A method, system, terminal and medium for identifying abnormal behavior of power workers
By segmenting and extracting features from power operation images, marking static and dynamic equipment areas, and combining human feature correction coefficients, the applicability and timeliness issues of abnormal power operation behavior identification are solved, enabling accurate identification of various abnormal situations and reducing misjudgments.
Patent Information
- Application Number
- CN202410977700.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-07-22
AI Technical Summary
Existing technologies are insufficient to effectively identify abnormal behavior of power workers, especially in situations where there is a lack of equipment, multiple devices, or the wrong equipment is being carried, and the applicability and timeliness of the identification models are also inadequate.
By segmenting real-time acquired images, extracting static and dynamic equipment features, marking the work background and operation area, determining behavior recognition values based on coverage overlap, and combining human features and spatial distance correction coefficients for anomaly identification.
It enables early identification of abnormal behavior by power workers, reduces the difficulty of identification, and maintains high efficiency and accuracy in different business operations, reducing misjudgments.
Smart Images

Figure CN118522076B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of electric power safety technology, and more specifically, to a method, system, terminal and medium for identifying abnormal behavior of electric power operators. Background Art
[0002] Power operations generally refer to various work activities related to the power system, including but not limited to the construction and maintenance of power generation, transmission, transformation, distribution and consumption. These operations often involve high-risk work such as aerial work and high-voltage electricity operation, so the safety requirements are extremely high.
[0003] Power operation sites need to be supervised by dedicated personnel to ensure that all operations comply with safety regulations and that violations are discovered and corrected in a timely manner. With the development of technology, more and more high-tech means are being applied to power operations, such as using video surveillance to monitor power operation sites in real time, and combining artificial intelligence technology for behavior recognition and risk warning. The abnormal behavior recognition of power operations in the prior art is mainly based on the establishment of an abnormal behavior recognition model based on machine learning algorithms. However, there are many types of abnormal behaviors in power operations, such as lack of safety equipment, wrong operating equipment, too many or too few operating equipment, wrong operating position, etc., and the business operations of power operations involve many equipment objects, not only static equipment in the power system, such as primary equipment and secondary equipment, but also dynamic equipment required for business operations, such as safety ropes, insulating shoes, climbing equipment, maintenance tools, etc. Therefore, the amount of sample data required to establish the abnormal behavior recognition model is large, and different abnormal behavior recognition models need to be established for different business operations, which makes it difficult to identify abnormal behaviors in power operations. In addition, since the sample image when establishing the abnormal behavior recognition model is an image of the collected working area, the abnormal behavior recognition model can only be effectively identified when the power operator is in the working area when the abnormal behavior recognition model is applied, which leads to poor timeliness of abnormal behavior recognition and warning.
[0004] Therefore, how to research and design a method, system, terminal and medium for identifying abnormal behavior of power workers that can overcome the above-mentioned defects is a problem that we urgently need to solve. Summary of the invention
[0005] In order to address the deficiencies in the prior art, the purpose of the present invention is to provide a method, system, terminal and medium for identifying abnormal behavior of power operators, which can perform early identification of various abnormal situations such as missing equipment, multiple equipment and carrying wrong equipment, and can be applicable to different business operations, reducing the difficulty of identifying abnormal behavior of power operators.
[0006] The above technical objectives of the present invention are achieved through the following technical solutions:
[0007] In a first aspect, a method for identifying abnormal behavior of power workers is provided, comprising the following steps:
[0008] After performing image segmentation on the real-time collected image, the background scene image and the working scene image are extracted;
[0009] Extracting static equipment feature sets from business operation information of power operations;
[0010] Mark the working background area on the background field map according to the static equipment feature set;
[0011] Extract the dynamic equipment feature set of the actual operation process from the workplace diagram;
[0012] Mark the operation area in the background scene according to the dynamic equipment feature set;
[0013] Determine the behavior recognition value of the power operation according to the coverage overlap between the operation area and the operation background area;
[0014] When the behavior recognition value is less than the set threshold, a behavior abnormality signal is output.
