AI front-end transformer substation inspection video real-time identification method and system

Abstract

The invention provides an AI front-end transformer substation inspection video real-time identification method and system. The system comprises at least one fixed point camera, at least one robot camera and an AI analysis module. The robot camera is installed on the transformer substation inspection robot and used for collecting equipment and environment video information in an inspection route coverage area of the transformer substation inspection robot. The fixed-point cameras are distributed in a substation equipment area and used for collecting equipment and environment video information in an area where robot inspection cannot reach in the substation equipment area; and the AI analysis module is used for processing the substation inspection videos acquired by the fixed point camera and the robot camera in real time, identifying and outputting equipment position information, analyzing and processing equipment image information in the acquired videos, and realizing real-time tracking of equipment states at the front end. According to the technical scheme, the AI analysis module is located at the front end, a front-end data processing mode is adopted, the collected video images do not need to be transmitted to the background, and the timeliness of data processing is achieved.

Description

technical field [0001] The disclosure belongs to the technical field of video processing, and in particular relates to an AI front-end-based real-time identification method and system for substation inspection video. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] The existing substation inspection system generally adopts the combined inspection mode of robot inspection and fixed-point monitoring. The robot inspection video and fixed-point monitoring video are sent back to the background server in the station through the network, and are manually reviewed by substation operation and maintenance personnel. The workload is heavy, the labor intensity is high, and it is greatly affected by subjective factors such as personnel's professional ability and sense of responsibility. Omissions and misreports of important video events often occur. ...

AI Technical Summary

Problems solved by technology

[0003] The existing substation inspection system generally adopts the combined inspection mode of robot inspection and fixed-point monitoring. The robot inspection video and fixed-point monitoring video are sent back to the background server in the station through the network, and are manually reviewed by substation operation and maintenance personnel. The workload is heavy, the labor intensity is high, and it is greatly affected by subjective factors such as personnel's business ability and sense of responsibility. There are often omissions and misreports of important video events.

[0004] With the application of artificial intelligence technology, some automatic video analysis systems running on the background server side have appeared, but currently they are limited to simple analysis functions such as intrusion in some areas, dynamic object detection, etc., and a large amount of data is sent back to the background analysis method , requires the guarantee of a stable and high-speed network channel, and there is a time delay in data transmission, there must be untimely video analysis, and it is impossible to detect abnormalities in the inspection video in time, so that the safety of equipment operation and personnel operations in the substation cannot be effectively guaranteed

Images