Power construction risk assessment management method and system

Abstract

The invention discloses an electric power construction risk assessment management method and system, and belongs to the technical field of data processing, and the method comprises the steps: presetting monitoring and risk prompt equipment, constructing a construction site three-dimensional coordinate system, recognizing and positioning construction elements and objects in real time, combining a construction specification file library, and precisely matching and pushing construction specifications and risk prompts to the nearest equipment. Meanwhile, the system can identify the wearing information of the construction personnel, timely correct the violation behaviors, effectively improve the safety and management efficiency of the construction site, reduce the accident risk, and provide powerful guarantee for the safety of power construction. The problem that in the prior art, safety risk information transmission is low in accuracy and efficiency in the power construction process is solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and system for risk assessment management of electric power construction. Background Art

[0002] In the field of power construction, safety management and risk assessment of the construction site are crucial. Power construction often involves high-risk links such as high voltage electricity, high-altitude operations, and large-scale machinery operations.

[0003] Traditionally, the safety management of power construction mainly relies on manual supervision and empirical judgment. However, this method has many limitations. With the advancement of science and technology, especially the rapid development of image recognition technology, sensor technology, motion capture technology and information technology, new opportunities have been provided for the safety management of power construction. These technologies can monitor the situation of the construction site in real time, identify the wear information, motion information and other dynamic elements of the construction site of the construction workers, and provide accurate and objective data support for risk assessment and safety management.

[0004] However, the current power construction safety management systems in the existing technology mostly focus on the accuracy of judgment, but ignore the accuracy and efficiency of information transmission. There are a large number of situations where risk monitoring finds problems but cannot be communicated in a timely manner, resulting in the failure of risk management and failure to prevent accidents.

[0005] Therefore, how to efficiently and accurately identify the risks that may arise during power construction and convey them to construction personnel or managers in a timely and accurate manner is a technical problem that urgently needs to be solved. Summary of the invention

[0006] In response to the problem of low accuracy and efficiency in the transmission of safety risk information during power construction in the prior art, the present invention provides a risk assessment management method and system for power construction. By pre-setting monitoring and risk warning equipment, a three-dimensional coordinate system for the construction site is constructed, and construction elements and objects are identified and located in real time. Combined with the construction specification file library, the construction specifications and risk warnings are accurately matched and pushed to the nearest equipment to ensure instant information transmission. At the same time, the system can identify the wearing information of construction personnel, correct violations in a timely manner, effectively improve the safety and management efficiency of the construction site, reduce the risk of accidents, provide strong protection for power construction safety, and solve the problem of low accuracy and efficiency in the transmission of safety risk information during power construction in the prior art.

[0007] The following is the technical solution of the present invention.

[0008] The risk assessment management method for power construction includes the following steps: S1: Preset several monitoring devices and risk warning devices on site that communicate with the management center; S2: Acquire continuous on-site construction image frames, obtain a background image by comparing previous and next frames, and establish a three-dimensional coordinate system of the construction site based on the background image; S3: Recognize the background image, obtain several elements in the background image, and determine the position of each element in the three-dimensional coordinate system; S4: searching the preset construction specification file library using the name of the element as a keyword to obtain the construction specification information of each element; S5: Continue to acquire continuous on-site construction image frames, perform XOR calculation with the background image, and obtain a dynamic image; S6: Recognize the dynamic image to obtain several objects in the dynamic image, determine the position of each object in the three-dimensional coordinate system, determine the element closest to the object based on the position of the object and the position of the element, and use the nearest risk warning device on site to output the construction specification information corresponding to the element; S7: Identify the wearing information of the object and compare it with the personnel specification information in the construction specification file library. If it is determined that there is a violation, use the nearest risk warning device on site to output risk warning information.

[0009] In the present invention, the background, elements, objects and three-dimensional coordinate system of the construction site are bundled through various identification means, and at the same time, the dimensional isolation between the normative documents and the actual construction site is broken, so that it can accurately judge whether the construction site is standardized or not, and on the basis of the identification, the nearest risk warning device can be found to provide prompts for relevant content. Therefore, after the implementation of the present invention, at the power construction site, when construction workers are close to different elements (such as transformers, wires and cables, guardrails, cranes, scaffolding, etc.), or when they are not dressed properly, the nearest risk warning device will provide corresponding prompts, which effectively improves the safety and management efficiency of the construction site, reduces the risk of accidents, provides strong protection for the safety of power construction, and solves the problems of low accuracy and efficiency in the transmission of safety risk information during power construction in the prior art.

