Intelligent identification method and medium for safety status of electric power personnel based on stride measurement

Abstract

The invention discloses a method and medium for intelligently identifying the safety state of electric power personnel based on stride measurement. The method includes: detecting and tracking each person's enclosing frame in a video screen based on a multi-target tracking algorithm and assigning a person ID number; Input the key point detection algorithm of the image to obtain the key points of the left and right ankles of the human body and associate the bounding box of the person; determine the bounding box of the person whose stride is to be measured and obtain the corresponding key point data of the left and right ankles, choose to measure the ankle, and measure the key points of the ankle Determine and measure the current motion state of the ankle, calculate and measure the moving distance between two adjacent static states of the ankle, record it as the personnel stride, and generate personnel status information; generate personnel safety status based on personnel status information and preset safety rules information. The present invention does not require additional manual intervention, and only needs to collect test pictures in real time through the camera without wearing other hardware devices. It has fast running speed, convenient deployment and is applicable to different scenarios.

Description

technical field [0001] The invention relates to the field of electric power safety, in particular to a method and medium for intelligently identifying the safety state of electric power personnel based on stride measurement. Background technique [0002] The voltage of the high-voltage laboratory is 66kV and above. Voltage is fatal to the human body. Inevitably, laboratories are divided into various work areas and cross-working phenomena. under high voltage. Personnel actions and safety control are particularly important. The existing work control method is usually through the supervision of security blocking personnel, and safety accidents occur from time to time. In order to better ensure the safety of personnel, there is an urgent need for an intelligent identification method for key points in high-voltage laboratories. Through human motion recognition, voice prompts and early warnings can be used to prevent accidents. [0003] Stride size is an important factor in h...

AI Technical Summary

Problems solved by technology

For example, the method of observing the motion state of pedestrians based on video is to accurately measure the foot length and stride of the person in the video through video screenshots, which achieves a higher-precision stride measurement than the sensor method, but the stride measurement in this method The steps require a lot of manual participation and the process is complicated, and the implementation cost is high, so the usage scenarios are relatively limited

[0004] At present, most of the security control is based on the form of security personnel and video recording. This kind of method has the following disadvantages: (1) It depends on the vision of personnel, and cannot cover all, let alone real-time supervision and viewing; (2) The way of recording video It is impossible to warn and prevent accidents in advance, it can only be analyzed at the right time; (3) The theoretical knowledge and experience requirements of personnel are high, and there may be omissions and insufficient supervision

Images