Image recognition-based power operation site safety monitoring method and system

Abstract

The application provides a power operation site safety monitoring method based on image recognition, and has the characteristics that: an image to be detected containing a scaffold is acquired; a human body key point recognition algorithm is used to recognize the image to be detected, so as to obtain key points of an operator; a frame recognition model is used to recognize the image to be detected, so as to obtain a scaffold frame; and according to the position relationship between the obtained key points of a high-altitude operator and the scaffold frame, it is determined whether there is a high-altitude unsafe behavior of the operator on the scaffold. By combining the behavior of the operator with the special environment of the scaffold high-altitude operation, the accuracy of the behavior detection of the operator in the special dangerous environment is improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of power safety, and particularly relates to a power operation site safety monitoring method and system based on image recognition. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute the prior art.

[0003] With the increasing demand for electricity, it is increasingly important to accelerate the construction and upgrading of power facilities and to strengthen the maintenance of power facilities.

[0004] Scaffolding provides full convenience for workers in high-altitude operations due to its convenience and flexibility, greatly improving work efficiency. The safety monitoring of the prior art for power operation is mostly focused on the monitoring of workers, such as the monitoring of non-standard behavior of workers and the monitoring of the standardization of workers wearing safety protection equipment, but ignores the fact that workers are in a high-altitude scaffold, and some behaviors of workers in ordinary environments such as reaching out do not pose a safety problem, but reaching out and other behaviors in a high-altitude scaffold do pose a safety problem. SUMMARY

[0005] To overcome the shortcomings of the prior art, the present application provides a power operation site safety monitoring method and system based on image recognition, which determines whether a worker has a dangerous behavior such as high-altitude reaching out on a scaffold according to the positional relationship between the worker's key points and the scaffold frame. By combining the worker's behavior with the special environment of high-altitude operation on a scaffold, the accuracy of worker behavior detection in this special dangerous environment is improved.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides a power operation site safety monitoring method based on image recognition, comprising:

[0007] Obtaining an image of a worker to be detected containing a scaffold;

[0008] Using a human key point recognition algorithm to recognize the image to be detected to obtain the key points of the worker;

[0009] Using a frame recognition model to recognize the image to be detected to obtain the scaffold frame;

[0010] According to the positional relationship between the obtained key points of the high-altitude worker and the scaffold frame, it is determined whether the worker has a high-altitude unsafe behavior on the scaffold.

[0011] The second aspect of the present application provides a power operation site safety monitoring system based on image recognition, comprising:

[0012] An acquisition module is configured to acquire an image of a worker to be detected including a scaffold;

[0013] A first extraction module is configured to identify the image of the worker to be detected by using a human key point identification algorithm to obtain key points of the worker;

[0014] A second extraction module is configured to identify the image of the worker to be detected by using a frame identification model to obtain a scaffold frame;

[0015] A safety monitoring module is configured to obtain whether the worker has a high-altitude unsafe behavior on the scaffold according to a positional relationship between the key points of the worker and the scaffold frame.

[0016] A third aspect of the present application provides a computer device, comprising a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the computer device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the power operation site safety monitoring method of image recognition.

[0017] A fourth aspect of the present application provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by the processor to perform the power operation site safety monitoring method of image recognition.

[0018] The above one or more technical solutions have the following beneficial effects:

[0019] In the present application, the worker to be detected and the scaffold are detected respectively to obtain key point information of the worker and frame information of the scaffold, and then the positional relationship between the key points of the worker and the scaffold frame is determined to determine whether the worker has a dangerous behavior such as high-altitude body exploration on the scaffold. By combining the behavior of the worker with the special environment of the high-altitude operation of the scaffold, the accuracy of the behavior detection of the worker in the special dangerous environment is improved.

[0020] The advantages of the additional aspects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be understood by the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0021] The drawings accompanying the specification of the present application form a part thereof, serve to provide further understanding of the present application, and together with the description of the exemplary embodiments of the present application and the explanation thereof serve to explain the present application, and do not constitute an improper limitation of the present application.

[0022] Figure 1A flow chart of the power operation site safety monitoring method based on image recognition in the first embodiment of the present application. DETAILED DESCRIPTION

[0023] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the present application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0024] It should be noted that the terms used herein are only intended to describe specific embodiments and are not intended to limit the exemplary embodiments according to the present application.

[0025] In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0026] Embodiment one

[0027] As shown in Figure 1 The present embodiment discloses a power operation site safety monitoring method based on image recognition, comprising:

[0028] Obtaining an image to be detected containing a scaffold and an operation personnel;

[0029] Using a human key point recognition algorithm to recognize the image to be detected, obtaining a key point of the operation personnel;

[0030] Using a frame recognition model to recognize the image to be detected, obtaining a scaffold frame;

[0031] According to the position relationship between the key point of the high-altitude personnel and the scaffold frame, it is obtained whether there is a high-altitude unsafe behavior of the operation personnel on the scaffold.