[0010] Preferably, the S1: preset several monitoring devices and risk warning devices on site that are connected to the management center for communication, including: According to the on-site terrain of the power construction, at least three monitoring devices are set up to collect images of the site from different angles; According to the on-site terrain of the power construction, fixed risk warning equipment and / or mobile risk warning equipment are set up, among which the fixed risk warning equipment is set according to the location of the construction target, and the mobile risk warning equipment is carried by the construction personnel.

[0011] Preferably, the step S2: acquiring continuous on-site construction image frames, obtaining a background image by comparing previous and next frames, and establishing a three-dimensional coordinate system of the construction site based on the background image, comprises: Acquire continuous on-site construction image frames and perform denoising, grayscale or color space conversion; The inter-frame difference method is used to make judgments by calculating the difference between the same pixels in adjacent frames. The area where the difference is less than the threshold is the static area, and the rest is the dynamic area. Continue to use the inter-frame difference method to judge the difference of the same pixel points between subsequent adjacent frames. The area with a difference value less than the threshold is the static area, and the rest is the dynamic area; The different static areas obtained are combined in the same image to obtain a complete static area as the background image; The background image is reconstructed in three dimensions using three-dimensional reconstruction technology to obtain the three-dimensional coordinate system of the construction site.

[0012] Preferably, the three-dimensional reconstruction of the background image using the three-dimensional reconstruction technology to obtain the three-dimensional coordinate system of the construction site includes: Based on the extracted background image, identifying feature points corresponding to corner points, edges or textures in the background image; Using a feature point matching algorithm, the identified feature points are matched with the feature points in the pre-defined three-dimensional model of the construction site to establish a corresponding relationship between the image pixel coordinates and the three-dimensional space coordinates; Based on the matched feature point pairs, a 3D reconstruction algorithm is used to calculate the 3D coordinate information of the construction site, including depth, height and width; Based on the calculated three-dimensional coordinate information, a three-dimensional coordinate system of the construction site is constructed to reflect the actual spatial layout and object positions of the construction site.

[0013] Preferably, the step S3: identifying the background image, obtaining several elements in the background image, and determining the position of each element in the three-dimensional coordinate system includes: Traverse the pixels of the background image, and divide the adjacent pixels with similar grayscale values ​​into the same target area, and the grayscale values ​​are considered to be similar if the grayscale value difference is less than a preset difference; Use machine learning or deep learning algorithms to identify each target area separately, obtain several elements and corresponding pixel coordinates, and take the lowest coordinate point of the pixel coordinates corresponding to the element as the element coordinates; Based on the correspondence between pixel coordinates and the three-dimensional coordinate system, the coordinate value of the element coordinates in the three-dimensional coordinate system is calculated to determine its actual position in the three-dimensional space, and each element is marked in the three-dimensional coordinate system.

[0014] In the present invention, the position is determined based on the lowest coordinate point of the pixel coordinates, which is convenient for distance calculation and determination.

[0015] Preferably, the step S4: searching a preset construction specification file library using the name of the element as a keyword to obtain construction specification information of each element includes: The text information of several construction specification documents is used in advance to form a construction specification document library, which is classified and indexed according to the name or other relevant attributes; Extract the name of the element as a keyword, search in the preset construction specification document library, and obtain the initial inspection results; Organize and screen the initial inspection results, exclude irrelevant or outdated specification information for the current construction site, and obtain accurate construction specification information; The construction specification information is associated with the corresponding elements to obtain the construction specification information of each element, forming an element-specification information pair.

[0016] Preferably, S5: continue to acquire continuous on-site construction image frames, perform XOR calculation with the background image, and obtain a dynamic image, including: Continue to acquire continuous on-site construction image frames, perform XOR calculation on each construction image frame and the background image, set pixels with the same pixel values ​​to zero, and use the area formed by the pixel coordinates of the remaining pixels as the dynamic image area. In different on-site construction image frames, each pixel point and its pixel value contained in the dynamic image area together constitute a dynamic image.

