Abnormity behavior detection method in combination with depth data and abnormity behavior system

Abstract

The invention provides an abnormity behavior detection method in combination with the depth data and an abnormity behavior system. The method comprises steps that a monitoring video image of a target area is acquired, a scene background model on the basis of the monitoring video image is established, the motion target prospect of a two-dimensional image is extracted, and communication domain analysis and target segmentation are carried out; a depth background graph of an original visual angle is acquired according to the monitoring video image, a motion target prospect of a three-dimensional image is extracted from the depth background graph, and two times of target prospect segmentation on the original visual angle and a downward-view visual angle after projection transformation is carried out; the effective person target information is extracted; according to the acquired person target information, tracking and behavior analysis on person targets are realized, whether behaviors of the person targets are abnormal can be determined according to preset abnormal behavior rules, if yes, alarm starts. Through the method and the system, abnormal events and abnormal behaviors are automatically identified, detection precision of the abnormal events is improved, and timely response can be realized on the unattended condition.

Description

technical field [0001] The invention relates to the technical field of computer depth vision, in particular to an abnormal behavior detection method and system combined with depth data. Background technique [0002] The traditional abnormal behavior is mainly analyzed based on video images, and its methods mainly include: model-based methods, preset feature-based methods and classifier-based methods. There are different defects in the above-mentioned several methods respectively: [0003] (1) The model-based method emphasizes the detection of abnormal events rather than classification. It establishes a certain model for normal events, and judges whether it is an abnormal event by comparing the degree of conformity between the event to be detected and the model. [0004] (2) The detection based on preset features mainly analyzes the trajectory of the target, and misjudges non-preset behaviors as abnormal. [0005] (3) The classifier-based method needs to extract image stati...

AI Technical Summary

Problems solved by technology

However, this method lacks the analysis of the deep features of the image, which leads to poor stability of the target recognition results, which in turn affects the accuracy of abnormal behavior detection

Images