Near-electricity operation risk identification method and system and readable storage medium

Abstract

The invention provides a near-electricity operation risk identification method and system and a readable storage medium. The method comprises the following steps: inputting a panoramic image into a first target identification model and a second target identification model respectively; judging whether the first target and the second target have an overlapping area according to the position information of the first target and the position information of the second target; if the first target and the second target have the overlapping region, segmenting the overlapping region from the panoramic image, and inputting the overlapping region into a pre-trained regression model; carrying out pixel separation on the overlapped region according to the pixel separation coefficient; and obtaining a first space coordinate of each pixel point in the first target according to the first pixel information and the first coordinate information, obtaining a second space coordinate of each pixel point in the second target according to the second pixel information and the second coordinate information, and judging whether a near-electricity operation risk exists according to the first space coordinate and the second space coordinate. According to the invention, the accuracy of identifying the current near-electricity operation risk can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of near - electricity operation risk identification, and particularly to a method, a system and a readable storage medium for near - electricity operation risk identification. Background Art

[0002] In the near - electricity operation scenario, accurately identifying the relative position relationship between the operating personnel and the energized equipment and timely discovering potential safety risks are the keys to ensuring the life safety of the operating personnel. However, traditional near - electricity operation risk identification methods often rely on manual inspections or simple image - processing techniques, and these methods have many limitations. On the one hand, manual inspections are inefficient and vulnerable to human factors, making it difficult to achieve all - weather and all - round monitoring. On the other hand, simple image - processing techniques are difficult to accurately identify target objects and their spatial position relationships in complex scenarios, resulting in low risk - identification accuracy.

[0003] With the rapid development of computer vision and deep - learning technologies, near - electricity operation risk identification methods based on image recognition have gradually become a research hotspot. However, existing risk - identification methods based on image recognition still face great challenges when dealing with complex scenarios such as target - object overlap and occlusion. Specifically, when the operating personnel and the energized equipment overlap in the image, traditional methods are difficult to accurately segment the overlapping area, and thus cannot accurately calculate the spatial distance between the two, which affects the accuracy of risk identification. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, a system and a readable storage medium for near - electricity operation risk identification, aiming to solve the problem that traditional technologies cannot accurately calculate the spatial distance between the two due to the difficulty of accurately segmenting the overlapping area, resulting in low accuracy of near - electricity operation risk identification.

[0005] In a first aspect, the present invention provides a method for near - electricity operation risk identification, the method comprising: Obtaining a panoramic image when an operator performs a near - electricity operation, and respectively inputting the panoramic image into a first target recognition model and a second target recognition model to obtain position information of a first target and position information of a second target; Judging whether there is an overlapping area between the first target and the second target according to the position information of the first target and the position information of the second target; If there is an overlapping area between the first target and the second target, then segmenting the overlapping area from the panoramic image and inputting the overlapping area into a pre - trained regression model to obtain a pixel separation coefficient; Perform pixel separation on the overlapping region according to the pixel separation coefficient, and obtain the first pixel information of each pixel point in the region covered by the first target and the corresponding first coordinate information, the second pixel information of each pixel point in the region covered by the second target, and the corresponding second coordinate information according to the pixel separation result; Obtain the first spatial coordinates of each pixel point in the first target according to the first pixel information and the first coordinate information, obtain the second spatial coordinates of each pixel point in the second target according to the second pixel information and the second coordinate information, and determine whether there is a risk of working near electricity according to the first spatial coordinates and the second spatial coordinates.

[0006] In summary, according to the above method for identifying the risk of working near electricity, by accurately segmenting the first target and the second target in the overlapping region to restore the pixel information that originally belonged to the first target and the second target respectively, and then accurately calculating the spatial distance between the two, the accuracy of identifying the current risk of working near electricity is greatly improved. Specifically, first, identify the first target and the second target in the panoramic image respectively, and then judge whether there is an overlapping region according to the position information of the two targets. Furthermore, accurately identify the pixel separation coefficient of the overlapping region, so as to obtain the actual pixel information (first pixel information) of the first target and the actual pixel information (second pixel information) of the second target under this pixel separation coefficient. Then, accurately calculate the spatial coordinates of each pixel point in the two targets based on the actual pixel information of the two, and then accurately judge whether there is a risk of working near electricity between the two targets.