[0015] Furthermore, the background field map is composed of static equipment with fixed properties in the power crop environment, including primary equipment, secondary equipment and infrastructure;
[0016] The work site diagram consists of dynamic equipment with mobile properties in the power crop environment, including maintenance instruments, safety facilities and auxiliary equipment.
[0017] Furthermore, the process of marking the operating background area in the background scene map according to the static device feature set is specifically as follows:
[0018] Mark the operable areas for performing business operations on single static equipment features in the background scene map;
[0019] The working background area is obtained by taking the union of all the working areas.
[0020] Furthermore, the process of marking the operation area in the background scene map according to the dynamic device feature set is specifically as follows:
[0021] According to the correlation between the static devices and the characteristics of a single dynamic device in the background field map, the static devices are divided into associated devices, irrelevant devices and excluded devices;
[0022] Filter out static devices that are simultaneously considered as associated devices of all dynamic device features from the background field map, and calculate the union of operable areas of all filtered static devices to obtain an operation area;
[0023] Wherein, if there is a business association between the static device and the dynamic device feature in the background scene map, the corresponding static device is regarded as an associated device of the corresponding dynamic device feature;
[0024] If there is no business association between the static device and the dynamic device features in the background scene map, the corresponding static device is regarded as an unrelated device of the corresponding dynamic device features;
[0025] If there is an exclusion relationship between the static device and the dynamic device features in the background scene, the corresponding static device is regarded as the exclusion device of the corresponding dynamic device feature.
[0026] Furthermore, the process of determining the behavior identification value is specifically as follows:
[0027] Calculate the intersection and union surfaces between the operation area and the background area;
[0028] The ratio between the intersection surface and the union surface is used as the behavior identification value of the power operation.
[0029] Furthermore, the method further comprises:
[0030] Extracting human features from real-time collected images, the human features represent power workers;
[0031] Determine the spatial distance between the human features and the center of the work background area;
[0032] The correction coefficient is determined according to the spatial distance. The larger the spatial distance, the smaller the correction coefficient.
[0033] The dynamic threshold is calculated by the product of the correction coefficient and the set threshold;
[0034] The behavior recognition value is compared with the dynamic threshold to identify abnormal behavior of power workers.
[0035] Furthermore, the calculation formula of the correction coefficient is specifically:
[0036]
[0037] Where D is the correction factor; H0 is the height between the center of the work background area and the horizontal ground; L s Indicates the spatial distance between the human feature and the center of the work background area; L0 indicates the set distance threshold.
[0038] In a second aspect, a system for identifying abnormal behavior of electric power workers is provided, the system being used to implement a method for identifying abnormal behavior of electric power workers as described in any one of the first aspects, comprising:
[0039] An image segmentation module is used to extract a background scene image and a working scene image after performing image segmentation on the real-time collected image;
[0040] A static feature module is used to extract a static device feature set from the business operation information of the power operation;
[0041] A background marking module is used to mark the operating background area in the background field map according to the static equipment feature set;
[0042] Dynamic feature module, used to extract dynamic equipment feature sets of actual operation process from the workplace diagram;
[0043] An operation marking module is used to mark the operation area in the background scene according to the dynamic equipment feature set;
[0044] A coverage analysis module is used to determine the behavior recognition value of the power operation according to the coverage overlap between the operation area and the operation background area;
[0045] The abnormality recognition module is used to output a behavior abnormality signal when the behavior recognition value is less than a set threshold.
[0046] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for identifying abnormal behavior of electric power workers as described in any one of the first aspects is implemented.
[0047] In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement a method for identifying abnormal behavior of power workers as described in any one of the first aspects.
