CN115880722A

CN115880722A - Intelligent identification method, system and medium worn by power distribution operating personnel

Info

Publication number: CN115880722A
Application number: CN202211531658.6A
Authority: CN
Inventors: 杨鑫; 邱明明; 胡聪; 吴慧峰; 管子然; 唐建辉; 胡正庭; 侯年冠; 张宇宣; 谭国栋; 石俏; 刘超; 韩广超; 庄巨周; 李�浩; 何文峰
Original assignee: Guangdong Power Grid Co Ltd; Foshan Power Supply Bureau of Guangdong Power Grid Corp
Current assignee: Guangdong Power Grid Co Ltd; Foshan Power Supply Bureau of Guangdong Power Grid Corp
Priority date: 2022-12-01
Filing date: 2022-12-01
Publication date: 2023-03-31

Abstract

The invention discloses an intelligent identification method, system and medium worn by power distribution operating personnel. The method belongs to the technical field of big data and power distribution operation, and comprises the following steps: performing image identification on an operator and wearing equipment in a monitoring video, performing position detection on image information of the operator, performing matching association on safety element information and the operator according to the position information, performing personnel attribute identification according to a plurality of detection results to obtain position area information and personnel attribute information, extracting standard wearing requirement data of the operator to judge the wearing condition of a track point, and performing threshold judgment according to the full-track wearing condition; thereby discerning distribution operation personnel's wearing based on big data and image identification analysis technique to dress according to the standard that obtains and discern the aassessment to the wearing condition of personnel's orbit, realize the discernment detection of wearing to operation personnel, improve the effective discernment control of wearing to operation personnel, in order to ensure personnel's safety.

Description

Intelligent identification method, system and medium worn by power distribution operating personnel

Technical Field

The invention relates to the technical field of big data and power distribution operation, in particular to an intelligent identification method, system and medium worn by power distribution operation personnel.

Background

At present, the protection and safety monitoring method for power distribution operating personnel generally adopts manual monitoring, protects people through common equipment and wearing, lacks of tracking identification technology of wearing standards for personnel, cannot effectively identify and supervise the wearing protection of the power distribution operating personnel of different work types aiming at power distribution operating environment and positions, and cannot realize intelligent technology for identifying, alarming and supervising incorrectly worn power distribution operating personnel.

According to the video monitoring means and the image recognition technology, the intelligent power distribution operator wearing recognition technology for carrying out image recognition on the power distribution operation environment, position and worker work type attributes, recognizing standard wearing requirements and carrying out wearing judgment and recognition on the whole construction process is established, is a scene technical means which is not available at present and is a technical vacancy in the technical field of power distribution service.

In view of the above problems, an effective technical solution is urgently needed.

Disclosure of Invention

An object of the embodiment of the application is to provide an intelligent identification method, system and medium that distribution operation personnel dressed, can discern distribution operation personnel's dressing according to big data and image identification analysis technique to dress according to the standard that obtains and discern the aassessment to the dressing condition of personnel's orbit, realize the discernment detection to operation personnel dress, improve the effective discernment control of dressing operation personnel, with the security of guarantee personnel.

The embodiment of the application also provides an intelligent identification method worn by power distribution workers, which comprises the following steps:

acquiring a real-time monitoring video of an operator without power failure in a distribution network, and carrying out image identification on the operator and wearing equipment in the monitoring video to obtain image information, wearing information and safety element information of the operator in an operation environment;

performing position detection on the image information of the operator through the established multi-scale human body detection model, supplementing the safety element information according to the detected position information, matching with the operator, and performing mapping association identification on the operator, the position and the safety element information;

integrating information according to a plurality of detection results obtained by matching and associating the identifiers for a plurality of times, and identifying personnel attributes to obtain the information of the position area to be tracked and the information of the personnel attributes;

extracting standard wearing requirement data of the operating personnel through a distribution network operation wearing database according to the to-be-tracked position area information and the personnel attribute information;

judging the track information of the target operator according to the intersection ratio of the target operator tracking frames of each track point, if the intersection ratio of the track points is smaller than a preset threshold value, judging that the target operator monitored in the track points does not exist, and removing the track points;

recording effective track points in the track information of the target operating personnel and the corresponding wearing information, and judging the wearing condition of the target operating personnel of each effective track point according to the standard wearing requirement data;

and judging a threshold value according to the full-orbit wearing condition of each operator in a preset monitoring time period, and warning and recording the operators exceeding the wearing warning threshold value.

