CN113743224B - Method and system for monitoring wearing of safety belt of ascending operator based on edge calculation - Google Patents
Method and system for monitoring wearing of safety belt of ascending operator based on edge calculation Download PDFInfo
- Publication number
- CN113743224B CN113743224B CN202110893236.2A CN202110893236A CN113743224B CN 113743224 B CN113743224 B CN 113743224B CN 202110893236 A CN202110893236 A CN 202110893236A CN 113743224 B CN113743224 B CN 113743224B
- Authority
- CN
- China
- Prior art keywords
- frame image
- wearing state
- image
- edge
- state detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
Abstract
The invention discloses a method and a system for monitoring the wearing of a safety belt of a climbing operator based on edge calculation, wherein the method comprises the following steps: acquiring a first wearing state detection original result through a first edge computing component; when the original result represents that the first wearing state is abnormal, a second edge computing component is used for proxy of the first edge computing component to obtain a first wearing state detection substitution result, and the first wearing state detection substitution result is generated according to a second frame image sent by the first edge intelligent terminal; when the original result or the alternative result represents that the first wearing state is normal, the second wearing state detection result is determined through the second edge calculation component, so that complex calculation amount of the first wearing state analysis process for each frame of acquired image is avoided, and the first wearing state detection efficiency is improved.
Description
Technical Field
The invention relates to the technical field of safety control of electric power operation sites, in particular to a method and a system for monitoring the wearing of safety belts of operators in ascending operation based on edge calculation.
Background
In the management of power safety production, control and management of safety of field operation are one of important contents of safety control and management of each level of units. In order to ensure safe operation and production, effective safe management and control are needed in both working and test sites, including supervision of the operation process of operators. In the prior art, the video image of the monitoring site is analyzed by utilizing the computer vision technology of the front edge, various abnormal conditions are identified and relevant responses are made, but the analysis method based on the video image has huge calculation amount of preprocessing, feature extraction, feature classification and the like of the image through a network model if each acquired frame image is subjected to safety analysis, has low identification efficiency and identification accuracy, and can possibly generate omission if part of image frames are selected for safety analysis according to a preset method.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method, a system, related equipment and a readable storage medium for monitoring the wearing of a safety belt of a climbing operator based on edge calculation, which are used for carrying out operation safety analysis and monitoring based on incrementally updated difference data, and effectively improving the operation safety analysis efficiency and accuracy. The specific technical scheme is as follows:
the utility model provides a method for monitoring the wearing of a safety belt of a worker on the basis of edge calculation, which is applied to an edge calculation device, wherein the edge calculation device is provided with a first edge calculation component and a second edge calculation component, and the method comprises the following steps:
acquiring a first wearing state detection original result through a first edge computing component, wherein the first wearing state detection original result is generated by the first edge computing component according to a first frame image sent by a first edge intelligent terminal;
when the original result represents that the first wearing state is abnormal, a second edge computing component is used for proxy of the first edge computing component to obtain a first wearing state detection substitution result, and the first wearing state detection substitution result is generated according to a second frame image sent by the first edge intelligent terminal;
and when the original result or the substitution result represents that the first wearing state is normal, determining a second wearing state detection result through a second edge calculation component, wherein the second wearing state detection result is generated by the second edge calculation component according to data sent by the second edge intelligent terminal.
Optionally, the first wearing state detection data is used for representing whether the safety belt exists on the worker, and the second wearing state detection data is used for representing whether the worker wears the safety belt correctly.
Optionally, the edge computing device is further configured with a data feature characterization component, where when the original result characterizes the first wearing state abnormality, the first wearing state detection substitution result is obtained by the second edge computing component by proxy of the first edge computing component, including:
when the original result represents that the first wearing state is abnormal, the data characteristic component acquires characteristic change data aiming at a first frame image, wherein the characteristic change data aiming at the first frame image is determined by the data characteristic representation component according to an image frame after the first frame image is sent by the first edge intelligent terminal;
the data characteristic characterization component determines that an image frame after the first frame image is transformed into a second frame image according to the characteristic change data;
and the second edge computing component executes a first wearing state detection program according to the second frame image to acquire a first wearing state detection substitution result.
