Substation worker working path tracking method

Abstract

The invention relates to a substation worker working path tracking method, and belongs to the field of intelligent video analysis and processing. The method comprises the following steps: acquiring current work order information; checking the identity and the wearing specification of the worker; obtaining path information, and planning an operation path; carrying out personnel tracking and path checking; and carrying out violation alarm and log recording. According to the invention, the false detection rate and the omission ratio are reduced. As the video is a continuous picture, the omission ratio can be reduced to below 1% by setting the threshold value of the number of continuously detected abnormal frames required by alarm; according to the method, regression filling in missing filling is selected to fill data sets such as a daily monitoring video of the transformer substation and common objects of the transformer substation, and the nearest feature value in a regression result is used as a filling result, so that the data utilization rate is improved; according to the invention, the detection accuracy of the tracking target in the video can reach 97.2%, and the detection delay is 76ms. Experimental results indicate that the method can well track the path of the staff in the transformer substation.

Description

technical field [0001] The invention relates to a method for tracking the work path of substation staff, in particular to video processing for work monitoring of substation staff, and belongs to the technical field of video intelligent analysis and processing. Background technique [0002] The lines and equipment in the substation have ultra-high voltage. Ensuring that the workers in the substation work in compliance with the safety procedures is the prerequisite for ensuring the safe and stable operation of the power system unit. To this end, it is necessary to establish a complete detection capability for hazardous elements in a strong electric field production environment. [0003] The traditional inspection of dangerous elements mostly relies on sensors or manual observation to detect, which has the problems of few types of detected hazards, poor detection accuracy and long alarm time. The substation intelligent monitoring technology that has been popularized in some ar...

AI Technical Summary

Problems solved by technology

In traditional target detection algorithms, most of them use the sliding window method for window nomination. The essence of this method is an exhaustive method, which will generate a large number of useless candidate regions, resulting in low algorithm performance.

In addition, the general target tracking algorithm will cause a huge performance consumption due to the tracking of all detections frame by frame, which will increase the tracking delay and decrease the accuracy rate.

Images