Optionally, in the intelligent identification method for power distribution operators to wear according to the embodiment of the present application, the acquiring a real-time monitoring video of distribution network operators without power outage, performing image identification on the operators and the wearing equipment in the monitoring video, and obtaining image information, wearing information of the operators and safety element information of an operation environment includes:

collecting a real-time monitoring video of a distribution network uninterrupted operation area in a preset region;

acquiring images with operators in a real-time monitoring video, and performing image recognition and image information extraction on the operators and wearable equipment to obtain image information and wearable information of the operators;

and identifying and extracting safety element information of the power distribution operation environment according to the image, wherein the safety element information comprises electric shock protection information, high altitude protection information, environment control illumination information and wind and rain prevention information.

Optionally, in the intelligent identification method worn by a power distribution operator according to the embodiment of the present application, the performing position detection on the image information of the operator through the established multi-scale human body detection model, supplementing the safety element information according to the detected position information, matching the safety element information with the operator, and mapping the operator, the position, and the safety element information to associate an identifier includes:

processing according to the personnel power distribution operation images in the sample library and establishing a multi-scale human body detection model;

carrying out position detection on the image information of the operator according to the multi-scale human body detection model to obtain position information of the operator, wherein the position information comprises operation position information and position positioning information;

performing information supplement on the electric shock protection information and the high-altitude protection information according to the operation position information;

performing information supplement on the environment-controlled lighting information and the wind and rain prevention information according to the position positioning information;

matching with the operator according to the supplemented safety factor information;

and combining the supplemented safety element information with the position information to carry out mapping association on the operator, and synthesizing the association identifier of the operator, the position and the safety element.

Optionally, in the intelligent identification method for power distribution operators to wear according to the embodiment of the present application, the performing information integration according to a plurality of detection results obtained by matching and associating identifiers for a plurality of times, performing personnel attribute identification, obtaining location area information to be tracked and personnel attribute information, and extracting standard wear requirement data of the operators through a distribution network operation wear database according to the location area information to be tracked and the personnel attribute information includes:

integrating a plurality of safety element information obtained by a plurality of matching and associated identifiers with the position information of corresponding operators to obtain the safety element information of the positions of the operators;

carrying out personnel attribute identification on the operators in the operator position safety element information according to the position information of the set and the safety element information to obtain personnel attribute information;

synthesizing a plurality of position information of the target operating personnel corresponding to the personnel attribute information to obtain the position area information to be tracked;

and inputting the personnel attribute information of the target operating personnel and the information of the position area to be tracked into a preset distribution network operation wearing database, and extracting the standard wearing requirement data of the target operating personnel.

Optionally, in the intelligent recognition method that distribution operation personnel dressed in this application embodiment, the intersection ratio of the target operation personnel tracking frame according to each track point judges target operation personnel track information, if the intersection ratio of track points is less than the preset threshold value, then judges monitoring in the track point the target operation personnel do not exist, get rid of the track point, include:

extracting all track points of the target operator according to the information of the position area to be tracked;

processing the image according to each track point to obtain the intersection ratio of the tracking frames of the target operator;

comparing a threshold value according to the intersection ratio of the track points and a preset threshold value;

if the intersection ratio of the track points is smaller than a preset threshold value, judging that the target operator does not exist in the track points, and removing the track points;

if the intersection ratio of the track points is larger than a preset threshold value, the target operator exists in the track points, the track points are effective, and effective track points are synthesized into track information of the target operator.

Optionally, in the intelligent recognition method that distribution operation personnel dressed in this application embodiment, right effective track point and correspondence in the target operation personnel orbit information dress information and record, according to the target operation personnel's of each effective track point wearing condition is judged to standard dress requirement data, include:

acquiring wearing information corresponding to the effective track point in the track information of the target operator, and recording the wearing information by combining the corresponding track point;

judging the wearing condition of the wearing information of the track points according to standard wearing requirement data corresponding to the target operating personnel;

and if the wearing information meets the standard wearing requirement data, the wearing condition of the track points is qualified.