Optionally, the data feature component acquires feature variation data for the first frame image, and determines that an image frame after the first frame image is transformed into the second frame image according to the feature variation data, including:
recording pixel points in a first frame image as first pixel points, and recording each pixel point in an image frame after the first frame image as a second pixel point;
according to the pixel data of the first frame image, searching a second pixel point corresponding to a first pixel point in a target area in the first frame image in the current image frame, and forming a pixel point pair according to the first pixel point and the second pixel point corresponding to the first pixel point;
and judging whether the number of the second pixel points in all the pixel point pairs is consistent with the number of all the first pixel points in the target area in the first frame image, and if not, determining that the current image frame is the second frame image.
Optionally, the searching for the second pixel point in the current image frame, where the second pixel point corresponds to the first pixel point in the target area in the first frame image includes: searching and acquiring a second belonging environmental feature with the maximum similarity with the first environmental feature in a second frame image based on a first belonging environmental feature of a first pixel point in a target area in the first frame image, and determining a second pixel point corresponding to the first pixel point in the second frame image based on the second belonging environmental feature.
Optionally, the second edge calculating component executes a first wearing state detection program according to the second frame image, and obtains a first wearing state detection substitution result, including:
forming a combined image to be detected based on second pixel points in the second frame image, which do not correspond to the first pixel points in the target area in the first frame image;
and analyzing and judging whether the safety belt target exists or not according to the combined image to be detected.
Optionally, the first edge intelligent terminal is a video monitoring device, and the second edge intelligent terminal is an intelligent hook sensor.
Climbing operator safety belt wears monitored control system based on edge calculation includes:
the first detection unit is used for acquiring a first wearing state detection original result through the first edge calculation component, wherein the first wearing state detection original result is generated by the first edge calculation component according to a first frame image sent by the first edge intelligent terminal;
the first detection unit is used for obtaining a first wearing state detection substitution result through the first edge calculation component when the original result represents that the first wearing state is abnormal, and the first wearing state detection substitution result is generated according to a first frame image sent by the first edge intelligent terminal;
and the third detection unit is used for determining a second wearing state detection result through the second edge calculation component when the original result or the substitution result represents that the first wearing state is normal, wherein the second wearing state detection result is generated by the second edge calculation component according to data sent by the second edge intelligent terminal.
An ascending operator safety belt wearing monitoring device based on edge calculation comprises a memory and a processor;
the memory is used for storing programs;
the processor is used for executing the program to realize each step of the method for monitoring the wearing of the safety belt of the ascending operator.
A readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above-described method for monitoring the wearing of a safety belt by an operator.
The method and the system for monitoring the wearing of the safety belt of the ascending operator based on the edge calculation have the following beneficial effects: based on the characteristic of the first wearing state detection data when the first wearing state is abnormal, searching for a new monitoring video image to obtain an incrementally updated image characteristic, determining a second frame image which is different from the first frame image in terms of the image characteristic, and analyzing the first wearing state based on the image characteristic which is incrementally updated compared with the first frame image in the second frame image, so that the complex calculation amount of the first wearing state analysis process for each frame of acquired image is avoided, and the first wearing state detection efficiency is improved.
Drawings
Fig. 1 is a flow chart of a method for monitoring the wearing of a safety belt of an ascending operator based on edge calculation in an embodiment of the present application;
fig. 2 is a block diagram of a safety belt wearing monitoring system for a climbing operator based on edge calculation in an embodiment of the present application.
Description of the embodiments
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Referring to fig. 1, an embodiment of the present application provides a method for monitoring the wearing of a safety belt of a worker on the basis of edge calculation, which is applied to an edge calculation device, wherein the edge calculation device is deployed with a first edge calculation component and a second edge calculation component, and the method includes:
acquiring a first wearing state detection original result through a first edge computing component, wherein the first wearing state detection original result is generated by the first edge computing component according to a first frame image sent by a first edge intelligent terminal;
when the original result represents that the first wearing state is abnormal, a second edge computing component is used for proxy of the first edge computing component to obtain a first wearing state detection substitution result, and the first wearing state detection substitution result is generated according to a second frame image sent by the first edge intelligent terminal;
and when the original result or the substitution result represents that the first wearing state is normal, determining a second wearing state detection result through a second edge calculation component, wherein the second wearing state detection result is generated by the second edge calculation component according to data sent by the second edge intelligent terminal.