[0017] Preferably, the step S6: identifying the dynamic image to obtain a number of objects in the dynamic image, determining the position of each object in the three-dimensional coordinate system, judging the element closest to the object based on the position of the object and the position of the element, and outputting the construction specification information corresponding to the element using the nearest risk warning device on site, includes: Using machine learning or deep learning algorithms to identify dynamic images, and obtaining several objects in the dynamic images; The lowest coordinate point of the pixel coordinates involved in the object is taken as the object coordinates; Based on the correspondence between the pixel coordinates and the three-dimensional coordinate system, the coordinate values ​​of the object coordinates in the three-dimensional coordinate system are calculated to determine the actual position of the object in the three-dimensional space; Based on the coordinate values ​​of the object coordinates in the three-dimensional coordinate system and the coordinate values ​​of different feature coordinates in the three-dimensional coordinate system, the Euclidean distance between them is calculated: ; Where: (x1, y1, z1) is the coordinate value of the object coordinate in the three-dimensional coordinate system, (x2, y2, z2) is the coordinate value of the feature coordinate in the three-dimensional coordinate system, and d is the Euclidean distance between the two points; The element closest to the object is determined based on the Euclidean distance, and the construction specification information corresponding to the element is output using the nearest risk warning device on site based on the location of the element.

[0018] Preferably, the S7: identifying the wearing information of the object and comparing it with the personnel specification information in the construction specification file library, and if it is determined that there is a violation, outputting risk warning information using the nearest risk warning device on site, including: Based on the recognition of dynamic images by machine learning or deep learning algorithms, the wearing information of the object is further recognized; Among them, the wearing information includes safety helmets, safety shoes, protective clothing, reflective clothing, and safety belts, and each item outputs yes or no; Extract personnel specification information from the construction specification file library, filter each wearing specification based on the power construction project, and output actual specification information of yes or no based on each wearing specification; If there is a sub-item where the wearing specification is yes and the wearing information is no, it is considered a violation. Based on the location of the object, the nearest risk warning device is matched to output risk warning information.

[0019] The present invention also provides an electric power construction risk assessment management system, including a management center, monitoring equipment and risk warning equipment connected to the management center for communication. When the system is running, the above-mentioned electric power construction risk assessment management method is executed.

[0020] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned power construction risk assessment management method when calling the computer program in the memory.

[0021] The present invention also provides a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of the above-mentioned power construction risk assessment management method are implemented.

[0022] The substantial effects of the present invention include: Through the preset monitoring equipment and risk warning equipment, combined with the construction of a three-dimensional coordinate system, accurate positioning and real-time monitoring of various elements on the construction site are achieved, which greatly improves the accuracy and timeliness of risk identification, allowing potential safety hazards to be quickly discovered and effectively controlled.

[0023] Through the establishment and application of the construction specification document library, the present invention realizes the standardized management of construction site operations. When construction workers approach specific elements or perform illegal operations, the nearest risk warning device can instantly output the corresponding construction specification information or risk warning, effectively guiding construction workers to standardize operations and reduce safety accidents caused by human errors. The present invention can automatically process and analyze the image data of the construction site, identify the wearing information of the construction workers, and automatically compare and judge with the construction specifications. It reduces the burden of manual supervision and improves the efficiency and accuracy of risk management.

[0024] At the same time, relying on the unique arrangement of risk warning equipment, the present invention significantly improves the accuracy and efficiency of risk warnings at power construction sites, enables safety management to truly play a role, reduces the incidence of safety accidents, and provides a strong guarantee for the safe and efficient conduct of power construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution will be clearly and completely described below in combination with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] It should be understood that in various embodiments of the present invention, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0028] It should be understood that in the present invention, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0029] It should be understood that in the present invention, "plurality" refers to two or more than two. "And / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "Contains A, B and C", "Contains A, B, C" means that A, B, and C are all included, "Contains A, B or C" means that one of A, B, and C is included, and "Contains A, B and / or C" means that any one, any two, or any three of A, B, and C are included.

[0030] The technical solution of the present invention is described in detail with specific embodiments below. The embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0031] Embodiment 1: Power construction risk assessment management methods, such as Figure 1 As shown, the following steps are included: S1: Preset several monitoring devices and risk warning devices on site that communicate with the management center.

[0032] Specifically include: According to the on-site terrain of the power construction, at least three monitoring devices are set up to collect images of the site from different angles; According to the on-site terrain of the power construction, fixed risk warning equipment and / or mobile risk warning equipment are set up, among which the fixed risk warning equipment is set according to the location of the construction target, and the mobile risk warning equipment is carried by the construction personnel.