[0032] In the present embodiment, the dangerous behavior of the operation personnel on the scaffold includes a body stretching behavior, i.e. the body is stretched backward, forward or outward to perform operation, the human key point is offset, and the high-altitude body stretching behavior is very dangerous for the position located high above the scaffold.

[0033] The quality of the image has a great influence on the detection effect, and the image is easily affected by factors such as collection equipment and light in the image collection process, therefore, the image to be detected needs to be preprocessed.

[0034] In the present embodiment, the preprocessing includes uniform light processing and denoising processing of the image. The Mask uniform light method can eliminate the image light contrast, enhance the image light small contrast, and make the image illumination and brightness consistent. The wavelet transform can preserve the frequency information and spatial information of the image.

[0035] The embodiment obtains an image to be detected containing a scaffold and a worker, identifies key points of the worker, and identifies a scaffold frame to determine a distance between the worker and the scaffold frame in two dimensions of depth and level. Once a certain key point of the upper body of the worker is beyond a preset threshold relative to the scaffold frame, it indicates that the worker has a leaning behavior on the scaffold, resulting in a certain distance between the human body and the scaffold.

[0036] In the embodiment, an openpose extraction model is used to extract key points of the worker. The openpose extraction model can extract human key point information using a basic two-dimensional image.

[0037] The openpose extraction model uses a bottom-up structure to extract human key points, including a head vertex, a head center point, a left shoulder point, a right shoulder point, a shoulder center point, a body center point, a left leg center point, and a right leg center point.

[0038] According to the obtained key point information of the worker, pixel point coordinates and depth information of each key point are determined. The position relationship with the scaffold is determined in the horizontal direction to determine the distance between the worker and the scaffold in the image to be detected. The distance between the worker and the scaffold in the image to be detected is determined in the depth direction according to the depth information of the key points.

[0039] Since multiple surfaces of the scaffold can be used by the worker to climb and perform work, the position relationship between the worker and the scaffold is determined from two aspects to avoid the problem of inaccurate judgment due to the same depth distance between the worker and the scaffold, but a leaning behavior occurs in the horizontal direction, resulting in inaccurate judgment.

[0040] In the embodiment, a frame recognition model is used to identify the image to be detected to obtain a scaffold frame. Specifically, a scaffold mask image is binarized, and the mask region is labeled as red when obtained. The region can be easily labeled by binarization. The SUSAN corner detection algorithm is used to detect the corners of the binarized image to obtain the corner coordinates of the scaffold.

[0041] In the embodiment, the binarized scaffold mask image is first dilated and then eroded using the image closing operation principle of image morphology.

[0042] According to the obtained corner coordinates of the scaffold, line information of the entire scaffold is obtained by connecting lines. The scaffold lines are traversed to obtain pixel points and depth distances of each point of the scaffold lines.

[0043] In the embodiment, the scaffold frame information is obtained by using the corner point coordinates, and the position relationship of the worker relative to the scaffold is determined according to the scaffold frame information and the depth distance and the pixel point position of the key points of the worker.

[0044] If the depth distance between the key points of the worker and each position of the scaffold frame is within the preset first threshold range, the worker does not have an unsafe behavior on the scaffold.

[0045] If the depth distance between the key points of the worker and each position of the scaffold frame is outside the preset first threshold range, the worker has a high-altitude body-probing unsafe behavior on the scaffold.

[0046] If the pixel distance between the key points of the worker and each position of the scaffold frame is within the preset second threshold range, the worker does not have an unsafe behavior on the scaffold.

[0047] If the pixel distance between the key points of the worker and each position of the scaffold frame is outside the preset second threshold range, the worker has a high-altitude body-probing unsafe behavior on the scaffold.

[0048] It should be noted that the first threshold and the second threshold can be set according to actual conditions, so as to indicate that the worker exceeds the safe distance relative to the scaffold.

[0049] Embodiment Two

[0050] The purpose of the embodiment is to provide an image recognition-based power operation site safety monitoring system, which comprises:

[0051] An acquisition module is configured to acquire an image of a worker to be detected, which contains a scaffold;

[0052] A first extraction module is configured to identify the image of the worker to be detected by using a human key point recognition algorithm to obtain key points of the worker;

[0053] A second extraction module is configured to identify the image of the worker to be detected by using a frame recognition model to obtain a scaffold frame;

[0054] A safety monitoring module is configured to determine whether the worker has a high-altitude unsafe behavior on the scaffold according to the position relationship between the key points of the high-altitude worker and the scaffold frame.

[0055] Embodiment Three

[0056] The purpose of the embodiment is to provide a computing device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the steps of the above method.