[0007] Further, the step of judging whether there is an overlapping region between the first target and the second target according to the position information of the first target and the position information of the second target includes: Respectively obtain the first area and the second area of the region where the first target is located and the region where the second target is located, and obtain the intersection-over-union ratio of the first target and the second target in the panoramic image according to the first area and the second area; Judge whether the intersection-over-union ratio is greater than a first preset threshold; If the intersection-over-union ratio is greater than the first preset threshold, it is determined that there is an overlapping region between the first target and the second target.

[0008] Further, the step of, if there is an overlapping region between the first target and the second target, segmenting the overlapping region from the panoramic image and inputting the overlapping region into a pre-trained regression model to obtain the pixel separation coefficient includes: Obtain a first image containing a single first target and a second image containing a single second target, extract the third pixel information and third pixel coordinates of each pixel point of the first target in the first image, and the fourth pixel information and fourth pixel coordinates of each pixel point of the second target in the second image; Randomly fuse the pixel points in the first image with the pixel points in the second image according to the third pixel coordinates and the fourth pixel coordinates to obtain a fused image, and the size of the fused image is equal to that of the first image and the second image; Extract the fused pixel information of each pixel point in the fused image, and calculate the pixel separation coefficient according to the fused pixel information and the corresponding third pixel information and fourth pixel information; Input the fused pixel information of each pixel point in the fused image and the pixel separation coefficient corresponding to each fused pixel information into the regression model to be trained to obtain a pre-trained regression model.

[0009] Further, the step of separating pixels in the overlapping region according to the pixel separation coefficient, and obtaining the first pixel information of each pixel point in the region covered by the first target and the first coordinate information corresponding to the first pixel information, and the second pixel information of each pixel point in the region covered by the second target and the second coordinate information corresponding to the second pixel information includes: Respectively retrieve the first average pixel information and the second average pixel information from a preset database according to the pixel information of each overlapping pixel point in the overlapping region; Obtain the first pixel information and the second pixel information according to the pixel information of each overlapping pixel point, the pixel separation coefficient corresponding to each overlapping pixel point, the first average pixel information, and the second average pixel information.

[0010] Further, the step of constructing the preset database includes: Extract the fused pixel information of each fusion point in the fused image, define any fusion point as the target fusion point, obtain the first non-fused pixel set in the region covered by the first target in the first image except the target fusion point, and the second non-fused pixel set in the region covered by the second target in the second image except the target fusion point; Obtain the third average pixel information according to the third pixel information of all pixel points included in the first non-fused pixel set, and obtain the fourth average pixel information according to the fourth pixel information of all pixel points included in the second non-fused pixel set; Associate the fused pixel information with the corresponding third average pixel information and fourth pixel information one by one, and obtain the preset database according to the association result.

[0011] Further, the step of obtaining the first pixel information and the second pixel information according to the pixel information of each overlapping pixel point, the pixel separation coefficient corresponding to each overlapping pixel point, the first average pixel information, and the second average pixel information includes: Obtain the first pixel information or the second pixel information according to the following formula: ; Wherein, represents the pixel information of the i-th overlapping pixel point, respectively represent the coordinate information of the i-th overlapping pixel point, represents the pixel separation coefficient corresponding to the i-th overlapping pixel point, represents the first pixel information or the second pixel information corresponding to the i-th overlapping pixel point, represents the first average pixel information or the second average pixel information corresponding to the i-th overlapping pixel point.