[0033] For example, at a substation construction site, four high-definition surveillance cameras were set up around the site as monitoring equipment. They can fully cover the construction site from different angles and communicate with the management center in real time. At the same time, fixed speakers were installed as risk warning devices in key construction areas such as transformers and high-voltage lines to provide safety warning information. In addition, each construction worker is equipped with a mobile risk warning device with an alarm function, such as a smart watch, smart helmet, etc. Once a violation is detected, the management center will immediately identify it through the monitoring equipment and send an alarm to the construction worker through these mobile devices to ensure the immediate communication of safety information.

[0034] S2: Acquire continuous on-site construction image frames, obtain a background image by comparing previous and next frames, and establish a three-dimensional coordinate system of the construction site based on the background image.

[0035] Specifically include: Acquire continuous on-site construction image frames and perform denoising, grayscale or color space conversion; The inter-frame difference method is used to make judgments by calculating the difference between the same pixels in adjacent frames. The area where the difference is less than the threshold is the static area, and the rest is the dynamic area. Continue to use the inter-frame difference method to judge the difference of the same pixel points between subsequent adjacent frames. The area with a difference value less than the threshold is the static area, and the rest is the dynamic area; For example, calculate the gray value difference of the same pixel in the two frames of images. Set a reasonable threshold (such as 10). When the gray value difference of a pixel is less than the threshold, the pixel is considered to belong to the static area; otherwise, it belongs to the dynamic area.

[0036] The different static areas obtained are combined in the same image to obtain a complete static area as the background image; Based on the extracted background image, identifying feature points corresponding to corner points, edges or textures in the background image; Using a feature point matching algorithm, the identified feature points are matched with the feature points in the pre-defined three-dimensional model of the construction site to establish a corresponding relationship between the image pixel coordinates and the three-dimensional space coordinates; Based on the matched feature point pairs, a 3D reconstruction algorithm is used to calculate the 3D coordinate information of the construction site, including depth, height and width; Based on the calculated three-dimensional coordinate information, a three-dimensional coordinate system of the construction site is constructed to reflect the actual spatial layout and object positions of the construction site.

[0037] For example, this embodiment can use SIFT, SURF or ORB algorithms to automatically identify key feature points such as corners and edges in the background image, and can use feature point matching algorithms such as FLANN or BFMatcher to accurately match the identified image feature points with the feature points in the pre-built three-dimensional model of the construction site. At the same time, the matching process can be accelerated by efficient data structures (such as kd trees). Then, this embodiment can use three-dimensional reconstruction algorithms such as SFM or MVS to calculate and determine the three-dimensional coordinates of each position on the construction site, and then use computer graphics and three-dimensional modeling software (such as Blender, 3dsMax or Unity) to construct a three-dimensional coordinate system that is completely consistent with the actual layout of the construction site.

[0038] For example, after identifying a utility pole in the background image, the system can determine its precise position in the three-dimensional coordinate system, and then provide accurate safety distance prompts for any construction workers approaching the utility pole, effectively preventing safety accidents such as electric shock. In this way, safety management at power construction sites has been significantly improved.

[0039] S3: Identify the background image, obtain several elements in the background image, and determine the position of each element in the three-dimensional coordinate system.

[0040] Specifically include: Traverse the pixels of the background image, and divide the adjacent pixels with similar grayscale values ​​into the same target area, and the grayscale values ​​are considered to be similar if the grayscale value difference is less than a preset difference; Use machine learning or deep learning algorithms to identify each target area separately, obtain several elements and corresponding pixel coordinates, and take the lowest coordinate point of the pixel coordinates corresponding to the element as the element coordinates; Based on the correspondence between pixel coordinates and the three-dimensional coordinate system, the coordinate value of the element coordinates in the three-dimensional coordinate system is calculated to determine its actual position in the three-dimensional space, and each element is marked in the three-dimensional coordinate system.

[0041] In this embodiment, the position is determined based on the lowest coordinate point of the pixel coordinates, which is convenient for distance calculation and determination.

[0042] For example, a deep learning model (such as YOLOv5) is used to identify each target area, determine its feature category, such as "transformer", "telephone pole", etc., and record the pixel coordinate range corresponding to the feature. To simplify the calculation, the system selects the pixel coordinate point at the bottom of each feature area as the representative coordinate of the feature.

