The invention discloses an aAbnormal behavior detection method based on a space-time automatic encoder

Abstract

The invention discloses an abnormal behavior detection method based on a space-time automatic encoder, and belongs to the technical field of image processing and mode recognition. The method comprisesthe steps of firstly obtaining a video image of a to-be-detected area; i; inputting the optical flow information and the RGB information of the video into a space-time auto-encoder respectively; p; passing through a 3D convolution layer in an automatic encoder; a; a pooling layer, an LSTM layer and a deconvolution layer, DERIVING RECONSTRUCTION INFORMATION, T, the method comprises the steps thatinput information is compared with reconstructed information, abnormal scores are obtained according to an abnormal scoring formula, t, then the two abnormal scores are fused to obtain a comprehensiveabnormal score, t, the comprehensive abnormal score is compared with a threshold value, whether abnormal behaviors exist or not and the occurrence time of abnormal conditions are judged, and the higher the abnormal score is, t, the higher the probability of occurrence of the abnormal conditions is. According to the invention, t, through the space-time automatic encoder fusing multi-modal input information, abnormal behaviors in crowds are detected in public areas such as banks, and early warning is sent to security personnel, so that emergencies such as major abnormal events are reduced.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and in particular relates to a method for detecting abnormal behavior based on a spatio-temporal automatic encoder. Background technique [0002] In recent years, violations of important public places such as the banking and financial industries have occurred from time to time in my country by different means, causing varying degrees of loss and injury to state property and people's lives. Starting from this, abnormal behavior detection in public places has become a research hotspot in the current security prevention and control system, and more and more experts and scholars are devoted to this field. [0003] To solve this problem, researchers have proposed a variety of abnormal behavior monitoring methods, which can be roughly divided into traditional methods, supervised learning methods and unsupervised learning methods according to different methods. Traditio...

AI Technical Summary

Problems solved by technology

[0004] In unsupervised learning, human body motion information is estimated only by image RGB information. This method is greatly affected by light and shadow, and the accuracy is limited in crowded places. When there are obstacles or crowds overlap, the detection effect is not good.

[0005] Due to the various defects of the existing algorithms, the effect is not ideal in practical applications, and the algorithm needs to be improved

Images