Abnormal behavior detection method and abnormal behavior detection device based fused characteristics

Abstract

The invention provides an abnormal behavior detection method and an abnormal behavior detection device based fused characteristics. The method comprises steps that, according to a detection tracking processing result of a motion target in a to-be-detected video, a behavior type of the motion target is determined; multi-dimensional characteristics of the motion target are extracted, including a pixel point change degree, a pixel point arrangement tightness degree, an integral shape, a frame image similarity degree, motion characteristics, position characteristics and form characteristics; the multi-dimensional characteristics are analyzed and processed according to a characteristic fusion model corresponding to the behavior type, whether the motion target has abnormal behaviors is determined according to the processing result; according to innovative characteristics of the multiple abnormal behaviors, algorithm robustness and stability can be effectively improved, according to the characteristic fusion model acquired through learning and training large-scale abnormal behaviors, the multi-dimensional characteristics are analyzed and processed, problems of algorithm overfitting and insufficient fitting can be effectively avoided, the method is suitable for multiple types of complex application scenes, time cost and manpower cost are greatly saved, and the method has high popularization values.

Description

technical field [0001] The invention relates to the field of video surveillance, in particular to a fusion feature-based abnormal behavior detection method and device. Background technique [0002] At present, many public places such as banks, shopping malls, stations, and traffic intersections are equipped with video surveillance devices, which are used to collect video images in preset monitoring areas in real time, and send the above video images to the monitoring center to form a monitoring system. However, many actual monitoring tasks corresponding to the above-mentioned monitoring system still need to be completed manually, and the existing video monitoring system usually only stores the collected video images, and does not perform any processing on the video images, so These uninterpreted (that is, processed) video images can usually only be used for post-event evidence collection, and cannot give full play to the real-time and initiative of monitoring. [0003] As t...

AI Technical Summary

Problems solved by technology

[0005] The inventor found in the research that the above-mentioned single feature often has great limitations in practical application, which may easily lead to missed or false positives of abnormal behaviors

Images