[0043] Subsequently, based on the previously established correspondence between the three-dimensional coordinate system and the image pixel coordinates, the system converts the representative coordinates of the elements into actual coordinates in three-dimensional space. For example, the transformer is precisely located at the position (x=30, y=5, z=2) in the three-dimensional coordinate system and marked at the corresponding position in the three-dimensional model. Through this method, the system can quickly and accurately identify and locate various elements on the construction site, providing a solid foundation for risk assessment and management.

[0044] S4: Search the preset construction specification file library using the name of the element as a keyword to obtain the construction specification information of each element.

[0045] Specifically include: The text information of several construction specification documents is used in advance to form a construction specification document library, which is classified and indexed according to the name or other relevant attributes; Extract the name of the element as a keyword, search in the preset construction specification document library, and obtain the initial inspection results; Organize and screen the initial inspection results, exclude irrelevant or outdated specification information for the current construction site, and obtain accurate construction specification information; The construction specification information is associated with the corresponding elements to obtain the construction specification information of each element, forming an element-specification information pair.

[0046] For example, in this embodiment, in order to ensure that construction activities comply with the specifications, the system builds a detailed construction specification document library. The library contains various power construction specification documents, such as "Power Construction Safety Work Regulations", "Electrical Equipment Installation Regulations", etc., and is classified and indexed by element name (such as "transformer" and "cable").

[0047] When the system identifies an element at the construction site, such as "transformer", it automatically extracts the name of the element as a keyword and searches for it in the construction specification document library. For example, the system enters "transformer" as a keyword and quickly retrieves relevant specification items, such as the installation location requirements and safety distance regulations for transformers.

[0048] Subsequently, the system intelligently screens the search results, eliminating the specification information that is irrelevant to the current construction site or outdated, ensuring that the provided specifications are the latest and applicable. Finally, the system associates the screened specification information with the "transformer" element to form a "transformer-construction specification information pair". In this way, construction personnel can instantly obtain accurate construction guidance for the "transformer" to ensure that the operation complies with safety regulations.

[0049] S5: Continue to acquire continuous on-site construction image frames, perform XOR calculation with the background image, and obtain a dynamic image.

[0050] Specifically include: Continue to acquire continuous on-site construction image frames, perform XOR calculation on each construction image frame and the background image, set pixels with the same pixel values ​​to zero, and use the area formed by the pixel coordinates of the remaining pixels as the dynamic image area. In different on-site construction image frames, each pixel point and its pixel value contained in the dynamic image area together constitute a dynamic image.

[0051] For example, at a certain moment, the system captures an image frame that includes a construction worker operating a crane. Next, the system XORs this real-time image frame with the previously established background image. During the calculation process, any pixels with the same pixel value (i.e., the static part of the background image) are set to zero, and the remaining pixels form the dynamic image area. For example, the crane operator and the moving part of the crane appear after the XOR calculation, while static elements such as buildings and fixed equipment in the background are eliminated.

[0052] Through such processing, the system can accurately extract dynamic image areas in different continuous image frames, which contain key dynamic information such as the activities of construction workers and the movement of equipment. These dynamic images provide an important basis for subsequent object recognition and risk assessment.

[0053] S6: Identify the dynamic image to obtain several objects in the dynamic image, determine the position of each object in the three-dimensional coordinate system, judge the element closest to the object based on the position of the object and the position of the element, and use the nearest risk warning device on site to output the construction specification information corresponding to the element.

[0054] Specifically include: Using machine learning or deep learning algorithms to identify dynamic images, and obtaining several objects in the dynamic images; The lowest coordinate point of the pixel coordinates involved in the object is taken as the object coordinates; Based on the correspondence between the pixel coordinates and the three-dimensional coordinate system, the coordinate values ​​of the object coordinates in the three-dimensional coordinate system are calculated to determine the actual position of the object in the three-dimensional space; Based on the coordinate values ​​of the object coordinates in the three-dimensional coordinate system and the coordinate values ​​of different feature coordinates in the three-dimensional coordinate system, the Euclidean distance between them is calculated: ; Where: (x1, y1, z1) is the coordinate value of the object coordinate in the three-dimensional coordinate system, (x2, y2, z2) is the coordinate value of the feature coordinate in the three-dimensional coordinate system, and d is the Euclidean distance between the two points; The element closest to the object is determined based on the Euclidean distance, and the construction specification information corresponding to the element is output using the nearest risk warning device on site based on the location of the element.

