inspection threshold, the second inspection threshold, and the Nth inspection threshold, respectively.

[0069] The inspection area is calibrated by moving an explosion-proof robot, and the calibration range threshold is obtained.

[0070] If the calibration range threshold is equal to the first inspection range threshold, stop the explosion-proof robot from moving and generate the first sub-region image;

[0071] When the explosion-proof robot continues to move until the calibration range threshold is greater than the first inspection range threshold and less than the second inspection threshold, an expanded area image is generated.

[0072] Determine whether the grayscale value of the image pixel in the expanded region is greater than the preset grayscale value;

[0073] If the value is greater than the first sub-region image, the expanded region image will be stitched together with the first sub-region image to form a complete first sub-region image.

[0074] If it is smaller than, then the first sub-region image is calibrated and recorded;

[0075] The entire area inspection image is sequentially divided into M sub-area images.

[0076] Thirdly, embodiments of this application also provide a computer-readable storage medium, which includes a program for an intelligent inspection method for an explosion-proof robot. When the program for an intelligent inspection method for an explosion-proof robot is executed by a processor, it implements the steps of the intelligent inspection method for an explosion-proof robot as described in any of the above claims.

[0077] As can be seen from the above, the intelligent inspection method, system, and medium for explosion-proof robots provided in this application acquire full-area inspection images, preprocess the full-area inspection images to generate building distribution information; classify buildings according to the building distribution information and calculate the correlation between buildings; compare the correlation between buildings with a preset association threshold to obtain a deviation rate; determine whether the deviation rate is greater than the preset deviation rate threshold; if it is greater, establish different inspection strategies for buildings; if it is less, generate a linkage inspection and conduct collaborative inspection through explosion-proof robots; by classifying different buildings and establishing different inspection paths according to different classification results, the technology of intelligent inspection is realized.

[0078] Other features and advantages of this application will be set forth in the following description, and the advantages of this application will be apparent in part from the description, or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0079] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0080] Figure 1 A flowchart of the intelligent inspection method for explosion-proof robots provided in the embodiments of this application;

[0081] Figure 2 A flowchart illustrating the generation of building distribution information for the intelligent inspection method for explosion-proof robots provided in this application embodiment;

[0082] Figure 3 A flowchart of the full-area inspection image segmentation method for the intelligent inspection method for explosion-proof robots provided in this application embodiment;

[0083] Figure 4This is a flowchart illustrating the inspection range threshold update and reset process of the intelligent inspection method for explosion-proof robots provided in this application embodiment.

[0084] Figure 5 This is a schematic diagram of the structure of the explosion-proof robot intelligent inspection system provided in the embodiments of this application. Detailed Implementation

[0085] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0086] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0087] Please refer to Figure 1 , Figure 1 This is a flowchart of an intelligent inspection method for an explosion-proof robot according to some embodiments of this application. The intelligent inspection method for an explosion-proof robot is used in a terminal device and includes the following steps:

[0088] S101, acquire full-area inspection images, preprocess the full-area inspection images, and generate building distribution information;

[0089] S102, Classify buildings according to building distribution information and calculate the correlation between buildings;

[0090] S103, compare the correlation between buildings with a preset association threshold to obtain the deviation rate;

[0091] S104, determine whether the deviation rate is greater than the preset deviation rate threshold;

[0092] If S105 is greater than 5, then different inspection strategies will be established for the buildings.

[0093] If S106 is less than 1, then a joint inspection is generated, and a collaborative inspection is carried out by an explosion-proof robot.

[0094] It should be noted that the full-area inspection images include one of the following: park images, industrial park images, factory images, warehouse images, or community images. Different inspection paths are generated for different areas. The explosion-proof robot performs mobile inspections according to the inspection paths. During the movement of the explosion-proof robot, the movement parameters are updated in real time to adapt the movement status of the explosion-proof robot to the inspection area.