Optionally, in the intelligent identification method worn by power distribution workers according to the embodiment of the present application, the threshold determination is performed according to the full-orbit wearing condition of each worker in a preset monitoring time period, and warning and recording are performed on workers exceeding a wearing warning threshold, including:

acquiring the wearing conditions of all the working personnel corresponding to all the effective track points in a preset monitoring time period, and acquiring full-track wearing unqualified data;

comparing a threshold value according to the full-trajectory wearing failure data and a preset wearing warning threshold value;

and if the full-track wearing unqualified data of the operating personnel is larger than the wearing warning threshold, warning and recording the operating personnel.

In a second aspect, an embodiment of the present application provides an intelligent identification system worn by a power distribution operator, where the system includes: the intelligent identification method comprises a memory and a processor, wherein the memory comprises a program of the intelligent identification method worn by the power distribution operator, and the program of the intelligent identification method worn by the power distribution operator realizes the following steps when being executed by the processor:

acquiring a real-time monitoring video of an operator without power failure of the distribution network, and performing image identification on the operator and wearing equipment in the monitoring video to obtain image information, wearing information and safety factor information of the operator and an operation environment;

integrating information according to a plurality of detection results obtained by matching and associating the identifiers for a plurality of times, and identifying personnel attributes to obtain the information of the position area to be tracked and the personnel attribute information;

extracting standard wearing requirement data of the operating personnel through a distribution network operation wearing database according to the position area information to be tracked and the personnel attribute information;

Optionally, in the intelligent recognition system that distribution operation personnel dressed in this application embodiment, gather and join in marriage the real-time monitoring video of joining in marriage the uninterrupted power supply operation personnel, carry out image recognition to operation personnel and the wearing equipment in the monitoring video, obtain operation personnel image information, dress information and operation environment's safe key element information, include:

In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium includes a program of an intelligent identification method worn by a power distribution worker, and when the program of the intelligent identification method worn by the power distribution worker is executed by a processor, the steps of the method of the intelligent identification method worn by the power distribution worker are implemented.

From the above, according to the intelligent identification method, system and medium worn by the power distribution operator provided by the embodiment of the application, image identification is performed on the operator and the wearing equipment in the monitoring video, the position of the image information of the operator is detected, the safety element information is supplemented according to the position information and is matched and mapped with the operator to be associated with identification, information integration is performed according to a plurality of detection results, personnel attribute identification is performed to obtain the area information of the position to be tracked and the personnel attribute information, the standard wearing requirement data of the operator is extracted through the distribution network operation wearing database, the track information is judged according to the intersection and comparison of each track point, the wearing condition of each track point is judged according to the standard wearing requirement data, and threshold judgment, warning and recording are performed according to the full-track wearing condition; thereby based on big data and distribution operation image identification analysis technique discernment and position relevance to distribution operation personnel's wearing to dress according to the standard that obtains discerns the aassessment to the wearing condition of personnel's orbit, realize the discernment detection to operation personnel dress, improve the effective discernment control to operation personnel dress, with guarantee personnel's safety.

Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.

Fig. 1 is a flowchart of an intelligent identification method worn by a power distribution worker according to an embodiment of the present disclosure;

fig. 2 is a flowchart of acquiring image information, wearing information, and safety factor information of a work environment of a power distribution worker wearing intelligent identification method according to an embodiment of the present application;

fig. 3 is a flowchart of supplementing and matching safety factor information and mapping associated identifiers according to the intelligent identification method worn by power distribution workers provided in the embodiment of the present application;

fig. 4 is a schematic structural diagram of an intelligent identification system worn by a power distribution worker according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that like reference numerals and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

Referring to fig. 1, fig. 1 is a flowchart of an intelligent identification method worn by a power distribution operator according to some embodiments of the present disclosure. The intelligent identification method worn by the power distribution operator is used in terminal equipment, such as a computer, a mobile phone terminal and the like. The intelligent identification method worn by the power distribution operator comprises the following steps:

s101, collecting a real-time monitoring video of an operator without power failure in a distribution network, carrying out image recognition on the operator and wearing equipment in the monitoring video, and obtaining image information, wearing information and safety element information of the operator in an operation environment;

s102, carrying out position detection on image information of the operator through the established multi-scale human body detection model, supplementing safety element information according to the detected position information, matching with the operator, and carrying out mapping association identification on the operator, the position and the safety element information;

s103, integrating information according to a plurality of detection results obtained by multiple matching and associated identification, and identifying personnel attributes to obtain the information of the position area to be tracked and the personnel attribute information;

s104, extracting standard wearing requirement data of the operating personnel through a distribution network operation wearing database according to the to-be-tracked position area information and the personnel attribute information;

s105, judging track information of the target operator according to the intersection ratio of the target operator tracking frames of each track point, if the intersection ratio of the track points is smaller than a preset threshold value, judging that the target operator monitored in the track points does not exist, and removing the track points;

s106, recording effective track points in the track information of the target operating personnel and the corresponding wearing information, and judging the wearing condition of the target operating personnel of each effective track point according to the standard wearing requirement data;

and S107, performing threshold judgment according to the full-orbit wearing condition of each operator in a preset monitoring time period, and warning and recording the operators exceeding the wearing warning threshold.

