A method for detecting a sleeping behavior of a person on duty based on a convolutional neural network

Abstract

The invention discloses a convolutional neural network-based method for detecting the sleep behavior of a person on duty, and the method comprises the steps: 1, collecting a sleep figure picture as apositive sample picture set; And collecting character pictures which do not sleep as a negative sample picture set. 2, using a YOLO v3 algorithm to facilitate positive and negative sample picture sets, obtaining a character area, and forming positive and negative sample data sets; 3, dividing the positive and negative sample data sets into a training data set and a test data set; And 4, constructing the convolutional neural network based on the ShuffleNet v2 model. And 5, training the convolutional neural network model by using the training data set. And 6, deploying the trained convolutionalneural network model in a visual analysis system, analyzing video stream data acquired by video monitoring equipment, and detecting the duty condition of a person on duty. According to the technical scheme, the target detection technology and the behavior recognition technology based on the convolutional neural network are fused according to the characteristics of the sleep behavior, and the analysis result is accurate and effective.

Description

technical field [0001] The invention relates to the technical field of personnel behavior analysis, in particular to a method for detecting sleeping behavior of personnel on duty based on a convolutional neural network. Background technique [0002] In the petrochemical industry, safe production is directly related to the life and property of every employee, as well as the survival and development of the enterprise. At present, all relevant enterprises have achieved all-round coverage of video surveillance in the factory area. At the same time, they have set up duty rooms and equipped corresponding duty personnel, trying to establish an effective safety production mechanism through the combination of human defense and technical defense. In a large factory area, due to the large area, the on-duty personnel are responsible for a large number of video surveillance equipment, which increases the work intensity. Especially at night, it is difficult for the on-duty personnel to e...

AI Technical Summary

Problems solved by technology

This method is time-consuming and labor-intensive, which not only causes a waste of manpower, but also is very inefficient, and cannot completely eliminate accidents

Images