In the embodiment of the application, for the case that the first edge computing component determines that the first wearing state is abnormal, the first edge computing component is not repeatedly adopted to detect the first wearing state of a new monitoring video image of an operator, that is, analysis of the first wearing state of each acquired image is not performed through image preprocessing, image enhancement, image feature extraction, image candidate frame generation and target identification classification, but based on the feature of the first wearing state detection data when the first wearing state is abnormal, the new monitoring video image is searched to obtain the image feature updated incrementally, a second frame image which is different from the first frame image in image feature is determined, and analysis of the first wearing state is performed based on the image feature updated incrementally compared with the first frame image in the second frame image, so that complex calculation amount of first wearing state analysis process is avoided for each acquired image and the first wearing state detection efficiency is improved.
In this application embodiment, to the control of wearing of operation personnel safety belt of ascending a height, can arrange multiple edge intelligent terminal at the operation scene of ascending a height, multiple edge intelligent terminal carries out data communication with edge computing device through communication module, edge intelligent terminal is used for gathering the monitored data of operation scene, concretely can be equipped with a plurality of video terminals at the operation scene, such as remove the control ball for gather the video data of operation scene, every team operation personnel is equipped with a plurality of mobile handheld terminals for the transmission data of operation team personnel to the higher level control backstage, every operation personnel is equipped with the security apparatus, including intelligent safety helmet, this intelligent safety helmet has functions such as high detection, pronunciation talkback. For the condition that the first wearing state detection result is abnormal, the edge computing device can send out alarm prompt information through intelligent safety helmet operators to prompt the operators to wear safety belts or correctly wear the safety belts. In this embodiment, the first edge intelligent terminal is a video monitoring device, the second edge intelligent terminal is an intelligent hook sensor, in an application scenario, the first edge computing component detects that an operator does not wear a safety belt, alarm information is sent out, the operator wears the safety helmet based on the alarm information, the second edge computing component proxies the first edge computing component to detect that the first wearing state detection substitution result is that the safety helmet is worn, and then the second edge computing component detects the second wearing state.
In one embodiment, a similar method to the first wearing state detection method may also be employed for the detection of the second wearing state.
The first wearing state detection data are used for representing whether the safety belt exists on the body of the operator or not, and the second wearing state detection data are used for representing whether the safety belt is correctly worn by the operator or not.
In order to improve the detection efficiency of the first wearing state and the second wearing state, the detection of the second wearing state of the application is determined based on sensing data, and specifically, the second edge intelligent terminal is an intelligent hook sensor, and whether an operator wears a safety belt correctly is directly judged through intelligent hook state data acquired by the sensor.
In one embodiment, the edge computing device is further configured with a data feature characterization component, wherein when the original result characterizes the first wearing state abnormality, the first wearing state detection substitution result is obtained by the second edge computing component through the second edge computing component proxy, and the method includes:
when the original result represents that the first wearing state is abnormal, the data characteristic component acquires characteristic change data aiming at a first frame image, wherein the characteristic change data aiming at the first frame image is determined by the data characteristic representation component according to an image frame after the first frame image is sent by the first edge intelligent terminal;
the data characteristic characterization component determines that an image frame after the first frame image is transformed into a second frame image according to the characteristic change data;
and the second edge computing component executes a first wearing state detection program according to the second frame image to acquire a first wearing state detection substitution result.
In the embodiment of the application, whether the image characteristics of each image frame are changed compared with the first frame image is determined by the data characterization component for all the image frames after the first frame image, and the first wearing state detection is performed for the second frame image which is different from the first frame image, so that the complex calculation amount of performing the first wearing state analysis process for each frame acquisition image is avoided.