[0048] Compared with the prior art, the present invention has the following beneficial effects:
[0049] 1. A method for identifying abnormal behavior of power workers provided by the present invention marks the operation background area in the background field map according to the static equipment features in the business operation information of the power operation, and marks the operation operation area in the background field map according to the dynamic equipment features in the work field map, and realizes the abnormal behavior identification of power workers according to the overlap between the operation operation area and the operation background area. It can identify various abnormal situations such as missing equipment, multiple equipment and carrying wrong equipment in advance, and can be applied to different business operations, reducing the difficulty of identifying abnormal behavior of power workers;
[0050] 2. The present invention also determines a correction coefficient based on the spatial distance between human features and the center of the work background area, and corrects the set threshold through the correction coefficient, which can reduce the occurrence of misjudgment of abnormal behavior in the preparation stage of power operations, and at the same time, can still effectively identify prominent abnormal behaviors when power operators approach the work background area. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:
[0052] Figure 1 is a flow chart of Embodiment 1 of the present invention;
[0053] Figure 2 It is a system block diagram in Example 2 of the present invention. DETAILED DESCRIPTION
[0054] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.
[0055] Embodiment 1: A method for identifying abnormal behavior of power workers, such as Figure 1 As shown, the following steps are included:
[0056] S1: extracting the background scene image and the working scene image after performing image segmentation on the real-time collected image;
[0057] S2: Extract static equipment feature set from the business operation information of power operation;
[0058] S3: Marking the operating background area in the background field map according to the static equipment feature set;
[0059] S4: Extract the dynamic equipment feature set of the actual operation process from the workplace diagram;
[0060] S5: Marking the operation area in the background scene according to the dynamic equipment feature set;
[0061] S6: Determine the behavior recognition value of the power operation according to the overlap between the operation area and the operation background area;
[0062] S7: Outputting a behavior abnormality signal when the behavior recognition value is less than a set threshold.
[0063] In step S1, the background field map consists of static equipment with fixed attributes in the power crop environment, including primary equipment, secondary equipment and infrastructure. Taking the business operation on the transmission tower as an example, the static equipment includes but is not limited to poles, insulators, hardware, lightning rods and disconnectors.
[0064] The work site map consists of dynamic equipment with mobile properties in the power crop environment, including maintenance instruments, safety facilities and auxiliary equipment. Taking the business operation on the transmission tower as an example, the dynamic equipment includes but is not limited to insulating shoes, safety gloves, safety ropes, maintenance tools and other equipment.
[0065] In step S2, static device features may be extracted from business operation information in the form of text or voice recordings using keyword extraction technology, or may be extracted from videos or images using image processing technology, without limitation.
[0066] In step S3, the process of marking the operating background area in the background scene map according to the static device feature set is specifically as follows: marking the operable areas for performing business operations on a single static device feature in the background scene map respectively; and obtaining the operating background area by taking the union of all operable areas.
[0067] Taking the maintenance wrench as an example, the maintenance wrench can be used to load and unload equipment such as hardware, insulators and lightning rods on transmission towers, but it cannot be used to operate transmission lines. Therefore, the working areas corresponding to the hardware, insulators and lightning rods are all regarded as the working areas of the maintenance wrench.
[0068] In step S4, when extracting the dynamic device feature set of the actual operation process from the workplace image, an image without business operation can be collected in advance as a reference image, and then the devices in the real-time collected image that are more than the reference image are used as dynamic device features.
[0069] In step S5, the process of marking the working operation area in the background field map according to the dynamic device feature set is specifically as follows: according to the association relationship between the static device and the single dynamic device feature in the background field map, the static devices are divided into associated devices, unrelated devices and excluded devices; static devices that are simultaneously regarded as associated devices of all dynamic device features are screened out from the background field map, and the union of the operable areas of all the screened static devices is calculated to obtain the working operation area.
[0070] Among them, if there is a business association between the static device in the background scene diagram and the dynamic device characteristics, the corresponding static device will be regarded as an associated device of the corresponding dynamic device characteristics, and the business association means that the dynamic device can be used to perform business operations on the static device; if there is no business association between the static device in the background scene diagram and the dynamic device characteristics, the corresponding static device will be regarded as an unrelated device of the corresponding dynamic device characteristics, and the absence of business association means that there is no business operation between the dynamic device and the static device; if there is an exclusion relationship between the static device in the background scene diagram and the dynamic device characteristics, the corresponding static device will be regarded as an exclusion device of the corresponding dynamic device characteristics, and the exclusion relationship means that the dynamic device cannot be used to perform business operations on the static device.
