Multi-region variable-scale 3D-HOF based surveillance video anomaly detection method

Abstract

The invention discloses a multi-region variable-scale 3D-HOF based surveillance video anomaly detection method, which comprises the steps of firstly acquiring surveillance video to serve as input, performing partition processing on the video, then extracting variable-scale 3D-HOF features and optical flow direction information entropy in each sub-region, combining the variable-scale 3D-HOF features and the optical flow direction information entropy into final detection features, finally learning an initial sparse combination set in each sub-region by using a sparse combination learning algorithm, judging whether the new data is abnormal or not through a reconstruction error, and updating the sparse combination set online by using normal data. The application of the invention not only solves a problem of perspective distortion existing in the surveillance video, but also makes full use of the difference of motion information in different optical flow amplitude intervals, and can acquiremore accurate moving speed information. The method disclosed by the invention is applicable to anomaly detection for the surveillance video, low in calculation complexity, accurate in detection result and good in algorithm robustness. The method has extensive applications in the technical field of video analysis.

Description

technical field [0001] The invention belongs to the technical field of video analysis, and in particular relates to a monitoring video anomaly detection method based on multi-area variable-scale 3D-HOF, which is used for detecting abnormal objects and motion patterns in the monitoring video. Background technique [0002] Surveillance video anomaly detection is an important research direction in the field of video analysis technology. It has broad application prospects in riot detection in public places, fare evasion detection at subway station entrances, fire warning, and intrusion monitoring. [0003] At present, most anomaly detection methods learn the model of the normal appearance and motion pattern of the object from the training video, and perform anomaly detection based on the established model, but rarely consider the position information of the object in the surveillance video on the appearance and motion pattern. Impact. Due to the perspective distortion in the vi...

AI Technical Summary

Problems solved by technology

[0005] The problem to be solved by the present invention is: in the abnormal detection technology of surveillance video, if the problem of perspective deformation is not considered, the abnormal motion in the distance will be misjudged as the normal motion in the vicinity, resulting in missed detection; while the existing solution to the problem of perspective deformation The anomaly detection method does not consider the relationship between the whole and the part in the video, which will lead to false detection

Images