Substation scene personnel target detection method and system

Abstract

The invention discloses a substation scene personnel target detection method, which comprises: inputting a to-be-detected image into a pre-trained brightness detection network, and obtaining brightness information of the to-be-detected image; determining a difference threshold according to the brightness information, obtaining a background-removed difference image by using an image difference method based on a fixed background reference, and determining personnel target scale information in the to-be-detected image; and inputting the to-be-detected image, the differential image and the personnel target scale information into a pre-trained personnel target detection network to obtain a position frame and a type of the personnel target. Meanwhile, the invention discloses a corresponding system. According to the invention, the background in the image is removed through the image difference method, and the personnel target detection network is adopted to effectively realize the personnel target detection of the substation scene with the complex background.

Description

technical field [0001] The invention relates to a method and system for detecting a human target in a substation scene, belonging to the fields of deep learning and artificial intelligence. Background technique [0002] The substation is an important power facility in the power grid. There are many power equipment in the substation. In order to ensure the safe and stable operation of the daily production process of the substation, it is necessary to monitor the people moving in the substation in real time. In recent years, with the development of artificial intelligence and video surveillance, the concept of "unattended" substation has been proposed, which has greatly improved the automation level of substations, reduced operating costs, and improved operational efficiency. However, in the daily production process of the substation, it is still necessary to manually maintain and overhaul the substation, and some high-voltage areas in the substation do not allow non-related p...

AI Technical Summary

Problems solved by technology

However, in the daily production process of the substation, it is still necessary to manually maintain and overhaul the substation, and some high-voltage areas in the substation do not allow non-related personnel to enter, so in order to improve the ability of the substation to control the safety of on-site workers, it is necessary Identify and locate personnel in substations

[0003] The scene in the substation is complex, and there will be interlacing and occlusion between the video background and the personnel detection target, resulting in unclear outline features of the personnel detection target, and because the light intensity in the substation varies greatly, it is difficult to use a fixed threshold for the characteristics of the personnel target and the complex background Segmentation makes it more difficult to detect human targets, so it is necessary to design a human target detection method for complex background substation scenarios

Images