[0012] Further, the step of obtaining the first spatial coordinates of each pixel point in the first target according to the first pixel information and the first coordinate information, and obtaining the second spatial coordinates of each pixel point in the second target according to the second pixel information and the second coordinate information includes: Obtain the first depth value of each pixel point in the first target and the second depth value of each pixel point in the second target according to the first pixel information and the second pixel information respectively; Calculate the first spatial coordinates or the second spatial coordinates according to the following formula: ; Wherein, respectively represent the x coordinate, y coordinate, and z coordinate of the i-th pixel point in the first target or the second target in the three-dimensional space, respectively represent the x coordinate and y coordinate of the i-th pixel point in the first target or the second target in the panoramic image, represents the x coordinate and y coordinate of the principal point of the camera used to capture the panoramic image, respectively represent the focal lengths of the camera used to capture the panoramic image in the x-axis direction and the y-axis direction, represents the depth value of the i-th pixel point in the first target or the second target in the panoramic image.

[0013] Further, the step of determining whether there is a risk of near-electrical operation according to the first spatial coordinates and the second spatial coordinates includes: Traverse the spatial distance between the pixel points in the first target and the pixel points in the second target according to the first spatial coordinates and the second spatial coordinates; Judge whether the spatial distance is greater than the second preset threshold; If there is at least one spatial distance less than or equal to the second preset threshold, it is determined that there is a risk in the current live working near electricity; If all the spatial distances are greater than the second preset threshold, it is determined that the current live working near electricity is safe and compliant.

[0014] In a second aspect, the present invention provides a risk identification system for live working near electricity, the system comprising: A target identification module, configured to obtain a panoramic image when an operator performs live working near electricity, and input the panoramic image into a first target identification model and a second target identification model respectively, to obtain position information of a first target and position information of a second target; An overlapping area detection module, configured to determine whether there is an overlapping area between the first target and the second target according to the position information of the first target and the position information of the second target; A pixel separation coefficient identification module, configured to, if there is an overlapping area between the first target and the second target, segment the overlapping area from the panoramic image, and input the overlapping area into a pre-trained regression model to obtain a pixel separation coefficient; A pixel separation module, configured to perform pixel separation on the overlapping area according to the pixel separation coefficient, and obtain first pixel information of each pixel point in the area covered by the first target and first coordinate information corresponding to the first pixel information, second pixel information of each pixel point in the area covered by the second target, and second coordinate information corresponding to the second pixel information according to the pixel separation result; A risk detection module, configured to obtain first spatial coordinates of each pixel point in the first target according to the first pixel information and the first coordinate information, obtain second spatial coordinates of each pixel point in the second target according to the second pixel information and the second coordinate information, and determine whether there is a risk in live working near electricity according to the first spatial coordinates and the second spatial coordinates.

[0015] In a third aspect, the present invention provides a readable storage medium, which stores one or more programs, and when the program is executed by a processor, the above-mentioned risk identification method for live working near electricity is implemented.

[0016] In a fourth aspect, the present invention provides an electronic device, the electronic device comprising a memory and a processor, wherein: The memory is used for storing a computer program; The processor is configured to implement the above-mentioned risk identification method for live working near electricity when executing the computer program stored on the memory. Description of the Drawings

[0017] Figure 1 It is a flowchart of the risk identification method for live working near electricity proposed in an embodiment of the present invention; Figure 2 This is a schematic structural diagram of a near-electrical operation risk identification system proposed in an embodiment of the present invention.

[0018] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. Specific Embodiments

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein shall have the ordinary meanings understood by those of ordinary skill in the art to which the present invention pertains. The words such as "including" used herein are intended to mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects.

[0020] As Figure 1 shown, an embodiment of the present invention proposes a near-electrical operation risk identification method, which includes steps S101 to S105, where: Step S101: Obtain a panoramic image when an operator performs a near-electrical operation, and input the panoramic image into a first target recognition model and a second target recognition model respectively to obtain the position information of a first target and the position information of a second target; It should be noted that the purpose of obtaining the panoramic image is to include the complete first target and second target. Both the first target recognition model and the second target recognition model are trained using a large number of historical images containing the first target and the second target. Before training, the first target or the second target in the historical images will be labeled, and the labeling object is the complete first target or second target to form a training set, and then input into the corresponding target recognition model for training, so as to obtain the first target recognition model and the second target recognition model. Therefore, the position information of the recognized first target and the position information of the second target are both complete.