[0071] In step S6, the behavior recognition value is determined by calculating the intersection and union surfaces between the operation area and the background area; and taking the ratio between the intersection and union surfaces as the behavior recognition value of the power operation.
[0072] If the intersection surface is the work operation area, it means that there may be a situation where the equipment is not carried enough; if the intersection surface completely includes the work background area, it means that there may be a situation where too much equipment is carried; if the intersection surface is only a part of the work operation area or the work background area, it means that there may be a situation where the equipment is carried incorrectly.
[0073] In step S7, the threshold value may be adjusted according to the sensitivity of the device with abnormal behavior, and the threshold value may be obtained based on historical data statistics or may be designed based on empirical values, which is not limited here.
[0074] In addition, in order to reduce the occurrence of misjudgment of abnormal behavior in the preparation stage of power operations, the present invention can also effectively identify prominent abnormal behaviors when power operators approach the operating background area.
[0075] The present invention also extracts human features from real-time collected images, the human features characterizing the power workers; determines the spatial distance between the human features and the center of the working background area; determines a correction coefficient based on the spatial distance, the larger the spatial distance, the smaller the correction coefficient; calculates a dynamic threshold by the product of the correction coefficient and a set threshold; compares the behavior recognition value with the dynamic threshold to realize the recognition of abnormal behavior of the power workers.
[0076] As an optional implementation, the calculation formula of the correction coefficient is specifically:
[0077]
[0078] Where D is the correction factor; H0 is the height between the center of the work background area and the horizontal ground; L sIndicates the spatial distance between the human feature and the center of the work background area; L0 indicates the set distance threshold.
[0079] Embodiment 2: A system for identifying abnormal behavior of electric power workers, the system is used to implement a method for identifying abnormal behavior of electric power workers as described in Embodiment 1, such as Figure 2 As shown, it includes an image segmentation module, a static feature module, a background marking module, a dynamic feature module, an operation marking module, a coverage analysis module and an anomaly recognition module.
[0080] Among them, the image segmentation module is used to extract the background scene map and the working scene map after performing image segmentation on the real-time collected image; the static feature module is used to extract the static equipment feature set from the business operation information of the power operation; the background marking module is used to mark the working background area in the background scene map according to the static equipment feature set; the dynamic feature module is used to extract the dynamic equipment feature set of the actual operation process from the working scene map; the operation marking module is used to mark the working operation area in the background scene map according to the dynamic equipment feature set; the coverage analysis module is used to determine the behavior recognition value of the power operation according to the coverage overlap between the working operation area and the working background area; the abnormal recognition module is used to output a behavior abnormality signal when the behavior recognition value is less than the set threshold.
[0081] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a method for identifying abnormal behavior of electric power workers as described in Example 1 is implemented.
[0082] The present invention also records a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement a method for identifying abnormal behavior of power workers as described in Example 1.
[0083] Working principle: The present invention marks the operation background area in the background scene map according to the static equipment characteristics in the business operation information of the power operation, and marks the operation area in the background scene map according to the dynamic equipment characteristics in the work scene map, and realizes the abnormal behavior identification of power operation personnel according to the overlap between the operation area and the operation background area. It can carry out early identification of various abnormal situations such as missing equipment, multiple equipment and carrying wrong equipment, and can be applicable to different business operations, reducing the difficulty of identifying abnormal behavior of power operation personnel.
