Electric power hot-line work safety detection method based on deep learning algorithm

Abstract

The invention discloses an electric power hot-line work safety detection method based on a deep learning algorithm. Firstly, a human body reference object which is regular in shape, obvious in featureand easy to detect is arranged on work clothes of an operator; a configuration file of the camera is read, and the actual height H of the human body reference object, the human body movement radius r1 and the equipment parameters are obtained; a historical monitoring video of the camera is extracted, and a human body target detection model and a human body reference object detection model are trained through the historical monitoring video; finally, human body target tracking is achieved through the detection model, a moving human body target is found out, safety distance detection is completed, and therefore hot-line work safety detection of operators is completed.

Description

technical field [0001] The invention belongs to the technical field of safety detection of electric live work, and more specifically, relates to a safety detection method of electric live work based on a deep learning algorithm. Background technique [0002] Power plants, substations and other places, as key links in the production and distribution of national power resources, play an increasingly important role in the entire power production system. The safety of production operations is naturally an important part of the normal operation of the entire power production system. There are many high-risk and high-voltage production environments in live electric work sites. There are many live equipment on site, and the internal structure is complex, which is prone to safety accidents. [0003] At present, the traditional video monitoring system only has simple functions such as real-time display and historical video data playback, and does not have an alarm function for abnorm...

AI Technical Summary

Problems solved by technology

However, in the process of traditional electric power production, the staff only abide by various production safety regulations by memory, such as the scope of certain dangerous areas, the safety distance of charged objects, and the specifications of various operations. Once negligent, it may lead to serious consequences, and there is no backing for safe operation

The traditional indoor positioning technology is difficult to meet the accuracy requirements, and cannot realize the specific positioning of the staff and the reminder of the safe working distance

Although the specially developed positioning equipment can meet the accuracy requirements, it is still limited by portability and high cost and cannot be used in mass production

Images