[0021] It should also be pointed out that all the position information in the present invention refers to coordinates. If it is the position information of pixel points, it represents the coordinates of the pixel points. If it is the position information of a target, it refers to the coordinates of all pixel points included in the target. In addition, the first target and the second target are one of an operator or a live equipment, and the first target and the second target are different.

[0022] Step S102: Determine whether there is an overlapping area between the first target and the second target according to the position information of the first target and the position information of the second target; It should be noted that in order to accurately identify whether there is an overlapping area between the first target and the second target in the panoramic image, it is first necessary to separately obtain the first area and the second area of the area where the first target is located and the area where the second target is located, and obtain the intersection over union (IoU) of the first target and the second target in the panoramic image according to the first area and the second area; determine whether the IoU is greater than a first preset threshold; if the IoU is greater than the first preset threshold, it is determined that there is an overlapping area between the first target and the second target. Specifically, the IoU is obtained by dividing the intersection of the first area and the second area by the union of the first area and the second area. The value of the first preset threshold is set according to the specific usage scenario and is not specifically limited in this embodiment. For example, it can be 0.1, 0.2, etc.

[0023] In addition, if the IoU is less than or equal to the first preset threshold, it means that there is no overlapping area between the first target and the second target or there is an overlapping area with a very small area. In this case, pixel separation is not required. In this case, the pixel information of the first target and the second target extracted is their actual pixel values, and thus the depth values of the pixel points of the first target and the second target can be directly obtained. The subsequent steps are the same as the processing steps of the first target and the second target after pixel separation, and will not be repeated in this embodiment.

[0024] Step S103: If there is an overlapping area between the first target and the second target, segment the overlapping area from the panoramic image and input the overlapping area into a pre-trained regression model to obtain a pixel separation coefficient; It should be noted that in the process of constructing the pre-trained regression model, first obtain a first image containing a single first target and a second image containing a single second target, extract the third pixel information and the third pixel coordinates of each pixel point of the first target in the first image, and the fourth pixel information and the fourth pixel coordinates of each pixel point of the second target in the second image; then randomly fuse the pixel points in the first image with the pixel points in the second image according to the third pixel coordinates and the fourth pixel coordinates to obtain a fused image, and the size of the fused image is equal to that of the first image and the second image; extract the fused pixel information of each pixel point in the fused image, and calculate the pixel separation coefficient according to the fused pixel information and the corresponding third pixel information and fourth pixel information; input the fused pixel information of each pixel point in the fused image and the pixel separation coefficient corresponding to each fused pixel information into the regression model to be trained to obtain a pre-trained regression model.

[0025] It should be noted that in this step, theoretically, in the process of pixel fusion, the formula should be satisfied: During the training process of the regression model, since the fused image is obtained by fusing the first image and the second image with known relevant pixel information, based on this, the pixel separation coefficient can be accurately calculated. In addition, since the pixel points in the overlapping area come from the overlap of different parts of the first target and the second target, in the actual operation process, there is generally a huge difference in the appearance colors of the first target and the second target, and the shape of the overlapping area may be extremely irregular, which may further amplify the difference between the pixel part belonging to the first target and the pixel part belonging to the second target in the overlapping area. Based on this, in order to further improve the pixel separation accuracy of the overlapping area, during the training of the regression model, for each pixel point in the fused image, its actual pixel separation coefficient is calculated separately, instead of using a conventional general pixel separation coefficient to adapt to the entire fused area or overlapping area.