In one embodiment, the data feature component obtains feature variation data for a first frame image and determines from the feature variation data that an image frame subsequent to the first frame image is transformed into a second frame image, comprising:
recording pixel points in a first frame image as first pixel points, and recording each pixel point in an image frame after the first frame image as a second pixel point;
according to the pixel data of the first frame image, searching a second pixel point corresponding to a first pixel point in a target area in the first frame image in the current image frame, and forming a pixel point pair according to the first pixel point and the second pixel point corresponding to the first pixel point;
and judging whether the number of the second pixel points in all the pixel point pairs is consistent with the number of all the first pixel points in the target area in the first frame image, and if not, determining that the current image frame is the second frame image.
In the embodiment of the present application, for the feature change determining method of each frame of image after the first image frame, a method of matching and judging with the pixels of the first image is adopted, specifically, for the region operation target region including the operator and the safety device carried by the operator in the first frame of image, in this embodiment, the analysis is performed only based on the target region, so as to avoid the analysis of the pixels of the invalid image region. In the process of pairing the pixel points of the subsequent image frame and the first frame image, if the second pixel points paired with all the first pixel points in the target area in the first frame image can be acquired in the subsequent image frame, namely, the current image frame and the first frame image are judged to have no difference, otherwise, the characteristic data different from the first frame image exists in the subsequent image frame, namely, the image frame is the second frame image.
In one embodiment, searching for a second pixel point in the current image frame corresponding to a first pixel point in the target area in the first frame image includes: searching and acquiring a second belonging environmental feature with the maximum similarity with the first environmental feature in a second frame image based on a first belonging environmental feature of a first pixel point in a target area in the first frame image, and determining a second pixel point corresponding to the first pixel point in the second frame image based on the second belonging environmental feature.
Specifically, a first affiliated environmental feature of the first pixel point in the first frame image is determined based on the features of surrounding pixel points of the first pixel point, the first affiliated environmental feature is used for representing the environment where the first pixel point is located, specifically, a first area containing the first pixel point is obtained by a preset area dividing method, the relative position of the first pixel point in the first area is recorded as a first relative position, the first affiliated environmental feature is calculated, a second area corresponding to each second pixel point is obtained in the second frame image based on the first relative position for each second pixel point, the second affiliated environmental feature is calculated, the second area with the largest similarity to the first affiliated environmental feature is searched in the second frame image based on the first affiliated environmental feature, a corresponding second area is determined based on the second affiliated environmental feature with the largest similarity, and the second pixel point in the second area is obtained according to the first relative position and serves as the second pixel point corresponding to the first pixel point.
In one embodiment, the second edge calculating component executes a first wearing state detection program according to the second frame image, and obtains a first wearing state detection substitution result, including:
forming a combined image to be detected based on second pixel points in the second frame image, which do not correspond to the first pixel points in the target area in the first frame image;
and analyzing and judging whether the safety belt target exists or not according to the combined image to be detected.
In the embodiment of the application, the second edge computing component takes the first edge computing component to obtain the first wearing state detection substitution result through the detection analysis of the combined image to be detected, and the analysis process is carried out by adopting the incrementally updated difference data, so that the calculated amount is further simplified, namely, compared with the first wearing state detection program executed by the second edge computing component, the first wearing state detection program is different from the first wearing state detection method executed by the first edge computing component, the calculated amount is reduced compared with the first wearing state detection program, the detection speed is faster, the noise influence of redundant pixel points is avoided, and the accuracy of the detection result is improved.
The following describes a safety belt wearing monitoring system for a person working above based on edge calculation disclosed in the embodiments of the present application, and the safety belt wearing monitoring system for a person working above based on edge calculation described below and the safety belt wearing monitoring method for a person working above based on edge calculation described above may be referred to correspondingly.
Referring to fig. 2, an embodiment of the present application provides a safety belt wearing monitoring system for a climbing operator based on edge calculation, including:
the first detection unit is used for acquiring a first wearing state detection original result through the first edge calculation component, wherein the first wearing state detection original result is generated by the first edge calculation component according to a first frame image sent by the first edge intelligent terminal;
the first detection unit is used for obtaining a first wearing state detection substitution result through the first edge calculation component when the original result represents that the first wearing state is abnormal, and the first wearing state detection substitution result is generated according to a first frame image sent by the first edge intelligent terminal;
and the third detection unit is used for determining a second wearing state detection result through the second edge calculation component when the original result or the substitution result represents that the first wearing state is normal, wherein the second wearing state detection result is generated by the second edge calculation component according to data sent by the second edge intelligent terminal.