[0095] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the generation of building distribution information using an intelligent inspection method for explosion-proof robots, as described in some embodiments of this application. According to embodiments of the present invention, acquiring a full-area inspection image, preprocessing the full-area inspection image, and generating building distribution information include:

[0096] S201, acquire the full-area inspection image, set the inspection range, and divide the full-area inspection image into several sub-images according to the inspection range.

[0097] S202, perform image enhancement processing on several sub-images and extract feature values ​​from the sub-images;

[0098] S203, the gray values ​​of pixels in several sub-images are obtained by calculating the gray values ​​of the input gray values ​​based on the image feature values;

[0099] S204, compare the gray values ​​of the pixels in the sub-image with a preset gray value threshold;

[0100] S205, if the gray value of a pixel in the sub-image is greater than the first preset gray value threshold, then the pixel is determined to be a low-speed moving object pixel; if the gray value of a pixel in the sub-image is greater than the second preset gray value threshold, then the pixel is determined to be a high-speed moving object pixel.

[0101] S206, if the gray value of a pixel in a sub-image is less than a first preset gray value threshold, then the pixel is determined to be a stationary object pixel; all stationary object pixels are fused to obtain building distribution information;

[0102] The first preset grayscale threshold is less than the second preset grayscale threshold.

[0103] It should be noted that the state of a pixel is determined based on its grayscale value. Low-speed motion includes pedestrians, high-speed motion includes moving cars, and stationary objects include buildings.

[0104] Please refer to Figure 3 , Figure 3This is a flowchart of a full-area inspection image segmentation method for an intelligent inspection method for explosion-proof robots, as described in some embodiments of this application. According to embodiments of the present invention, a full-area inspection image is acquired, and the full-area inspection image is preprocessed to generate building distribution information, including:

[0105] S301, acquire the full-area inspection image, set multiple inspection range thresholds, the multiple inspection range thresholds are the first inspection threshold, the second inspection threshold to the Nth inspection threshold;

[0106] S302, the inspection area is calibrated by moving an explosion-proof robot to obtain the calibration range threshold;

[0107] S303, if the calibration range threshold is equal to the first inspection range threshold, stop the explosion-proof robot from moving and generate the first sub-region image;

[0108] S304, when the explosion-proof robot continues to move until the calibration range threshold is greater than the first inspection range threshold and less than the second inspection threshold, an expanded area image is generated.

[0109] S305, determine whether the gray value of the pixel in the expanded region image is greater than the preset pixel gray value;

[0110] If the value is greater than the first sub-region image, the expanded region image will be stitched together with the first sub-region image to form a complete first sub-region image.

[0111] If it is smaller than, then the first sub-region image is calibrated and recorded;

[0112] S306, the entire area inspection image is sequentially divided into M sub-area images.

[0113] It should be noted that by using the mobile calibration of the explosion-proof robot, the inspection images of the entire area can be accurately segmented, ensuring that the same building is located in the same sub-area image, preventing building segmentation and affecting the determination of building judgment and distribution information.

[0114] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the inspection range threshold update and reset process of an intelligent inspection method for an explosion-proof robot, as described in some embodiments of this application. According to an embodiment of the present invention, a full-area inspection image is acquired, and multiple inspection range thresholds are set. These multiple inspection range thresholds are a first inspection threshold, a second inspection threshold, and so on, up to an Nth inspection threshold, including:

[0115] S401, the inspection area is calibrated by moving the explosion-proof robot to obtain the calibration range threshold;

[0116] S402, if the calibration range threshold is equal to the first inspection range threshold, generate the first sub-region image and calculate the gray value of the first sub-region image;

[0117] S403, when the mobile explosion-proof robot makes the calibration range threshold greater than the first inspection range threshold and less than the second inspection threshold, it generates an expanded area image and calculates the gray value of the expanded area image.

