Behavior identification method and device

Abstract

The invention provides a behavior identification method and device. The method is applied to a computing device which comprises an identification model for carrying out behavior identification. The method comprises a step of carrying out image processing on collected visible light image and infrared image to obtain a target area to be tracked, a step of detecting whether the target area to be tracked comprises pedestrians or not, a step of tracking the pedestrians if so, and detecting pedestrian edges in a tracking process to obtain an area of pedestrians to be identified from the target area to be tracked, and a step of inputting the area of the pedestrians to be identified into the identification model to obtain a behavior identification result of the pedestrians. Thus, the behavior identification of the pedestrians in the images is carried out.

Description

technical field [0001] The present invention relates to the technical field of computer vision, and in particular, to a method and device for behavior recognition. Background technique [0002] With the improvement of people's safety awareness and the increase of various emergencies (for example, fire) faced by society, safety monitoring has been paid more and more attention by society, institutions and individuals. The traditional security monitoring system mainly realizes the monitoring of the scene through manual monitoring, and does not have the ability to monitor the environment in real time and actively. [0003] For example, in the event of a fire, the cause of the fire can only be found through video later. However, traditional methods cannot effectively predict the behavior characteristics of people in the scene, and cannot judge whether the monitored personnel have illegal or illegal behaviors, and cannot achieve real-time monitoring and alarm purposes. Therefore...

AI Technical Summary

Problems solved by technology

The traditional security monitoring system mainly realizes the monitoring of the scene through manual monitoring, and does not have the ability of real-time and active environmental monitoring

[0003] For example, in the event of a fire, the cause of the fire can only be found through video. Fires include fires caused by human-initiated fires, electrical or equipment aging, etc.

However, traditional methods cannot effectively predict the behavior characteristics of personnel in the scene, cannot judge whether the monitored personnel have illegal or irregular behaviors, and cannot achieve the purpose of real-time monitoring and alarming

Images