The embodiment of the application provides a safety belt wearing monitoring device for a climbing operator based on edge calculation, which comprises a memory and a processor;
the memory is used for storing programs;
the processor is used for executing the program to realize each step of the method for monitoring the wearing of the safety belt of the ascending operator.
The hardware structure of the safety belt wearing monitoring equipment for the climbing operator can comprise: at least one processor, at least one communication interface, at least one memory and at least one communication bus;
in the embodiment of the application, the number of the processor, the communication interface, the memory and the communication bus is at least one, and the processor, the communication interface and the memory complete communication with each other through the communication bus;
the processor may be a Central Processing Unit (CPU), or a specific integrated circuit (asic) ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention, etc.;
the memory may comprise a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory;
the memory stores a program, and the processor can call the program stored in the memory, wherein the program is used for realizing each step of the method for monitoring the wearing of the safety belt of the ascending operator.
The embodiment of the application provides a readable storage medium, on which a computer program is stored, where the computer program is executed by a processor, and the steps of the method for monitoring the wearing of the safety belt of the ascending operator are implemented, and specifically, the refinement function and the expansion function of the computer program stored on the readable storage medium can be described with reference to the foregoing.
The present invention is not limited to the above-described specific embodiments, and various modifications may be made by those skilled in the art without inventive effort from the above-described concepts, and are within the scope of the present invention.
Claims (6)
1. The method is characterized by being applied to an edge computing device, wherein the edge computing device is provided with a first edge computing component and a second edge computing component, and the method comprises the following steps:
acquiring a first wearing state detection original result through a first edge computing component, wherein the first wearing state detection original result is generated by the first edge computing component according to a first frame image sent by a first edge intelligent terminal;
when the original result represents that the first wearing state is abnormal, a second edge computing component is used for proxy of the first edge computing component to obtain a first wearing state detection substitution result, and the first wearing state detection substitution result is generated according to a second frame image sent by the first edge intelligent terminal;
when the original result or the substitution result represents that the first wearing state is normal, a second wearing state detection result is determined through a second edge calculation component, wherein the second wearing state detection result is generated by the second edge calculation component according to data sent by a second edge intelligent terminal;
the edge computing device is further configured with a data feature characterization component, wherein when the original result characterizes a first wearing state abnormality, a first wearing state detection substitution result is obtained by the first edge computing component through a second edge computing component proxy, and the method comprises the following steps:
when the original result represents that the first wearing state is abnormal, the data characteristic component acquires characteristic change data aiming at a first frame image, wherein the characteristic change data aiming at the first frame image is determined by the data characteristic representation component according to an image frame after the first frame image is sent by the first edge intelligent terminal;
the data characteristic characterization component determines that an image frame after the first frame image is transformed into a second frame image according to the characteristic change data;
the second edge computing component executes a first wearing state detection program according to the second frame image to obtain a first wearing state detection substitution result;
the data feature component obtains feature change data for a first frame image, and determines that an image frame after the first frame image is transformed into a second frame image according to the feature change data, and the data feature component comprises:
recording pixel points in a first frame image as first pixel points, and recording each pixel point in an image frame after the first frame image as a second pixel point;
according to the pixel data of the first frame image, searching a second pixel point corresponding to a first pixel point in a target area in the first frame image in the current image frame, and forming a pixel point pair according to the first pixel point and the second pixel point corresponding to the first pixel point;
judging whether the number of second pixel points in all pixel point pairs is consistent with the number of all first pixel points in a target area in the first frame image, if not, determining that the current image frame is a second frame image;
the searching the second pixel point corresponding to the first pixel point in the target area in the first frame image in the current image frame comprises the following steps: searching and acquiring a second belonging environmental feature with the maximum similarity with the first belonging environmental feature in a second frame image based on a first belonging environmental feature of a first pixel point in a target area in the first frame image, and determining a second pixel point corresponding to the first pixel point in the second frame image based on the second belonging environmental feature;
the second edge computing component executes a first wearing state detection program according to a second frame image to obtain a first wearing state detection substitution result, and the second edge computing component comprises:
forming a combined image to be detected based on second pixel points in the second frame image, which do not correspond to the first pixel points in the target area in the first frame image;
and analyzing and judging whether the safety belt target exists or not according to the combined image to be detected.