[0084] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0085] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0088] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for identifying abnormal behavior of power workers, characterized in that: The following steps are involved: After performing image segmentation on the real-time collected image, the background scene image and the working scene image are extracted; Extracting static equipment feature sets from business operation information of power operations; Mark the working background area on the background field map according to the static equipment feature set; Extract the dynamic equipment feature set of the actual operation process from the workplace diagram; Mark the operation area in the background scene according to the dynamic equipment feature set; Determine the behavior recognition value of the power operation according to the coverage overlap between the operation area and the operation background area; Outputting a behavior abnormality signal when the behavior recognition value is less than a set threshold; The background field map is composed of static equipment with fixed attributes in the power crop environment, including primary equipment, secondary equipment and infrastructure; The work site diagram is composed of dynamic equipment with mobile properties in the power crop environment, including maintenance instruments, safety facilities and auxiliary equipment; The process of marking the operation area in the background scene map according to the dynamic device feature set is specifically as follows: According to the correlation between the static devices and the characteristics of a single dynamic device in the background field map, the static devices are divided into associated devices, irrelevant devices and excluded devices; Filter out static devices that are simultaneously considered as associated devices of all dynamic device features from the background field map, and calculate the union of operable areas of all filtered static devices to obtain an operation area; If there is a business association between the static device and the dynamic device features in the background scene, the corresponding static device is regarded as an associated device of the corresponding dynamic device features; the business association means that the dynamic device can be used to perform business operations on the static device; If there is no business association between the static device and the dynamic device features in the background scene, the corresponding static device is regarded as an unrelated device of the corresponding dynamic device features; no business association means that there is no business operation between the dynamic device and the static device; If there is an exclusion relationship between the static device and the dynamic device features in the background scene, the corresponding static device is regarded as an exclusion device of the corresponding dynamic device features; the exclusion relationship means that the dynamic device cannot be used to perform business operations on the static device; The specific process of determining the behavior identification value is as follows: Calculate the intersection and union surfaces between the operation area and the background area; The ratio between the intersection surface and the union surface is used as the behavior identification value of the power operation.
2. A method for identifying abnormal behavior of electric power workers according to claim 1, characterized in that: The process of marking the operating background area in the background field map according to the static device feature set is specifically as follows: Mark the operable areas for performing business operations on single static equipment features in the background scene map; The working background area is obtained by taking the union of all the working areas.
3. A method for identifying abnormal behavior of electric power workers according to claim 1, characterized in that: The method further includes: Extracting human features from real-time collected images, the human features represent power workers; Determine the spatial distance between the human features and the center of the work background area; The correction coefficient is determined according to the spatial distance. The larger the spatial distance, the smaller the correction coefficient. The dynamic threshold is calculated by the product of the correction coefficient and the set threshold; The behavior recognition value is compared with the dynamic threshold to identify abnormal behavior of power workers.
4. A method for identifying abnormal behavior of electric power workers according to claim 3, characterized in that: The calculation formula of the correction coefficient is specifically: Where D is the correction factor; H0 is the height between the center of the work background area and the horizontal ground; L s Indicates the spatial distance between the human feature and the center of the work background area; L0 indicates the set distance threshold.
5. A system for identifying abnormal behavior of power workers, characterized in that: The system is used to implement a method for identifying abnormal behavior of electric power workers as described in any one of claims 1 to 4, comprising: An image segmentation module is used to extract a background scene image and a working scene image after performing image segmentation on the real-time collected image; A static feature module is used to extract a static device feature set from the business operation information of the power operation; A background marking module is used to mark the operating background area in the background field map according to the static equipment feature set; Dynamic feature module, used to extract dynamic equipment feature sets of actual operation process from the workplace diagram; An operation marking module is used to mark the operation area in the background scene according to the dynamic equipment feature set; A coverage analysis module is used to determine the behavior recognition value of the power operation according to the coverage overlap between the operation area and the operation background area; The abnormality recognition module is used to output a behavior abnormality signal when the behavior recognition value is less than a set threshold.
6. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for identifying abnormal behavior of power workers as described in any one of claims 1 to 4 is implemented.
7. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement a method for identifying abnormal behavior of power workers as described in any one of claims 1 to 4.