[0055] For example, through deep learning algorithms, the system identified a construction worker (object) approaching a high-voltage transformer (element) from a dynamic image. The system uses the bottom pixel coordinate point of the construction worker's image as the object coordinate, and uses the previously established correspondence between the pixel coordinates and the three-dimensional coordinate system to calculate the actual position of the construction worker in three-dimensional space. Next, the system calculates the Euclidean distance between the construction worker and the high-voltage transformer. By comparison, the system determines that the element closest to the construction worker is the high-voltage transformer.

[0056] Based on this judgment, the system immediately outputs relevant construction specification information of the high-voltage transformer to the construction personnel through the nearest risk warning device at the construction site, such as speakers, smart speakers, or smart wearable devices, including safe operating distances, necessary protective measures, etc., to ensure the safety of construction activities.

[0057] S7: Identify the wearing information of the object and compare it with the personnel specification information in the construction specification file library. If it is determined that there is a violation, use the nearest risk warning device on site to output risk warning information.

[0058] Specifically include: Based on the recognition of dynamic images by machine learning or deep learning algorithms, the wearing information of the object is further recognized; Among them, the wearing information includes safety helmets, safety shoes, protective clothing, reflective clothing, and safety belts, and each item outputs yes or no; Extract personnel specification information from the construction specification file library, filter each wearing specification based on the power construction project, and output actual specification information of yes or no based on each wearing specification; If there is a sub-item where the wearing specification is yes and the wearing information is no, it is considered a violation. Based on the location of the object, the nearest risk warning device is matched to output risk warning information.

[0059] For example, the system uses a deep learning algorithm to identify that a construction worker (object) is not wearing a safety helmet. The system has extracted personnel specification information from the construction specification document library in advance, clearly defining the safety equipment that must be worn in power construction projects, including safety helmets, safety shoes, etc., and marking the necessity of each wearing specification (yes / no). By comparison, the system found that the construction worker did not wear a safety helmet, that is, the "safety helmet" sub-item in the wearing information was no, while the wearing specification required it to be worn (yes). This constitutes a violation.

[0060] The system immediately matches the nearest risk warning device, such as a nearby speaker, based on the current location of the construction worker. The device then issues a voice prompt: "Please note that you are not wearing a safety helmet. Please correct it immediately!" This reminds the construction worker to comply with safety regulations and prevent potential safety risks.

[0061] In this embodiment, the background, elements, objects and three-dimensional coordinate system of the construction site are bundled through various identification means, and at the same time, the dimensional isolation between the normative documents and the actual construction site is broken, so that it can accurately judge whether the construction site is standardized or not, and on the basis of the identification, the nearest risk warning device can be found to provide prompts for relevant content. Therefore, after the implementation of this embodiment, at the power construction site, when construction workers are close to different elements (such as transformers, wires and cables, guardrails, cranes, scaffolding, etc.), or when they are not dressed properly, the nearest risk warning device will provide corresponding prompts, effectively improving the safety and management efficiency of the construction site, reducing the risk of accidents, providing strong protection for the safety of power construction, and solving the problems of low accuracy and efficiency in the transmission of safety risk information during power construction in the prior art.

[0062] Embodiment 2: This embodiment also provides a power construction risk assessment management system, including a management center, monitoring equipment and risk warning equipment connected to the management center for communication. When the system is running, the above-mentioned power construction risk assessment management method is executed.

[0063] Among them, the monitoring equipment is usually a high-definition surveillance camera, and the risk warning equipment can be various smart wearable devices, or speakers and sound boxes fixed on site.

[0064] Embodiment 3: This embodiment also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned power construction risk assessment management method when calling the computer program in the memory.

[0065] Embodiment 4: This embodiment also provides a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of the above-mentioned power construction risk assessment management method are implemented.

[0066] The substantial effects of the embodiments of the present application include: Through the preset monitoring equipment and risk warning equipment, combined with the construction of a three-dimensional coordinate system, accurate positioning and real-time monitoring of various elements on the construction site are achieved, which greatly improves the accuracy and timeliness of risk identification, allowing potential safety hazards to be quickly discovered and effectively controlled.