2. The edge calculation based safety belt wearing monitoring method for a climbing operator according to claim 1, wherein the first wearing state detection data is used for representing whether the safety belt exists on the operator, and the second wearing state detection data is used for representing whether the operator wears the safety belt correctly.
3. The method for monitoring the wearing of the safety belt of the ascending operator based on the edge calculation according to claim 1, wherein the first edge intelligent terminal is a video monitoring device, and the second edge intelligent terminal is an intelligent hook sensor.
4. Ascending operator safety belt wears monitored control system based on edge calculation, its characterized in that includes:
the first detection unit is used for acquiring a first wearing state detection original result through the first edge calculation component, wherein the first wearing state detection original result is generated by the first edge calculation component according to a first frame image sent by the first edge intelligent terminal;
the first detection unit is used for obtaining a first wearing state detection substitution result through the first edge calculation component when the original result represents that the first wearing state is abnormal, and the first wearing state detection substitution result is generated according to a first frame image sent by the first edge intelligent terminal;
the third detection unit is used for determining a second wearing state detection result through the second edge calculation component when the original result or the replacement result represents that the first wearing state is normal, wherein the second wearing state detection result is generated by the second edge calculation component according to data sent by the second edge intelligent terminal;
the system further includes a data characterization component, wherein when the original result characterizes a first wear state anomaly, the first edge calculation component is proxied by a second edge calculation component to obtain a first wear state detection replacement result, comprising:
when the original result represents that the first wearing state is abnormal, the data characteristic component acquires characteristic change data aiming at a first frame image, wherein the characteristic change data aiming at the first frame image is determined by the data characteristic representation component according to an image frame after the first frame image is sent by the first edge intelligent terminal;
the data characteristic characterization component determines that an image frame after the first frame image is transformed into a second frame image according to the characteristic change data;
the second edge computing component executes a first wearing state detection program according to the second frame image to obtain a first wearing state detection substitution result;
the data feature component obtains feature change data for a first frame image, and determines that an image frame after the first frame image is transformed into a second frame image according to the feature change data, and the data feature component comprises:
recording pixel points in a first frame image as first pixel points, and recording each pixel point in an image frame after the first frame image as a second pixel point;
according to the pixel data of the first frame image, searching a second pixel point corresponding to a first pixel point in a target area in the first frame image in the current image frame, and forming a pixel point pair according to the first pixel point and the second pixel point corresponding to the first pixel point;
judging whether the number of second pixel points in all pixel point pairs is consistent with the number of all first pixel points in a target area in the first frame image, if not, determining that the current image frame is a second frame image;
the searching the second pixel point corresponding to the first pixel point in the target area in the first frame image in the current image frame comprises the following steps: searching and acquiring a second belonging environmental feature with the maximum similarity with the first belonging environmental feature in a second frame image based on a first belonging environmental feature of a first pixel point in a target area in the first frame image, and determining a second pixel point corresponding to the first pixel point in the second frame image based on the second belonging environmental feature;
the second edge computing component executes a first wearing state detection program according to a second frame image to obtain a first wearing state detection substitution result, and the second edge computing component comprises:
forming a combined image to be detected based on second pixel points in the second frame image, which do not correspond to the first pixel points in the target area in the first frame image;
and analyzing and judging whether the safety belt target exists or not according to the combined image to be detected.
5. The equipment for monitoring the wearing of the safety belt of the ascending operator based on the edge calculation is characterized by comprising a memory and a processor;
the memory is used for storing programs;
the processor for executing the program to realize the respective steps of the ascending operator seat belt wear monitoring method according to any one of claims 1 to 3.