[0026] Step S104: Perform pixel separation on the overlapping area according to the pixel separation coefficient, and obtain the first pixel information of each pixel point in the area covered by the first target and the first coordinate information corresponding to the first pixel information, the second pixel information of each pixel point in the area covered by the second target, and the second coordinate information corresponding to the second pixel information according to the pixel separation result; It should be noted that in this step, the first average pixel information and the second average pixel information are respectively retrieved from the preset database according to the pixel information of each overlapping pixel point in the overlapping area; the first pixel information and the second pixel information are obtained according to the pixel information of each overlapping pixel point, the pixel separation coefficient corresponding to each overlapping pixel point, the first average pixel information, and the second average pixel information. As for the first coordinate information and the second coordinate information, for non-overlapping areas, they can be obtained from their respective position information, and for overlapping areas, they can be obtained from the pixel coordinates of each pixel point in the overlapping area.

[0027] In addition, it should be emphasized that during the process of pixel separation, while accurately identifying the pixel separation coefficients of each pixel point in the overlapping area, since the actual pixel information of the first target and the second target is unknown, the actual pixel information of the first target and the second target in the overlapping area cannot be obtained at this time. Therefore, in this step, the concepts of non-overlapping area and prior pixels are introduced. Due to the uncertainty limitation of the overlapping area in the panoramic image during actual shooting, if the non-overlapping area in the panoramic image is used as the source of average pixel information, on the one hand, assuming that the area of the non-overlapping area is small, resulting in a small number of covered pixel points, it will inevitably affect the representativeness of the average pixel information. On the other hand, the non-overlapping area in the panoramic image is unique, while there are a large number of pixel points that need to be pixel-separated in the overlapping area. Using the average pixel information obtained from the unique non-overlapping area as the prior pixels of all pixel points in the overlapping area, affected by pixel positions and the actual working environment, the representativeness of the average pixel information will be further reduced, resulting in a very large error in the actual pixel information of the first target and the second target finally restored.

[0028] Based on this, in some embodiments, the fused pixel information of each fusion point in the fused image is extracted. Any fusion point is defined as the target fusion point, and a first non-fused pixel set of the area covered by the first target in the first image except the target fusion point, and a second non-fused pixel set of the area covered by the second target in the second image except the target fusion point are obtained; the third average pixel information is obtained according to the third pixel information of all pixel points included in the first non-fused pixel set, and the fourth average pixel information is obtained according to the fourth pixel information of all pixel points included in the second non-fused pixel set; the fused pixel information is respectively associated with the corresponding third average pixel information and fourth pixel information one by one, and a preset database is obtained according to the association result.

[0029] In some embodiments, the first pixel information or the second pixel information is specifically obtained according to the following formula: ; wherein, represents the pixel information of the i-th overlapping pixel point, respectively represent the coordinate information of the i-th overlapping pixel point, represents the pixel separation coefficient corresponding to the i-th overlapping pixel point, represents the first pixel information or the second pixel information corresponding to the i-th overlapping pixel point, represents the first average pixel information or the second average pixel information corresponding to the i-th overlapping pixel point.

[0030] Step S105: Obtain the first spatial coordinates of each pixel point in the first target according to the first pixel information and the first coordinate information, obtain the second spatial coordinates of each pixel point in the second target according to the second pixel information and the second coordinate information, and determine whether there is a risk of near-electrical operation according to the first spatial coordinates and the second spatial coordinates.

[0031] It should be noted that in order to obtain the relevant spatial coordinates, first, the first depth value of each pixel point in the first target and the second depth value of each pixel point in the second target need to be obtained according to the first pixel information and the second pixel information respectively; The first spatial coordinates or the second spatial coordinates are calculated according to the following formula: ; where, respectively represent the x coordinate, y coordinate, and z coordinate of the i-th pixel point in the first target or the second target in the three-dimensional space, respectively represent the x coordinate and y coordinate of the i-th pixel point in the first target or the second target in the panoramic image, represents the x coordinate of the principal point and the y coordinate of the principal point of the camera used to capture the panoramic image, respectively represent the focal lengths of the camera used to capture the panoramic image in the x-axis direction and the y-axis direction, represents the depth value of the i-th pixel point in the first target or the second target in the panoramic image.

[0032] In addition, the acquisition of the depth value is obtained by identifying through the first monocular depth model and the second monocular depth model. The first monocular depth model is trained by an image containing the known pixel information and the corresponding depth value of the first target, and the second monocular depth model is trained by an image containing the known pixel information and the corresponding depth value of the second target.

[0033] In addition, then traverse the spatial distance between the pixel points in the first target and the pixel points in the second target according to the first spatial coordinates and the second spatial coordinates; determine whether the spatial distances are all greater than the second preset threshold; if there is at least one spatial distance less than or equal to the second preset threshold, it is determined that there is a risk in the current near-electrical operation, and an alarm message will be sent to the cloud service platform or the operation management platform within the first preset time to prompt the operator that there is an operation risk. The relevant information of the operator, such as the phone number, etc., is pre-stored in the platform, and thus an alarm reminder can be sent to the operator remotely; if the spatial distances are all greater than the second preset threshold, it is determined that the current near-electrical operation is safe and compliant. The second preset threshold and the first preset time are related to the specific usage requirements or application scenarios and are not detailedly limited in this embodiment.

[0034] In summary, according to the above method for identifying risks in near-electrical operations, by precisely segmenting the first target and the second target in the overlapping area to restore the pixel information that originally belonged to the first target and the second target respectively, the spatial distance between the two can be accurately calculated, thereby greatly improving the accuracy of identifying the current risks in near-electrical operations. Specifically, first, the panoramic image is respectively used to identify the first target and the second target, and then it is judged whether there is an overlapping area according to the position information of the two targets. Furthermore, the pixel separation coefficient of the overlapping area is accurately identified, so as to obtain the actual pixel information (the first pixel information) of the first target and the actual pixel information (the second pixel information) of the second target under this pixel separation coefficient. Then, based on the actual pixel information of the two, the spatial coordinates of each pixel point in the two targets are accurately calculated, and then it is accurately judged whether there are risks in near-electrical operations between the two targets.

[0035] As Figure 2 , an embodiment of the present invention further provides a system for identifying risks in near-electrical operations, and the system includes: A target recognition module 10, configured to obtain a panoramic image when an operator performs a near-electrical operation, and input the panoramic image into a first target recognition model and a second target recognition model respectively to obtain the position information of the first target and the position information of the second target; An overlapping area detection module 20, configured to judge whether there is an overlapping area between the first target and the second target according to the position information of the first target and the position information of the second target; A pixel separation coefficient recognition module 30, configured to, if there is an overlapping area between the first target and the second target, segment the overlapping area from the panoramic image and input the overlapping area into a pre-trained regression model to obtain a pixel separation coefficient; A pixel separation module 40, configured to perform pixel separation on the overlapping area according to the pixel separation coefficient, and obtain the first pixel information of each pixel point in the area covered by the first target and the first coordinate information corresponding to the first pixel information, the second pixel information of each pixel point in the area covered by the second target, and the second coordinate information corresponding to the second pixel information according to the pixel separation result; A risk detection module 50, configured to obtain the first spatial coordinates of each pixel point in the first target according to the first pixel information and the first coordinate information, obtain the second spatial coordinates of each pixel point in the second target according to the second pixel information and the second coordinate information, and judge whether there is a risk in near-electrical operations according to the first spatial coordinates and the second spatial coordinates.

[0036] On the other hand, the present invention further provides a readable storage medium, on which one or more programs are stored, and when the program is executed by a processor, the above method for identifying risks in near-electrical operations is implemented.

[0037] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored on the memory to implement the above-mentioned method for identifying the risk of working near electricity.

[0038] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a predefined sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0039] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or more wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0040] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in the memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0041] Although the embodiments of the present invention have been described in detail above, it will be apparent to those skilled in the art that various modifications and variations can be made to these embodiments. However, it should be understood that such modifications and variations are all within the scope and spirit of the present invention as described in the claims. Moreover, the present invention described herein can have other embodiments and can be implemented or realized in various ways.