[0057] Embodiment Four

[0058] The purpose of this embodiment is to provide a computer-readable storage medium.

[0059] A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method.

[0060] The steps and methods involved in the above embodiments two, three and four correspond to embodiment one, and the detailed description can be found in the relevant description part of embodiment one. The term "computer-readable storage medium" should be understood as including a single medium or multiple media of one or more instruction sets; it should also be understood as including any medium capable of storing, encoding or carrying instruction sets for execution by a processor and causing the processor to perform any of the methods in the present application.

[0061] Those skilled in the art should understand that the above-mentioned modules or steps of the present application can be realized by a general computer device, alternatively, they can be realized by program codes executable by a computing device, so that they can be stored in a storage device for execution by a computing device, or they can be respectively made into individual integrated circuit modules, or a plurality of modules or steps among them can be made into a single integrated circuit module. The present application is not limited to any specific combination of hardware and software.

[0062] The above describes the specific embodiments of the present application in combination with the accompanying drawings, but is not a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications or variations made by those skilled in the art on the basis of the technical solutions of the present application without creative labor are still within the protection scope of the present application.

Claims

1. A method for monitoring safety at a power work site based on image recognition, characterized by, The method comprises the following steps: obtaining an image of a worker including a scaffold to be detected; recognizing the image to be detected by using a human key point recognition algorithm to obtain key points of the worker; recognizing the image to be detected by using a frame recognition model to obtain a scaffold frame; obtaining whether the worker has an unsafe behavior on the scaffold according to the position relationship between the key points of the worker and the scaffold frame; extracting key points of a human skeleton of the worker by using openpose, and determining a depth distance and a pixel position of each key point according to the extracted key points; obtaining line information of the entire scaffold by connecting in a line manner according to corner point coordinates of the scaffold, traversing the scaffold lines to obtain a pixel point and a depth distance of each point of the scaffold lines; obtaining scaffold frame information by using the corner point coordinates, and judging the position relationship of the worker relative to the scaffold according to the scaffold frame information and the depth distance and the pixel position of the key points of the worker.

2. The image recognition-based power work site safety monitoring method of claim 1, wherein, The method comprises the following steps: obtaining a scaffold mask image based on the image to be detected; performing binaryzation processing on the scaffold mask image; detecting corners of the binaryzation scaffold mask image based on a corner detection algorithm to obtain corner point coordinates of the scaffold.

3. The image recognition-based power operation site safety monitoring method according to claim 2, wherein if the depth distance between the key points of the worker and each position of the scaffold frame is within a preset first threshold range, the worker does not have an unsafe behavior on the scaffold; if the depth distance between the key points of the worker and each position of the scaffold frame is outside the preset first threshold range, the worker has an unsafe behavior of reaching out on the scaffold.

4. The image recognition-based power work site safety monitoring method of claim 3, wherein, The method further comprises the following steps: if the pixel distance between the pixel points of the key points of the worker and each position of the scaffold frame is within a preset second threshold range, the worker does not have an unsafe behavior on the scaffold; if the pixel distance between the pixel points of the key points of the worker and each position of the scaffold frame is outside the preset second threshold range, the worker has an unsafe behavior of reaching out on the scaffold.

5. The image recognition-based power work site safety monitoring method of claim 2, wherein, The method further comprises performing a closed operation operation of image inflation and then corrosion on the binaryzation scaffold mask image by using an image closed operation principle of image morphology.

6. The image recognition-based power work site safety monitoring method of claim 1, wherein, The method further comprises performing denoising and dodging processing on the image to be detected.

7. An image recognition-based power work site safety monitoring system, characterized by, The method comprises the following steps: an acquisition module: obtaining an image of a worker including a scaffold to be detected; a first extraction module: recognizing the image to be detected by using a human key point recognition algorithm to obtain key points of the worker; a second extraction module: recognizing the image to be detected by using a frame recognition model to obtain a scaffold frame; a safety monitoring module: obtaining whether the worker has an unsafe behavior on the scaffold according to the position relationship between the key points of the worker and the scaffold frame. The openpose is used to extract the key points of the human skeleton of the worker, and the depth distance and pixel position of each key point are determined according to the extracted key points; According to the corner point coordinates of the scaffold, the line information of the whole scaffold is obtained through the connection line, the scaffold lines are traversed, and the pixel point and the depth distance of each point of the scaffold line are obtained; The scaffold frame information is obtained by using the corner point coordinates, and the position relationship of the worker relative to the scaffold is judged according to the scaffold frame information and the depth distance and pixel position of the key points of the worker.

8. A computer device, comprising: It comprises a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the computer equipment runs, the processor and the memory communicate through the bus, the machine readable instructions are executed by the processor to execute the image recognition based power operation site safety monitoring method of any one of claims 1 to 6. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to execute the image recognition based power operation site safety monitoring method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, ​

Images