6. A readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method for monitoring the wearing of a safety belt by a person working on a height as claimed in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893236.2A CN113743224B (en) | 2021-08-04 | 2021-08-04 | Method and system for monitoring wearing of safety belt of ascending operator based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893236.2A CN113743224B (en) | 2021-08-04 | 2021-08-04 | Method and system for monitoring wearing of safety belt of ascending operator based on edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113743224A CN113743224A (en) | 2021-12-03 |
| CN113743224B true CN113743224B (en) | 2023-05-23 |
Family
ID=78730083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110893236.2A Active CN113743224B (en) | 2021-08-04 | 2021-08-04 | Method and system for monitoring wearing of safety belt of ascending operator based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113743224B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709443A (en) * | 2016-12-19 | 2017-05-24 | 同观科技（深圳）有限公司 | Method for detecting wearing state of safety belt and terminal |
| CN108921004A (en) * | 2018-04-27 | 2018-11-30 | 淘然视界(杭州)科技有限公司 | Safety cap wears recognition methods, electronic equipment, storage medium and system |
| KR20210064123A (en) * | 2020-06-29 | 2021-06-02 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Method and apparatus for recognizing wearing state of safety belt, electronic device, and storage medium |
| CN113111823A (en) * | 2021-04-22 | 2021-07-13 | 广东工业大学 | Abnormal behavior detection method and related device for building construction site |
-
2021
- 2021-08-04 CN CN202110893236.2A patent/CN113743224B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709443A (en) * | 2016-12-19 | 2017-05-24 | 同观科技（深圳）有限公司 | Method for detecting wearing state of safety belt and terminal |
| CN108921004A (en) * | 2018-04-27 | 2018-11-30 | 淘然视界(杭州)科技有限公司 | Safety cap wears recognition methods, electronic equipment, storage medium and system |
| KR20210064123A (en) * | 2020-06-29 | 2021-06-02 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Method and apparatus for recognizing wearing state of safety belt, electronic device, and storage medium |
| CN113111823A (en) * | 2021-04-22 | 2021-07-13 | 广东工业大学 | Abnormal behavior detection method and related device for building construction site |
Non-Patent Citations (1)
| Title |
|---|
| 基于深度学习的安全帽佩戴检测实现与分析;邓开发;邹振宇;;计算机时代(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113743224A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101957325A (en) | Substation equipment appearance abnormality recognition method based on substation inspection robot | |
| CN111222423A (en) | Target identification method and device based on operation area and computer equipment | |
| CN111126153B (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
| CN110134571A (en) | Rotary-type mechanical equipment health status monitoring method and device | |
| CN112347916A (en) | Power field operation safety monitoring method and device based on video image analysis | |
| CN113283344A (en) | Mining conveying belt deviation detection method based on semantic segmentation network | |
| CN110929591A (en) | Transformer substation monitoring method and device, computer equipment and storage medium | |
| CN110602485B (en) | Fault detection method and related product | |
| CN111695512B (en) | Unattended cultural relic monitoring method and unattended cultural relic monitoring device | |
| CN111062918B (en) | Abnormality detection method and device based on computer vision | |
| CN112215120B (en) | Method and device for determining visual search area and driving simulator | |
| CN112454008A (en) | Cutting platform service life prediction method and system based on network model and readable storage medium | |
| CN114155492A (en) | High-altitude operation safety belt hanging rope high-hanging low-hanging use identification method and device and electronic equipment | |
| CN110428579A (en) | Indoor Monitoring System, method and device based on image recognition | |
| CN113743224B (en) | Method and system for monitoring wearing of safety belt of ascending operator based on edge calculation | |
| CN111222477B (en) | Vision-based method and device for detecting departure of hands from steering wheel | |
| CN113516091B (en) | Method for identifying electric spark image of transformer substation | |
| CN113536842A (en) | Electric power operator safety dressing identification method and device | |
| CN115546736A (en) | River channel sand collection monitoring processing method and system based on image collection | |
| CN116824471A (en) | Intelligent derrick area operation monitoring method and system | |
| CN114741690A (en) | Network security monitoring method, device, equipment and computer storage medium | |
| CN114720812A (en) | Method and system for processing and positioning faults of power distribution network | |
| CN112347824A (en) | Wearing object identification method, device, equipment and storage medium | |
| CN116150666B (en) | Energy storage system fault detection method and device and intelligent terminal | |
| CN114153730A (en) | Method for generating buried point configuration page and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |