Adaptive abnormal crowd behavior analysis method

Abstract

The invention discloses an adaptive abnormal crowd behavior analysis method, which is used for analyzing crowd behaviors in a video image. The method comprises the following steps of performing streak line calculation on the video image; calculating a streak line flow; detecting abnormal behaviors; performing foreground detection on the video image of abnormal crowd behaviors; performing adaptive crowd density estimation comprising pixel-counting-based density estimation and texture-analysis-based density estimation, and finally dividing estimated density into four density levels, i.e. a low density level, a medium density level, a high density level and an ultrahigh density level, thereby finishing grading the abnormal crowd behaviors. According to the method, the concepts of streak line and streak line flow are introduced to analyze whether a crowd in the video image is abnormal or not; the method has the advantage of detection accuracy; the densities of crowds involved in the abnormal crowd behaviors in different density scenarios are estimated in an adaptive way, and the detected abnormal crowd behaviors are graded by using density estimation results as main characteristics; the method is used for accurately grading the abnormal behaviors (such as mass brawl) in crowded public places, and giving alarms.

Description

technical field [0001] The invention relates to a method for analyzing group abnormal behavior based on intelligent video monitoring in the field of public security, in particular to an adaptive group abnormal behavior analysis method based on a pulse line model, which belongs to the field of machine vision and intelligent information processing. Background technique [0002] The occurrence of abnormal group behavior will pose a hazard to social public security, and the harmfulness of different levels of abnormal group behavior to social public security is not the same, and the corresponding attention and sensitivity are also different. When group abnormal behavior occurs, different measures should be taken for different levels of abnormal behavior. For example, when the population density in the scene where an abnormal event occurs is low (or the number of groups is small), it can be considered that the attention and sensitivity of the event are relatively low; however, whe...

AI Technical Summary

Problems solved by technology

However, these methods may not be able to detect abnormal behavior in the corresponding crowd scene when the video has factors such as low resolution, jitter, or the group movement speed in the video is too fast or too slow

In 2012, Hassner et al. published the article "Violent flows: Real-time detection of violent crowd behavior" on CVPRW (International Computer Vision and Pattern Recog

Images