Claims

1. A method for identifying risks in near-electrical operations, characterized in that, The method includes: Obtain a panoramic image when an operator performs live working near electricity, and input the panoramic image into a first target recognition model and a second target recognition model respectively to obtain the position information of a first target and the position information of a second target; Judge whether there is an overlapping area between the first target and the second target according to the position information of the first target and the position information of the second target; If there is an overlapping area between the first target and the second target, segment the overlapping area from the panoramic image, and input the overlapping area into a pre-trained regression model to obtain a pixel separation coefficient; Perform pixel separation on the overlapping area according to the pixel separation coefficient, and obtain the first pixel information of each pixel point in the area covered by the first target and the corresponding first coordinate information according to the pixel separation result, the second pixel information of each pixel point in the area covered by the second target and the corresponding second coordinate information; Obtain the first spatial coordinates of each pixel point in the first target according to the first pixel information and the first coordinate information, obtain the second spatial coordinates of each pixel point in the second target according to the second pixel information and the second coordinate information, and judge whether there is a risk of live working near electricity according to the first spatial coordinates and the second spatial coordinates.

2. The near-electrical operation risk identification method according to claim 1, wherein The step of judging whether there is an overlapping area between the first target and the second target according to the position information of the first target and the position information of the second target includes: Respectively obtain the first area of the area where the first target is located and the second area of the area where the second target is located, and obtain the intersection-over-union ratio of the first target and the second target in the panoramic image according to the first area and the second area; Judge whether the intersection-over-union ratio is greater than a first preset threshold; If the intersection-over-union ratio is greater than the first preset threshold, it is determined that there is an overlapping area between the first target and the second target.

3. The near-electrical operation risk identification method according to claim 2, wherein The step of, if there is an overlapping area between the first target and the second target, segment the overlapping area from the panoramic image, and input the overlapping area into a pre-trained regression model to obtain a pixel separation coefficient includes: Obtain a first image containing a single first target and a second image containing a single second target, extract the third pixel information and the third pixel coordinates of each pixel point of the first target in the first image, and the fourth pixel information and the fourth pixel coordinates of each pixel point of the second target in the second image; Randomly fuse the pixel points in the first image with the pixel points in the second image according to the third pixel coordinates and the fourth pixel coordinates to obtain a fused image, and the size of the fused image is equal to that of the first image and the second image; Extract the fused pixel information of each pixel point in the fused image, and calculate the pixel separation coefficient according to the fused pixel information and the corresponding third pixel information and fourth pixel information; Input the fused pixel information of each pixel point in the fused image and the pixel separation coefficient corresponding to each fused pixel information into a regression model to be trained to obtain a pre-trained regression model.

4. The near-electrical operation risk identification method according to claim 3, wherein The step of separating pixels of the overlapping region according to the pixel separation coefficient, and obtaining the first pixel information of each pixel point in the region covered by the first target and the first coordinate information corresponding to the first pixel information, and the second pixel information of each pixel point in the region covered by the second target and the second coordinate information corresponding to the second pixel information includes: Respectively retrieve the first average pixel information and the second average pixel information from a preset database according to the pixel information of each overlapping pixel point in the overlapping region; Obtain the first pixel information and the second pixel information according to the pixel information of each overlapping pixel point, the pixel separation coefficient corresponding to each overlapping pixel point, the first average pixel information, and the second average pixel information.

5. The near-electrical operation risk identification method according to claim 4, wherein The step of constructing the preset database includes: Extract the fused pixel information of each fused point in the fused image, define any fused point as the target fused point, obtain the first non-fused pixel set in the region covered by the first target in the first image except the target fused point, and the second non-fused pixel set in the region covered by the second target in the second image except the target fused point; Obtain the third average pixel information according to the third pixel information of all pixel points included in the first non-fused pixel set, and obtain the fourth average pixel information according to the fourth pixel information of all pixel points included in the second non-fused pixel set; Associate the fused pixel information with the corresponding third average pixel information and fourth pixel information one by one, and obtain the preset database according to the association result.