[0118] S404, subtract the gray value of the first sub-region image from the gray value of the expanded region image to obtain the gray value difference;

[0119] S405, compare the grayscale difference with the preset difference to obtain the similarity between the expanded region image and the first sub-region image;

[0120] S406, if the similarity is greater than the preset similarity threshold, the first inspection range threshold and the second inspection threshold are superimposed to obtain a new inspection range threshold, and the set inspection range threshold is updated and reset.

[0121] It should be noted that by calculating the similarity between the expanded image and the first sub-region image through the grayscale difference and the preset difference, the first sub-region image can be accurately segmented, ensuring that the same building is located in the same sub-region image, improving the segmentation accuracy of the whole region image, and realizing the real-time update of the set inspection range threshold.

[0122] According to an embodiment of the present invention, classifying buildings based on building distribution information and calculating the correlation between buildings includes:

[0123] Obtain building distribution information and calculate the building footprint;

[0124] The area difference is obtained by calculating the difference in the floor area of ​​different buildings;

[0125] Determine whether the area difference is less than the first area difference threshold;

[0126] If it is less than, then obtain the building outline, overlap the different building outlines and calculate the distance;

[0127] Determine if the distance between the outlines of different buildings is less than a distance threshold. If it is less, classify the different buildings into the same type of building.

[0128] According to an embodiment of the present invention, if the value is greater than a certain threshold, different inspection strategies are established for the building; if the value is less than a certain threshold, a coordinated inspection is generated, and collaborative inspection is performed using an explosion-proof robot, including:

[0129] Different types of buildings are inspected separately, and inspection paths are generated based on building distribution information. The inspection movement parameters of the explosion-proof robot are established based on the inspection paths and building distribution information.

[0130] The explosion-proof robot is controlled to move in a predetermined manner according to the inspection movement parameters;

[0131] Similar buildings are inspected collaboratively, and path planning is performed for similar buildings to generate collaborative inspection paths for similar buildings.

[0132] Explosion-proof robots inspect similar buildings according to a collaborative inspection path;

[0133] After the inspection is completed, different types of buildings will be inspected separately.

[0134] According to an embodiment of the present invention, it further includes: setting an inspection plan, the explosion-proof robot automatically performs inspection tasks 24 hours a day, and supports free configuration of inspection routes, inspection points, point actions, and inspection plans;

[0135] During robot inspection or monitoring, the planning of inspection actions at different locations is set up;

[0136] Intelligent inspection is performed based on the inspection actions.

[0137] It should be noted that the inspection actions include: scene capture, preset point recall, audio broadcast, text and voice broadcast, around the perimeter, vehicle inspection, off-duty alarm, vehicle illegal parking detection, vehicle angle steering, continuous loop broadcast, charging, supplementary lighting control, and door opening.

[0138] Please refer to Figure 5 , Figure 5 This is a schematic diagram of the structure of an explosion-proof robot intelligent inspection system according to some embodiments of this application. Secondly, embodiments of this application provide an explosion-proof robot intelligent inspection system 5, which includes: a memory 51 and a processor 52. The memory 51 includes a program for an explosion-proof robot intelligent inspection method. When the program for the explosion-proof robot intelligent inspection method is executed by the processor, it implements the following steps:

[0139] Acquire full-area inspection images, preprocess the full-area inspection images, and generate building distribution information;

[0140] The buildings are classified based on their distribution information, and the correlation between them is calculated.

[0141] The correlation between buildings is compared with a preset association threshold to obtain the deviation rate;

[0142] Determine whether the deviation rate is greater than the preset deviation rate threshold;

[0143] If the value is greater than the specified value, different inspection strategies will be established for the building.

[0144] If the value is less than the specified value, a joint inspection is generated, and a collaborative inspection is carried out by an explosion-proof robot.

[0145] It should be noted that the full-area inspection images include one of the following: park images, industrial park images, factory images, warehouse images, or community images. Different inspection paths are generated for different areas. The explosion-proof robot performs mobile inspections according to the inspection paths. During the movement of the explosion-proof robot, the movement parameters are updated in real time to adapt the movement status of the explosion-proof robot to the inspection area.

[0146] According to an embodiment of the present invention, a full-area inspection image is acquired, and the full-area inspection image is preprocessed to generate building distribution information, including:

[0147] Acquire the full-area inspection image, set the inspection range, and divide the full-area inspection image into several sub-images according to the inspection range.

[0148] Image enhancement processing is performed on several sub-images, and feature values ​​of the sub-images are extracted;

[0149] The grayscale value is calculated by inputting grayscale value based on image feature value to obtain the grayscale value of pixels in several sub-images;

[0150] Compare the gray values ​​of the pixels in the sub-image with a preset gray value threshold;

[0151] If the gray value of a pixel in a sub-image is greater than the first preset gray value threshold, then the pixel is determined to be a pixel of a low-speed moving object.

[0152] If the gray value of a pixel in a sub-image is greater than the second preset gray value threshold, then the pixel is determined to be a pixel of a high-speed moving object.

[0153] If the gray value of a pixel in a sub-image is less than the first preset gray value threshold, then the pixel is determined to be a static object pixel.

[0154] The distribution information of buildings is obtained by fusing all the pixels of stationary objects;

[0155] The first preset grayscale threshold is less than the second preset grayscale threshold.

[0156] It should be noted that the state of a pixel is determined based on its grayscale value. Low-speed motion includes pedestrians, high-speed motion includes moving cars, and stationary objects include buildings.

[0157] According to an embodiment of the present invention, a full-area inspection image is acquired, and the full-area inspection image is preprocessed to generate building distribution information, including:

[0158] Acquire full-area inspection images, and set multiple inspection range thresholds, which are the first inspection threshold, the second inspection threshold, and the Nth inspection threshold, respectively.

[0159] The inspection area is calibrated by moving an explosion-proof robot, and the calibration range threshold is obtained.

[0160] If the calibration range threshold is equal to the first inspection range threshold, stop the explosion-proof robot from moving and generate the first sub-region image;

[0161] When the explosion-proof robot continues to move until the calibration range threshold is greater than the first inspection range threshold and less than the second inspection threshold, an expanded area image is generated.

[0162] Determine whether the grayscale value of the pixels in the expanded region image is greater than the preset pixel grayscale value;

[0163] If the value is greater than the first sub-region image, the expanded region image will be stitched together with the first sub-region image to form a complete first sub-region image.

[0164] If it is smaller than, then the first sub-region image is calibrated and recorded;

[0165] The entire area inspection image is sequentially divided into M sub-area images.

[0166] It should be noted that by using the mobile calibration of the explosion-proof robot, the inspection images of the entire area can be accurately segmented, ensuring that the same building is located in the same sub-area image, preventing building segmentation and affecting the determination of building judgment and distribution information.

[0167] According to an embodiment of the present invention, a full-area inspection image is acquired, and multiple inspection range thresholds are set, wherein the multiple inspection range thresholds are a first inspection threshold, a second inspection threshold to an Nth inspection threshold, including:

[0168] The inspection area is calibrated by moving an explosion-proof robot, and the calibration range threshold is obtained.

[0169] If the calibration range threshold is equal to the first inspection range threshold, the first sub-region image is generated, and the grayscale value of the first sub-region image is calculated.

[0170] When the mobile explosion-proof robot makes the calibration range threshold greater than the first inspection range threshold and less than the second inspection threshold, it generates an expanded region image and calculates the gray value of the expanded region image.

[0171] The grayscale difference is obtained by subtracting the grayscale value of the first sub-region image from the grayscale value of the expanded region image.

[0172] The grayscale difference is compared with a preset difference to obtain the similarity between the expanded region image and the first sub-region image;

[0173] If the similarity is greater than the preset similarity threshold, the first inspection range threshold and the second inspection threshold are superimposed to obtain a new inspection range threshold, and the set inspection range threshold is updated and reset.

[0174] It should be noted that by calculating the similarity between the expanded image and the first sub-region image through the grayscale difference and the preset difference, the first sub-region image can be accurately segmented, ensuring that the same building is located in the same sub-region image, improving the segmentation accuracy of the whole region image, and realizing the real-time update of the set inspection range threshold.

[0175] According to an embodiment of the present invention, classifying buildings based on building distribution information and calculating the correlation between buildings includes:

[0176] Obtain building distribution information and calculate the building footprint;

[0177] The area difference is obtained by calculating the difference in the floor area of ​​different buildings;

[0178] Determine whether the area difference is less than the first area difference threshold;

[0179] If it is less than, then obtain the building outline, overlap the different building outlines and calculate the distance;

[0180] Determine if the distance between the outlines of different buildings is less than a distance threshold. If it is less, classify the different buildings into the same type of building.

[0181] According to an embodiment of the present invention, if the value is greater than a certain threshold, different inspection strategies are established for the building; if the value is less than a certain threshold, a coordinated inspection is generated, and collaborative inspection is performed using an explosion-proof robot, including:

[0182] Different types of buildings are inspected separately, and inspection paths are generated based on building distribution information. The inspection movement parameters of the explosion-proof robot are established based on the inspection paths and building distribution information.

[0183] The explosion-proof robot is controlled to move in a predetermined manner according to the inspection movement parameters;

[0184] Similar buildings are inspected collaboratively, and path planning is performed for similar buildings to generate collaborative inspection paths for similar buildings.

[0185] Explosion-proof robots inspect similar buildings according to a collaborative inspection path;

[0186] After the inspection is completed, different types of buildings will be inspected separately.

[0187] According to an embodiment of the present invention, it further includes: setting an inspection plan, the explosion-proof robot automatically performs inspection tasks 24 hours a day, and supports free configuration of inspection routes, inspection points, point actions, and inspection plans;

[0188] During robot inspection or monitoring, the planning of inspection actions at different locations is set up;

[0189] Intelligent inspection is performed based on the inspection actions.

[0190] It should be noted that the inspection actions include: scene capture, preset point recall, audio broadcast, text and voice broadcast, around the perimeter, vehicle inspection, off-duty alarm, vehicle illegal parking detection, vehicle angle steering, continuous loop broadcast, charging, supplementary lighting control, and door opening.

[0191] A third aspect of the present invention provides a computer-readable storage medium including a program for an intelligent inspection method for an explosion-proof robot. When executed by a processor, the program implements the steps of the intelligent inspection method for an explosion-proof robot as described in any of the above claims.

[0192] This invention discloses an intelligent inspection method, system, and medium for explosion-proof robots. The method involves acquiring a full-area inspection image, preprocessing the image to generate building distribution information, classifying buildings based on this information, calculating the correlation between buildings, comparing the correlation with a preset association threshold to obtain a deviation rate, determining whether the deviation rate exceeds the preset threshold, establishing different inspection strategies for buildings if the deviation rate exceeds the threshold, and generating a coordinated inspection using the explosion-proof robot if the deviation rate exceeds the threshold. By classifying different buildings and establishing different inspection paths based on the classification results, the invention achieves intelligent inspection technology.

[0193] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0194] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0195] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0196] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0197] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for intelligent inspection of explosion-proof robots, characterized in that, include: Acquire full-area inspection images, preprocess the full-area inspection images, and generate building distribution information; The buildings are classified based on their distribution information, and the correlation between them is calculated. The correlation between the buildings is compared with a preset association threshold to obtain the deviation rate; Determine whether the deviation rate is greater than a preset deviation rate threshold; If the value is greater than the specified value, different inspection strategies will be established for the building. If it is less than, a joint inspection is generated, and a collaborative inspection is carried out by an explosion-proof robot; The step of classifying buildings based on building distribution information and calculating the correlation between buildings includes: Obtain building distribution information and calculate the building footprint; The area difference is obtained by calculating the difference in the floor area of ​​different buildings; Determine whether the area difference is less than a first area difference threshold; If it is less than, then obtain the building outline, overlap the different building outlines and calculate the distance; Determine if the distance between the outlines of different buildings is less than a distance threshold. If it is less, classify the different buildings into the same type of building.

