Retro-gradation detection method based on video and system thereof

Abstract

The invention relates to the field of image understanding in computer vision, and discloses a retro-gradation detection method based on a video and a system thereof. In the invention, an angular point is extracted in a frame difference image, angular point optical flow tracking is performed in an original image, and generation of retro-gradation is judged according to an optical flow characteristic vector decomposition motion mode so that robustness of retro-gradation detection is enhanced, and probability of omission report and false report in the retro-gradation detection in a complex scene is effectively reduced. Different motion modes are obtained by aiming at motion areas in the video via an iteration clustering algorithm so that the motion modes corresponding to different moving objects in the complex scene can be effectively extracted and analysis of the retro-gradation detection is facilitated. Movement of image blocks in a larger range can be dealt with by adopting an idea of pyramid hierarchy so that the method is applicable to application scenes of the retro-gradation detection.

Description

technical field [0001] The invention relates to the field of image understanding in computer vision, in particular to video-based retrograde detection technology. Background technique [0002] Video-based retrograde detection is a kind of crowd abnormal behavior detection. In the current society, security issues have become a growing concern. The behavior of crowds, including crowd gathering, fighting, and movement trajectory trends, has gradually become a new topic of concern for computer vision researchers. The behavior of the crowd has good guiding significance for the work of the public security department. For example: the public security department can use video technology to detect crowd gathering or fights to prevent riots from escalating; the traffic department uses the statistics of crowd movement trajectories in the area for a period of time to make some decision-making guidance, such as increasing traffic police in congested places and evacuating traffic wait....

AI Technical Summary

Problems solved by technology

The retrograde detection in the crowd also has its application scenarios. It is as big as the pilgrimage to Mecca in Saudi Arabia. It is because some people do not follow the established route, which causes the crowd to trample on the tragedy. , is not only a manifestation of lack of public morality, but also a potential danger

[0003] In the existing technology, most of the considerations are to use the motion trajectory of the human body or the motion trajectory of the human joints to detect abnormal behaviors. This kind of tracking-based method can often achieve good results in simple scenes, but in complex scenes, the crowd density is relatively large. , when the number of people is large, due to the failure of tracking, it will bring a lot of false positives and false positives

Images