[0067] Through the establishment and application of the construction specification document library, this embodiment realizes the standardized management of construction site operations. When construction workers are close to specific elements or perform illegal operations, the nearest risk warning device can instantly output the corresponding construction specification information or risk warning, effectively guide construction workers to standardize operations, and reduce safety accidents caused by human errors. This embodiment can automatically process and analyze the image data of the construction site, identify the wearing information of the construction workers, and automatically compare and judge with the construction specifications. It reduces the burden of manual supervision and improves the efficiency and accuracy of risk management.

[0068] At the same time, this embodiment relies on the unique layout of risk warning equipment to significantly improve the accuracy and efficiency of risk warnings at power construction sites, allowing safety management to truly play a role, reducing the incidence of safety accidents, and providing a strong guarantee for the safe and efficient conduct of power construction.

[0069] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the specific device can be divided into different functional modules to complete all or part of the functions described above.

[0070] In the embodiments provided in the present application, it should be understood that the disclosed structures and methods can be implemented in other ways. For example, the embodiments of the structure described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another structure, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, structures or units, which can be electrical, mechanical or other forms.

[0071] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0072] In addition, each functional unit in the embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0073] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0074] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for risk assessment and management of power construction, characterized in that: The following steps are involved: S1: Preset several monitoring devices and risk warning devices on site that communicate with the management center; S2: Acquire continuous on-site construction image frames, obtain a background image by comparing previous and next frames, and establish a three-dimensional coordinate system of the construction site based on the background image; S3: Recognize the background image, obtain several elements in the background image, and determine the position of each element in the three-dimensional coordinate system; S4: searching the preset construction specification file library using the name of the element as a keyword to obtain the construction specification information of each element; S5: Continue to acquire continuous on-site construction image frames, perform XOR calculation with the background image, and obtain a dynamic image; S6: Recognize the dynamic image to obtain several objects in the dynamic image, determine the position of each object in the three-dimensional coordinate system, determine the element closest to the object based on the position of the object and the position of the element, and use the nearest risk warning device on site to output the construction specification information corresponding to the element; S7: Identify the wearing information of the object and compare it with the personnel specification information in the construction specification file library. If it is determined that there is a violation, use the nearest risk warning device on site to output risk warning information.

2. The power construction risk assessment management method according to claim 1 is characterized in that: S1: Preset several monitoring devices and risk warning devices that communicate with the management center on site, including: According to the on-site terrain of the power construction, at least three monitoring devices are set up to collect images of the site from different angles; According to the on-site terrain of the power construction, fixed risk warning equipment and / or mobile risk warning equipment are set up, among which the fixed risk warning equipment is set according to the location of the construction target, and the mobile risk warning equipment is carried by the construction personnel.

3. The power construction risk assessment management method according to claim 1 is characterized in that: S2: acquiring continuous on-site construction image frames, obtaining a background image by comparing previous and next frames, and establishing a three-dimensional coordinate system of the construction site based on the background image, including: Acquire continuous on-site construction image frames and perform denoising, grayscale or color space conversion; The inter-frame difference method is used to make judgments by calculating the difference between the same pixels in adjacent frames. The area where the difference is less than the threshold is the static area, and the rest is the dynamic area. Continue to use the inter-frame difference method to judge the difference of the same pixel points between subsequent adjacent frames. The area with a difference value less than the threshold is the static area, and the rest is the dynamic area; The different static areas obtained are combined in the same image to obtain a complete static area as the background image; The background image is reconstructed in three dimensions using three-dimensional reconstruction technology to obtain the three-dimensional coordinate system of the construction site.

4. The power construction risk assessment management method according to claim 3 is characterized in that: The three-dimensional reconstruction of the background image using the three-dimensional reconstruction technology to obtain the three-dimensional coordinate system of the construction site includes: Based on the extracted background image, identifying feature points corresponding to corner points, edges or textures in the background image; Using a feature point matching algorithm, the identified feature points are matched with the feature points in the pre-defined three-dimensional model of the construction site to establish a corresponding relationship between the image pixel coordinates and the three-dimensional space coordinates; Based on the matched feature point pairs, a 3D reconstruction algorithm is used to calculate the 3D coordinate information of the construction site, including depth, height and width; Based on the calculated three-dimensional coordinate information, a three-dimensional coordinate system of the construction site is constructed to reflect the actual spatial layout and object positions of the construction site.

