Laboratory personnel unsafe behavior safety inspection method based on machine vision

Abstract

The invention provides a laboratory personnel unsafe behavior safety inspection method based on machine vision. The method comprises the following steps: firstly, determining the identity of laboratory personnel and whether the laboratory personnel meet laboratory safety admission conditions by adopting a face recognition system; using an image sensor for collecting video images of the laboratorypersonnel; after image processing, extracting a human body behavior feature set, and determining whether the laboratory personnel performs a unsafe operation or has unsafe behaviors or not according to the human body behavior feature set; if yes, a searching for a corresponding unsafe behavior term number in a laboratory safety inspection standard library database, and giving the content description of the unsafe behaviors; generating a safety inspection table of the violation behaviors of the laboratory personnel, sending the safety inspection table to the management personnel, generating a formal safety inspection report after confirmation, sending the formal safety inspection report to the violation personnel and the related management personnel, and carrying out warning and responsibility rectification; and continuously supervising and inspecting the unsafe behaviors of the violation personnel within a specified rectification period until the rectification is finished.

Description

technical field [0001] The invention belongs to the technical field of laboratory safety involved in the discipline of safety engineering, and specifically relates to a method of automatically identifying unsafe behaviors of laboratory personnel by using machine vision, pattern recognition, expert systems and image processing technologies, and promptly issuing warnings and ordering rectification method. Background technique [0002] Laboratory accidents are generally caused by the joint action of human-object-environmental factors. At present, more than 50% of laboratory safety accidents are caused by people's unsafe behaviors. Traditionally, the security inspection of laboratory personnel relies on security inspectors to conduct on-site inspections or remote identification and monitoring through video. Its accuracy and timeliness are limited to the professional technical ability, experience accumulation and sense of responsibility of safety inspectors, and it is difficult...

AI Technical Summary

Problems solved by technology

Its accuracy and timeliness are limited to the professional technical ability, experience accumulation and sense of responsibility of safety inspectors, and it is difficult to implement dynamic, accurate, comprehensive and efficient automated safety inspections on unsafe behaviors of laboratory personnel

Images