It should be noted that, for realizing passing through video monitoring and image recognition, to distribution operation environment, position and operation personnel carry out image recognition, in order to differentiate operational environment and position and correspond personnel's working property, obtain the wearing standard that accords with distribution personnel's work and environment, rethread wearing standard carries out whole journey tracking discernment to operation personnel, judge the overall process wearing condition by monitoring operation personnel, warn to the operation personnel that are not conform to and dress the restriction requirement, in order to realize according to image recognition and big data processing technique to the safety supervision technique of distribution operation personnel's wearing condition, reach the safety control means of intelligent guarantee distribution construction, concrete process is: the method comprises the steps of collecting a real-time monitoring video of an operator without power failure in a distribution network, carrying out image recognition on the operator and wearing equipment in the monitoring video, obtaining image information, wearing information and safety element information of an operation environment of the operator, carrying out position detection on the image information of the operator through a multi-scale human body detection model, supplementing the safety element information according to the detected position information, matching with the operator, carrying out mapping association on the operator, the position and the safety element information, carrying out information integration according to a plurality of obtained detection results to carry out personnel attribute recognition on the operator, obtaining position area information to be tracked and personnel attribute information, extracting standard wearing requirement data of the operator through a distribution network operation wearing database, judging target operator track information according to the intersection ratio of a target operator tracking frame of each track point, recording track points in the target operator track information and corresponding wearing information, judging the wearing conditions of the target operator of each effective track point according to the standard wearing requirement data, carrying out whole track wearing conditions according to the operators, and judging the warning and recording the wearing conditions of the operators exceeding the wearing threshold value.

Referring to fig. 2, fig. 2 is a flowchart of obtaining image information, wearing information, and safety factor information of a work environment of a power distribution worker wearing the power distribution worker according to some embodiments of the present disclosure. According to the embodiment of the invention, the acquisition of the real-time monitoring video of the distribution network uninterrupted operating personnel, the image recognition of the operating personnel and the wearing equipment in the monitoring video, and the acquisition of the image information, the wearing information and the safety factor information of the operating personnel and the operating environment are specifically as follows:

s201, collecting a real-time monitoring video of a distribution network uninterrupted operation area in a preset region;

s202, obtaining images with operators in the real-time monitoring video, and carrying out image recognition and image information extraction on the operators and the wearable equipment to obtain image information and wearable information of the operators;

and S203, identifying and extracting safety element information of the power distribution working environment according to the image, wherein the safety element information comprises electric shock protection information, high altitude protection information, environment control illumination information and wind and rain prevention information.

The method includes the steps that in order to obtain wearing conditions of personnel in a non-power-outage operation area in a monitored area and further judge according to personnel type attributes and working environments in combination with wearing requirements, firstly, video images of the operation area need to be obtained, the images are identified to obtain information of personnel, wearing and environment safety elements, namely, real-time monitoring videos in a target area of distribution network non-power-outage operation in a preset area are collected, images with the personnel in the videos are identified, image information and wearing information of the personnel are extracted through the images, image information with the personnel is obtained by identifying the images, meanwhile, wearing information of the personnel is identified, wearing equipment such as wearing safety helmets, protective clothing, insulating gloves and protective boots and the like and wearing equipment are identified, safety element information of the power distribution operation environment where the personnel are located is extracted through image identification, the safety element information is safety element information of power distribution work which is identified and judged according to the information of the personnel in the images and the working environment, and comprises protection information, high-altitude protection information, environment-control illumination information and rain-protection information, and electric shock-protection information which reflect rain-protection elements and electric shock-protection information which are needed by the personnel in the power distribution environment.