2. The intelligent inspection method for explosion-proof robots according to claim 1, characterized in that, The process of acquiring full-area inspection images, preprocessing the full-area inspection images, and generating building distribution information includes: Acquire the full-area inspection image, set the inspection range, and divide the full-area inspection image into several sub-images according to the inspection range. Image enhancement processing is performed on several sub-images, and feature values ​​of the sub-images are extracted; The grayscale value is calculated by inputting grayscale value based on image feature value to obtain the grayscale value of pixels in several sub-images; Compare the gray values ​​of the pixels in the sub-image with a preset gray value threshold; If the gray value of a pixel in a sub-image is greater than the first preset gray value threshold, then the pixel is determined to be a pixel of a low-speed moving object. If the gray value of a pixel in a sub-image is greater than the second preset gray value threshold, then the pixel is determined to be a pixel of a high-speed moving object. If the gray value of a pixel in a sub-image is less than the first preset gray value threshold, then the pixel is determined to be a static object pixel. The distribution information of buildings is obtained by fusing all the pixels of stationary objects; The first preset grayscale threshold is less than the second preset grayscale threshold.

3. The intelligent inspection method for explosion-proof robots according to claim 2, characterized in that, The process of acquiring full-area inspection images, preprocessing the full-area inspection images, and generating building distribution information includes: Acquire full-area inspection images, and set multiple inspection range thresholds, which are the first inspection threshold, the second inspection threshold, and the Nth inspection threshold, respectively. The inspection area is calibrated by moving an explosion-proof robot, and the calibration range threshold is obtained. If the calibration range threshold is equal to the first inspection range threshold, stop the explosion-proof robot from moving and generate the first sub-region image; When the explosion-proof robot continues to move until the calibration range threshold is greater than the first inspection range threshold and less than the second inspection threshold, an expanded area image is generated. Determine whether the grayscale value of the image pixel in the expanded region is greater than the preset grayscale value; If the value is greater than the first sub-region image, the expanded region image will be stitched together with the first sub-region image to form a complete first sub-region image. If it is smaller than, then the first sub-region image is calibrated and recorded; The entire area inspection image is sequentially divided into M sub-area images.

4. The intelligent inspection method for explosion-proof robots according to claim 3, characterized in that, The process of acquiring a full-area inspection image involves setting multiple inspection range thresholds, which are defined as a first inspection threshold, a second inspection threshold, and so on up to the Nth inspection threshold. The inspection area is calibrated by moving an explosion-proof robot, and the calibration range threshold is obtained. If the calibration range threshold is equal to the first inspection range threshold, the first sub-region image is generated, and the grayscale value of the first sub-region image is calculated. When the mobile explosion-proof robot makes the calibration range threshold greater than the first inspection range threshold and less than the second inspection threshold, it generates an expanded region image and calculates the gray value of the expanded region image. The grayscale difference is obtained by subtracting the grayscale value of the first sub-region image from the grayscale value of the expanded region image. The grayscale difference is compared with a preset difference to obtain the similarity between the expanded region image and the first sub-region image; If the similarity is greater than the preset similarity threshold, the first inspection range threshold and the second inspection threshold are superimposed to obtain a new inspection range threshold, and the set inspection range threshold is updated and reset.

