Static human body detection method based on video monitoring

Abstract

The invention discloses a static human body detection method based on video monitoring. The method comprises: using a Faster-RCNN deep learning network model and a background elimination method to carry out target extraction on a real-time video image, obtaining two coordinate parameters of the same target frame at the same moment; analyzing the two coordinate parameters; judging whether the target is in a static state or not; the static target cannot be detected due to the fact that the static target is fused into the background in background subtraction modeling, so that when the target detected by the Faster-RCNN deep learning network model is not extracted in the background subtraction, indicating that the target is in a static state, judging that the target is static, and giving an alarm. A static human body is recognized through video monitoring, an alarm is given for abnormal conditions that an operator stays still for a long time, falls to the ground and faints, the monitoringpersonnel can check or rescue in time, the workload of the monitoring personnel for watching a monitoring video for a long time is effectively reduced, the working efficiency is improved, and the labor cost is saved.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to a method for detecting a still human body based on video monitoring. Background technique [0002] In recent years, with the rapid development of the economy, information technology has gradually spread to all walks of life, especially video surveillance has been widely used in social production and life, and it has played a huge role in ensuring the safety of life and property and maintaining social order. effect. Enterprises use technologies such as network, computer and video surveillance to efficiently manage personnel and production processes, and the detection of the safety status of operating personnel has become an urgent problem to be solved in the production safety of enterprises. [0003] At present, many methods have been proposed for pedestrian detection, which can be roughly divided into three categories: methods based on global features, me...

AI Technical Summary

Problems solved by technology

[0003] At present, many methods have been proposed for pedestrian detection, which can be roughly divided into three categories: the method based on global features, the method based on human body parts, and the method based on stereo vision. High recognition rate, however, these methods are suitable for detecting moving human bodies, and lack of detection of stationary human bodies

At present, most enterprises install cameras in the workshops to monitor the safety status of workers. The monitors are in the stage of human judgment. Long-term monitoring will increase their workload, and they are prone to visual fatigue. Rescue workers who are in an abnormal state such as coma or coma

Images