Referring to fig. 3, fig. 3 is a flowchart of a method for intelligent identification worn by a power distribution operator to supplement and match security element information and map associated identifiers according to some embodiments of the present application. According to the embodiment of the invention, the position detection is performed on the image information of the operator through the established multi-scale human body detection model, the safety element information is supplemented according to the detected position information, the safety element information is matched with the operator, and mapping association identification is performed on the operator, the position and the safety element information, specifically:

s301, processing according to the personnel power distribution operation images in the sample library and establishing a multi-scale human body detection model;

s302, carrying out position detection on the image information of the operator according to the multi-scale human body detection model to obtain position information of the operator, wherein the position information comprises operation position information and position positioning information;

s303, supplementing the electric shock protection information and the high-altitude protection information according to the operation position information;

s304, performing information supplement on the environment-control illumination information and the wind and rain prevention information according to the position positioning information;

s305, matching with the operator according to the supplemented safety factor information;

and S306, mapping and associating the supplemented safety element information with the position information, and synthesizing the association identification of the operator, the position and the safety element.

The method comprises the steps of acquiring safety element information required by power distribution construction of workers, identifying the construction position of the workers, constructing a multi-scale human body detection model, processing and establishing the multi-scale human body detection model according to personnel power distribution operation images in a sample library, performing identification training through a large number of image samples to establish the multi-scale human body detection model, detecting information of the construction position of the workers, acquiring operation position information and position positioning information, respectively supplementing the safety element information, matching the supplemented safety element information with the workers according to the supplemented safety element information, accurately and effectively associating the construction safety element with the workers, determining safety element information of the workers by the workers in the certain images, mapping the safety element information with the position information of the workers, acquiring the position information of the workers, associating the safety element information with the worker information of the workers, combining the safety element information with the workers, monitoring and monitoring of the workers, and further realizing the further association of the construction safety element information and the protection condition of the workers.

According to the embodiment of the invention, information integration is carried out according to a plurality of detection results obtained by matching and associating the identification for a plurality of times, personnel attribute identification is carried out, position area information to be tracked and personnel attribute information are obtained, and standard wearing requirement data of an operator is extracted through a distribution network operation wearing database according to the position area information to be tracked and the personnel attribute information, and the method specifically comprises the following steps:

integrating a plurality of safety element information obtained by a plurality of matching and associated identifications by combining position information of corresponding operators to obtain position safety element information of the operators;

It should be noted that after identifying any operator, construction location and safety element, when inspecting and judging the wearing condition of an operator, it is necessary to first clarify the working property or work type of the operator, and obtain the working area and construction track point of the operator within a preset time, so as to judge whether the operator wears the working area according to the work type requirement of the operator, and to conduct whole area operation wear supervision on the operator, to achieve the design, the construction location and the detection information of the safety element obtained by matching and associating the identification for many times of the operator are integrated, so as to obtain the safety element information set of the operator at a plurality of construction locations, after a certain amount of information is collected, the construction location frequently appearing in the operator and the corresponding safety element information can be identified by the information set, the attribute of the operator can be clarified, the attribute information of the operator can be obtained, if the collected information finds that the operator frequently appears in front of the detection box of the power distribution network, the wearing equipment and tools of the detection personnel can be identified by the information set, if the operator frequently appears in front of the detection box of the line, the detection equipment and tools can obtain the detection information of the working area, the target data of the working area, the working area where the operator is obtained by combining the detection data base, the operator, the working area where the operator is obtained by tracking information of the operator, the data base can be obtained, the data base, the standard wearing requirements of the target operator in the work type, construction position and area are inquired through the database, if a certain line detection operator performs line detection operation on the upper part of a telegraph pole in the field area of northern villages at night in winter, the standard wearing requirements of the target operator comprise equipment, tools and the like which are worn in standards such as cold protection, illumination, warning, positioning, falling prevention, electric shock prevention and the like, and standard wearing requirement data is set according to the standard wearing requirements.