6. The near-electrical-operation risk identification method according to claim 4, wherein The step of obtaining the first pixel information and the second pixel information according to the pixel information of each overlapping pixel point, the pixel separation coefficient corresponding to each overlapping pixel point, the first average pixel information, and the second average pixel information includes: Obtain the first pixel information or the second pixel information according to the following formula: ； Among them, represents the pixel information of the i-th overlapping pixel point, respectively represent the coordinate information of the i-th overlapping pixel point, represents the pixel separation coefficient corresponding to the i-th overlapping pixel point, represents the first pixel information or the second pixel information corresponding to the i-th overlapping pixel point, represents the first average pixel information or the second average pixel information corresponding to the i-th overlapping pixel point.

7. The near-electrical operation risk identification method according to claim 6, characterized in that The step of obtaining the first spatial coordinates of each pixel point in the first target according to the first pixel information and the first coordinate information, and obtaining the second spatial coordinates of each pixel point in the second target according to the second pixel information and the second coordinate information includes: Respectively obtain the first depth value of each pixel point in the first target and the second depth value of each pixel point in the second target according to the first pixel information and the second pixel information; Calculate and obtain the first spatial coordinates or the second spatial coordinates according to the following formula: ； Among them, respectively represent the x coordinate, y coordinate, and z coordinate of the i-th pixel point in the first target or the second target in the three-dimensional space, respectively represent the x coordinate and y coordinate of the i-th pixel point in the first target or the second target in the panoramic image, represent the x coordinate of the principal point and the y coordinate of the principal point of the camera used to capture the panoramic image, respectively represent the focal lengths of the camera used to capture the panoramic image in the x-axis direction and the y-axis direction, represents the depth value of the i-th pixel point in the first target or the second target in the panoramic image.

8. The near-electrical-operation risk identification method according to claim 6, wherein The step of determining whether there is a risk of near-electrical operation according to the first spatial coordinates and the second spatial coordinates includes: Traverse the spatial distance between the pixel points in the first target and the pixel points in the second target according to the first spatial coordinates and the second spatial coordinates; Judge whether the spatial distance is greater than a second preset threshold; If there is at least one spatial distance less than or equal to the second preset threshold, it is determined that the current near-electrical operation is risky; If the spatial distances are all greater than the second preset threshold, it is determined that the current near-electrical operation is safe and compliant.

9. A near-electrical-operation risk identification system, characterized in that, The system includes: A target recognition module, configured to obtain a panoramic image when an operator performs an operation near electricity, and input the panoramic image into a first target recognition model and a second target recognition model respectively to obtain position information of a first target and position information of a second target; An overlapping area detection module, configured to determine whether there is an overlapping area between the first target and the second target according to the position information of the first target and the position information of the second target; A pixel separation coefficient recognition module, configured to, if there is an overlapping area between the first target and the second target, segment the overlapping area from the panoramic image, and input the overlapping area into a pre-trained regression model to obtain a pixel separation coefficient; A pixel separation module, configured to perform pixel separation on the overlapping area according to the pixel separation coefficient, and obtain first pixel information of each pixel point in the area covered by the first target and first coordinate information corresponding to the first pixel information, second pixel information of each pixel point in the area covered by the second target, and second coordinate information corresponding to the second pixel information according to the pixel separation result; A risk detection module, configured to obtain first spatial coordinates of each pixel point in the first target according to the first pixel information and the first coordinate information, obtain second spatial coordinates of each pixel point in the second target according to the second pixel information and the second coordinate information, and determine whether there is a risk of an operation near electricity according to the first spatial coordinates and the second spatial coordinates.

10. A readable storage medium, characterized in that, The readable storage medium stores one or more programs, which when executed by a processor implement the method for identifying the risk of an operation near electricity according to any one of claims 1-8.

Images