5. The power construction risk assessment management method according to claim 1 is characterized in that: S3: identifying the background image, obtaining several elements in the background image, and determining the position of each element in the three-dimensional coordinate system, including: Traverse the pixels of the background image, and divide the adjacent pixels with similar grayscale values ​​into the same target area, and the grayscale values ​​are considered to be similar if the grayscale value difference is less than a preset difference; Use machine learning or deep learning algorithms to identify each target area separately, obtain several elements and corresponding pixel coordinates, and take the lowest coordinate point of the pixel coordinates corresponding to the element as the element coordinates; Based on the correspondence between pixel coordinates and the three-dimensional coordinate system, the coordinate value of the element coordinates in the three-dimensional coordinate system is calculated to determine its actual position in the three-dimensional space, and each element is marked in the three-dimensional coordinate system.

6. The power construction risk assessment management method according to claim 1 is characterized in that: S4: searching the preset construction specification file library using the name of the element as a keyword to obtain the construction specification information of each element, including: The text information of several construction specification documents is used in advance to form a construction specification document library, which is classified and indexed according to the name or other relevant attributes; Extract the name of the element as a keyword, search in the preset construction specification document library, and obtain the initial inspection results; Organize and screen the initial inspection results, exclude irrelevant or outdated specification information for the current construction site, and obtain accurate construction specification information; The construction specification information is associated with the corresponding elements to obtain the construction specification information of each element, forming an element-specification information pair.

7. The power construction risk assessment management method according to claim 1 is characterized in that: S5: Continue to obtain continuous on-site construction image frames, perform XOR calculation with the background image, and obtain a dynamic image, including: Continue to acquire continuous on-site construction image frames, perform XOR calculation on each construction image frame and the background image, set pixels with the same pixel values ​​to zero, and use the area formed by the pixel coordinates of the remaining pixels as the dynamic image area. In different on-site construction image frames, each pixel point and its pixel value contained in the dynamic image area together constitute a dynamic image.

8. The power construction risk assessment management method according to claim 5 is characterized in that: S6: identifying the dynamic image, obtaining several objects in the dynamic image, determining the position of each object in the three-dimensional coordinate system, judging the element closest to the object based on the position of the object and the position of the element, and outputting the construction specification information corresponding to the element using the nearest risk warning device on site, including: Using machine learning or deep learning algorithms to identify dynamic images, and obtaining several objects in the dynamic images; The lowest coordinate point of the pixel coordinates involved in the object is taken as the object coordinates; Based on the correspondence between the pixel coordinates and the three-dimensional coordinate system, the coordinate values ​​of the object coordinates in the three-dimensional coordinate system are calculated to determine the actual position of the object in the three-dimensional space; Based on the coordinate values ​​of the object coordinates in the three-dimensional coordinate system and the coordinate values ​​of different feature coordinates in the three-dimensional coordinate system, the Euclidean distance between them is calculated: ； Where: (x1, y1, z1) is the coordinate value of the object coordinate in the three-dimensional coordinate system, (x2, y2, z2) is the coordinate value of the feature coordinate in the three-dimensional coordinate system, and d is the Euclidean distance between the two points; The element closest to the object is determined based on the Euclidean distance, and the construction specification information corresponding to the element is output using the nearest risk warning device on site based on the location of the element.

9. The power construction risk assessment management method according to claim 1, characterized in that: S7: identifying the wearing information of the object and comparing it with the personnel specification information in the construction specification file library. If it is determined that there is a violation, the nearest risk warning device on site is used to output risk warning information, including: Based on the recognition of dynamic images by machine learning or deep learning algorithms, the wearing information of the object is further recognized; Among them, the wearing information includes safety helmets, safety shoes, protective clothing, reflective clothing, and safety belts, and each item outputs yes or no; Extract personnel specification information from the construction specification file library, filter each wearing specification based on the power construction project, and output actual specification information of yes or no based on each wearing specification; If there is a sub-item where the wearing specification is yes and the wearing information is no, it is considered a violation. Based on the location of the object, the nearest risk warning device is matched to output risk warning information.

10. A power construction risk assessment and management system, comprising a management center, monitoring equipment and risk warning equipment connected to the management center, characterized in that: When the system is running, the power construction risk assessment management method as described in any one of claims 1 to 9 is executed.

11. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, the steps of the power construction risk assessment management method as claimed in any one of claims 1 to 9 are implemented.

12. A storage medium, characterized in that: The storage medium stores computer executable instructions, and when the computer executable instructions are loaded and executed by the processor, the steps of the power construction risk assessment management method as described in any one of claims 1 to 9 are implemented.

Images