According to the embodiment of the invention, the track information of the target operator is judged according to the intersection ratio of the target operator tracking frames of each track point, if the intersection ratio of the track points is smaller than a preset threshold value, it is judged that the target operator monitored in the track points does not exist, and the track points are removed, specifically:

acquiring the intersection ratio of the tracking frames of the target operators according to the image processing of each track point;

It should be noted that, because the target operator of image recognition has a problem of capturing and recognizing deviation in the path trajectory of the construction area within a preset time period, and thus some area trajectories do not have target operators, in order to accurately grasp the accurate construction trajectory points of the target operator, image processing needs to be performed on each trajectory point, the accuracy of capturing the target operator is judged, a preset threshold value judgment is performed according to frame intersection and comparison obtained by image processing of each trajectory point of the target operator, if the intersection and comparison of a certain trajectory point is smaller than a preset threshold value, it is judged that the target operator of the trajectory point does not exist, the trajectory point is an invalid trajectory point, the trajectory point is removed, otherwise, if the trajectory point is larger than the preset threshold value, the trajectory points judged to be valid are synthesized, trajectory information of the target operator is obtained, the intersection and comparison (IoU) of the target operator tracking frame is a standard for measuring the accuracy of detecting objects/persons, according to the true area marked in the image, the more accurate detection ratio of the target operator is obtained, and the accuracy of the detection area intersection and the measurement ratio is calculated as follows: ioU = intersection of the detection area and the real area/union of the detection area and the real area, in this scheme, whether the detection target operator really exists in the detected area is judged by intersection and comparison of the tracking frames obtained by image processing, so as to improve accuracy of detection of the target operator and screen out invalid track points in track information of the tracking area.

According to the embodiment of the present invention, the effective trace points in the trace information of the target operator and the corresponding wearing information are recorded, and the wearing condition of the target operator at each effective trace point is determined according to the standard wearing requirement data, specifically:

It should be noted that, the wearing information corresponding to the effective track point in the obtained track information of the target operator is compared with the corresponding standard wearing requirement data, the wearing condition of the target operator at the track point is judged, if the wearing information of a certain track point meets the preset comparison requirement of the standard wearing requirement data, the wearing condition of the target operator at the track point is judged to meet the standard wearing requirement data, the wearing condition of the track point is qualified, and the wearing conditions of all the track points of the target operator in the track are sequentially judged.

According to the embodiment of the invention, the threshold value judgment is carried out according to the full-orbit wearing condition of each operator in the preset monitoring time period, and the operator exceeding the wearing warning threshold value is warned and recorded, specifically:

It should be noted that, after the wearing condition of all effective track points of each monitored operator in a preset monitoring time period is identified, an unqualified wearing condition in the full track of each operator can be obtained, that is, unqualified wearing data is worn, threshold comparison is performed on the unqualified wearing data of the full track and a preset wearing warning threshold, if the unqualified wearing data of the full track of the operator is larger than the wearing warning threshold, the operator is warned and recorded, that is, the unqualified wearing data in the full track of a certain operator is compared with the preset wearing threshold, the wearing condition of the full-track operation is judged, if the unqualified wearing data exceeds the preset threshold requirement, the number of times that the operator does not meet the standard in the full-track operation in the time period is indicated to exceed the standard, the operator needs to be warned and recorded, the person wearing condition can be identified through the judgment of the illegal wearing condition of the full track, warning and processing are performed, so as to avoid safety operation accidents caused by the improper wearing of the operator, and the safety supervision and construction management means of the intelligent power distribution management of the power distribution operators according to the image identification and the large data processing technology in the scheme is realized.

As shown in fig. 4, the present invention also discloses an intelligent identification system worn by a power distribution operator, which includes a memory 41 and a processor 42, where the memory includes an intelligent identification method program worn by the power distribution operator, and when the processor executes the sign abnormality correction data, the intelligent identification method program worn by the power distribution operator implements the following steps:

According to the embodiment of the invention, the acquisition of the real-time monitoring video of the distribution network uninterrupted operating personnel, the image recognition of the operating personnel and the wearing equipment in the monitoring video, and the acquisition of the image information, the wearing information and the safety factor information of the operating personnel and the operating environment are specifically as follows:

The method includes the steps of acquiring a video image of a work area, identifying the image to acquire information of personnel, wearing and environment safety elements, namely acquiring a real-time monitoring video in a target area of distribution network uninterrupted power operation in a preset area, identifying the image with the worker in the video, extracting image information and wearing information of the worker through the image, identifying wearing information of the worker, identifying wearing equipment of the worker, such as wearing safety helmets, protective clothing, insulating gloves and protective boots, and wearing equipment, and extracting safety element information of the power distribution work environment where the worker is located through the image identification, wherein the safety element information is safety element information of power distribution work, which is identified and judged according to the information of the worker in the image and the work environment information, and comprises high-altitude protection information, environment-controlled illumination information and windproof information, and electric shock protection information which are required to be applied by the worker in the power distribution environment and is reflected.