5. The intelligent inspection method for explosion-proof robots according to claim 1, characterized in that, If the value is greater than the specified value, different inspection strategies will be established for the building. If the value is less than the specified value, a coordinated inspection is generated, and an explosion-proof robot performs a collaborative inspection, including: Different types of buildings are inspected separately, and inspection paths are generated based on building distribution information. The inspection movement parameters of the explosion-proof robot are established based on the inspection paths and building distribution information. The explosion-proof robot is controlled to move in a predetermined manner according to the inspection movement parameters; Similar buildings are inspected collaboratively, and path planning is performed for similar buildings to generate collaborative inspection paths for similar buildings. Explosion-proof robots inspect similar buildings according to a collaborative inspection path; After the inspection is completed, different types of buildings will be inspected separately.

6. An explosion-proof robot intelligent inspection system, characterized in that, The system includes a memory and a processor. The memory contains a program for an intelligent inspection method for explosion-proof robots. When the program for the intelligent inspection method for explosion-proof robots is executed by the processor, it performs the following steps: Acquire full-area inspection images, preprocess the full-area inspection images, and generate building distribution information; The buildings are classified based on their distribution information, and the correlation between them is calculated. The correlation between the buildings is compared with a preset association threshold to obtain the deviation rate; Determine whether the deviation rate is greater than a preset deviation rate threshold; If the value is greater than the specified value, different inspection strategies will be established for the building. If it is less than, a joint inspection is generated, and a collaborative inspection is carried out by an explosion-proof robot; The step of classifying buildings based on building distribution information and calculating the correlation between buildings includes: Obtain building distribution information and calculate the building footprint; The area difference is obtained by calculating the difference in the floor area of ​​different buildings; Determine whether the area difference is less than a first area difference threshold; If it is less than, then obtain the building outline, overlap the different building outlines and calculate the distance; Determine if the distance between the outlines of different buildings is less than a distance threshold. If it is less, classify the different buildings into the same type of building.

7. The explosion-proof robot intelligent inspection system according to claim 6, characterized in that, The process of acquiring full-area inspection images, preprocessing the full-area inspection images, and generating building distribution information includes: Acquire the full-area inspection image, set the inspection range, and divide the full-area inspection image into several sub-images according to the inspection range. Image enhancement processing is performed on several sub-images, and feature values ​​of the sub-images are extracted; The grayscale value is calculated by inputting grayscale value based on image feature value to obtain the grayscale value of pixels in several sub-images; Compare the gray values ​​of the pixels in the sub-image with a preset gray value threshold; If the gray value of a pixel in a sub-image is greater than the first preset gray value threshold, then the pixel is determined to be a pixel of a low-speed moving object. If the gray value of a pixel in a sub-image is greater than the second preset gray value threshold, then the pixel is determined to be a pixel of a high-speed moving object. If the gray value of a pixel in a sub-image is less than the first preset gray value threshold, then the pixel is determined to be a static object pixel. The distribution information of buildings is obtained by fusing all the pixels of stationary objects; The first preset grayscale threshold is less than the second preset grayscale threshold.

8. The explosion-proof robot intelligent inspection system according to claim 6, characterized in that, The process of acquiring full-area inspection images, preprocessing the full-area inspection images, and generating building distribution information includes: Acquire full-area inspection images, and set multiple inspection range thresholds, which are the first inspection threshold, the second inspection threshold, and the Nth inspection threshold, respectively. The inspection area is calibrated by moving an explosion-proof robot, and the calibration range threshold is obtained. If the calibration range threshold is equal to the first inspection range threshold, stop the explosion-proof robot from moving and generate the first sub-region image; When the explosion-proof robot continues to move until the calibration range threshold is greater than the first inspection range threshold and less than the second inspection threshold, an expanded area image is generated. Determine whether the grayscale value of the image pixel in the expanded region is greater than the preset grayscale value; If the value is greater than the first sub-region image, the expanded region image will be stitched together with the first sub-region image to form a complete first sub-region image. If it is smaller than, then the first sub-region image is calibrated and recorded; The entire area inspection image is sequentially divided into M sub-area images.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a program for an intelligent inspection method for an explosion-proof robot. When the program is executed by a processor, it implements the steps of the intelligent inspection method for an explosion-proof robot as described in any one of claims 1 to 5.

Images