According to the embodiment of the invention, the position detection is performed on the image information of the operator through the established multi-scale human body detection model, the safety element information is supplemented according to the detected position information, the safety element information is matched with the operator, and mapping association identification is performed on the operator, the position and the safety element information, specifically:

performing information supplement on the environment-control lighting information and the wind and rain prevention information according to the position positioning information;

It should be noted that, in order to make the identified and obtained safety element information required by the power distribution construction of the worker more accurate, the safety element information needs to be supplemented according to the position information of the power distribution operation, because the power distribution construction environment is often a large scene, the worker is usually located at a certain position of a power distribution unit, a building and a facility, so that scene identification needs to be performed according to the position where the specific worker is located, the safety element information is supplemented according to the construction position information identified by the scene, a multi-scale human body detection model is processed and established according to the personnel power distribution operation images in a sample library, a large number of image samples of the power distribution operation of the worker are contained in the sample library, a multi-scale human body detection model is established through identification training of a large number of image samples, the model can detect the construction position of the worker, obtain operation position information and position positioning information, then supplement the safety element information respectively, match with the worker according to the supplemented safety element information, make the construction safety element and the worker accurately and effectively correlate, a certain unified operation element information in a certain image can be clear, then correlate with the construction position information, and further realize the correlation with the safety element monitoring and the safety element correlation of the construction worker, and the safety element matching judgment of the worker are further combined with the construction worker.

According to the embodiment of the invention, the track information of the target operator is judged according to the intersection ratio of the target operator tracking frames of each track point, if the intersection ratio of the track points is smaller than a preset threshold value, the target operator monitored in the track points is judged to be absent, and the track points are removed, which specifically comprises the following steps:

comparing a threshold value according to the intersection ratio of each track point and a preset threshold value;

It should be noted that, because the target operator of image recognition has a problem of capturing and recognizing deviation in the path trajectory of the construction area within a preset time period, and thus some area trajectories do not have target operators, in order to accurately grasp the accurate construction trajectory points of the target operator, image processing needs to be performed on each trajectory point, the accuracy of capturing the target operator is judged, a preset threshold value judgment is performed according to frame intersection and comparison obtained by image processing of each trajectory point of the target operator, if the intersection and comparison of a certain trajectory point is smaller than a preset threshold value, it is judged that the target operator of the trajectory point does not exist, the trajectory point is an invalid trajectory point, the trajectory point is removed, otherwise, if the trajectory point is larger than the preset threshold value, the trajectory points judged to be valid are synthesized, trajectory information of the target operator is obtained, the intersection and comparison (IoU) of the target operator tracking frame is a standard for measuring the accuracy of detecting objects/persons, according to the true area marked in the image, the more accurate detection ratio of the target operator is obtained, and the accuracy of the detection area intersection and the measurement ratio is calculated as follows: ioU = intersection of the detection area and the real area/union of the detection area and the real area, in the scheme, whether the detection target operator really exists in the detected area is judged through intersection comparison of the tracking frames obtained through image processing, so that the accuracy of detection on the target operator is improved, and invalid track points in track information of the tracking area are screened out.

the wearing condition of the wearing information of the track points is judged according to standard wearing requirement data corresponding to the target operating personnel;

It should be noted that, the wearing information corresponding to the effective track point in the obtained track information of the target operator is compared with the corresponding standard wearing requirement data, the wearing condition of the target operator at the track point is judged, if the wearing information of a certain track point meets the preset comparison requirement of the standard wearing requirement data, the wearing condition of the target operator at the track point is judged to meet the standard wearing requirement data, the wearing condition of the track point is qualified, and the wearing conditions of the target operator at each track point in the track are sequentially judged.

A third aspect of the present invention provides a readable storage medium, which includes a program of an intelligent identification method worn by a power distribution operator, and when the program of the intelligent identification method worn by the power distribution operator is executed by a processor, the steps of the intelligent identification method worn by the power distribution operator as described in any of the above are implemented.

The invention discloses an intelligent identification method, a system and a medium worn by power distribution operators, which are characterized in that image identification is carried out on operators and wearing equipment in a monitoring video, the position of image information of the operators is detected, safety element information is supplemented according to the position information and is matched with and mapped with the operators to be identified, information integration is carried out according to a plurality of detection results, personnel attribute identification is carried out to obtain position area information to be tracked and personnel attribute information, standard wearing requirement data of the operators is extracted through a distribution network operation wearing database, track information is judged according to the intersection and intersection ratio of each track point, the wearing condition of each track point is judged according to the standard wearing requirement data, threshold judgment is carried out according to the full track wearing condition, and warning and recording are carried out; thereby based on big data and distribution operation image identification analysis technique discernment and position relevance to distribution operation personnel's wearing to dress according to the standard that obtains discerns the aassessment to the wearing condition of personnel's orbit, realize the discernment detection to operation personnel dress, improve the effective discernment control to operation personnel dress, with guarantee personnel's safety.

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

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Alternatively, the integrated unit of the present invention may be stored in a readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product stored in a storage medium, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.

Claims

1. An intelligent identification method worn by a power distribution operator is characterized by comprising the following steps:

2. The intelligent identification method for the power distribution operator to wear according to claim 1, wherein the acquiring of the real-time monitoring video of the distribution network operator without power outage, performing image identification on the operator and the wearing equipment in the monitoring video, and obtaining the image information, the wearing information and the safety element information of the operation environment of the operator comprises:

3. The intelligent identification method for the power distribution operator to wear according to claim 2, wherein the performing position detection on the image information of the operator through the established multi-scale human body detection model, supplementing the safety element information according to the detected position information, matching with the operator, and performing mapping association identification on the operator, the position and the safety element information comprises:

supplementing the electric shock protection information and the high-altitude protection information according to the operation position information;

4. The intelligent identification method for the wearing of the power distribution operator according to claim 3, wherein the information integration is performed according to a plurality of detection results obtained by a plurality of matching and association marks, the personnel attribute identification is performed, the position area information to be tracked and the personnel attribute information are obtained, and the standard wearing requirement data of the operator is extracted through a distribution network operation wearing database according to the position area information to be tracked and the personnel attribute information, and the method comprises the following steps:

5. The intelligent recognition method that distribution operation personnel dressed, according to claim 4, characterized in that, the crossing ratio of the target operation personnel tracking frame according to each track point judges target operation personnel track information, if the crossing ratio of track point is less than the preset threshold value, then judges that the target operation personnel who monitors in the track point does not exist, gets rid of the track point, includes:

6. The intelligent recognition method that distribution operation personnel dressed, according to claim 5, characterized in that, effective track point and correspondence in the target operation personnel orbit information are taken notes, dress the target operation personnel's of requiring data to judge each effective track point wearing condition according to the standard is dressed, includes:

7. The intelligent identification method for the wearing of the power distribution workers according to claim 6, wherein the threshold value judgment is carried out according to the full-orbit wearing condition of each worker in the preset monitoring time period, and the warning and recording are carried out on the workers exceeding the wearing warning threshold value, and the method comprises the following steps:

comparing a threshold value according to the full-trajectory wearing failing data and a preset wearing warning threshold value;

8. An intelligent identification system worn by a power distribution worker, the system comprising: the intelligent identification system comprises a memory and a processor, wherein the memory comprises a program of the intelligent identification method worn by the power distribution operator, and the program of the intelligent identification method worn by the power distribution operator realizes the following steps when executed by the processor:

carrying out position detection on the image information of the operator through the established multi-scale human body detection model, supplementing safety element information according to the detected position information, matching with the operator, and carrying out mapping association identification on the operator, the position and the safety element information;

and judging a threshold value according to the full-track wearing condition of each operator in a preset monitoring time period, and warning and recording the operators exceeding the wearing warning threshold value.

9. The intelligent identification system of distribution operation personnel dress of claim 8, characterized in that, gather the real-time monitoring video of joining in marriage the uninterrupted operation personnel of net, carry out image recognition to operation personnel and the wearing equipment in the monitoring video, obtain operation personnel image information, dress information and the safe essential element information of operational environment, include:

acquiring images with operating personnel in a real-time monitoring video, and performing image identification and image information extraction on the operating personnel and wearable equipment to obtain image information and wearable information of the operating personnel;

10. A computer-readable storage medium containing a program of an intelligent identification method worn by a power distribution worker, the program of the intelligent identification method worn by a power distribution worker realizing the steps of the intelligent identification method worn by a power distribution worker according to any one of claims 1 to 7 when executed by a processor.