Method and device for detecting strenuous motion in video

Abstract

The invention relates to the field of video processing, and discloses a method and a device for detecting a strenuous motion in a video. According to the method and the device, a motion corner point light stream in a video frame is detected and calculated; a motion entropy is calculated according to the motion corner point light stream; and whether the strenuous motion exists is judged. By adopting a motion corner point, a motion can be effectively captured without being influenced by a corner point on the background, and noise interference can be reduced; furthermore, only the motion corner point light stream is required to be calculated, and light streams of non-motion pixels are not required to be calculated, so that the calculation amount is greatly reduced; for each motion communication region, all the motion corner point light streams in the motion communication region are counted, so that the motion entropy of the motion communication region can be calculated; and therefore, whether the strenuous motion exists is judged.

Description

technical field [0001] The invention relates to the field of video processing, in particular to detection technology for violent motion in video monitoring. Background technique [0002] The detection and tracking of moving objects is to find the position of the moving object of interest in each image of a sequence of images, so as to achieve the purpose of detection, tracking, behavior analysis and recognition. The theory and implementation of object detection and tracking have been extensively and deeply researched, and remarkable results have been achieved. However, most of the existing target detection and tracking systems are limited to specific application backgrounds, and the behavior analysis and recognition algorithms still need to be further studied and deepened. [0003] Chinese patent CN 101751678A provides a severe motion detection method, which mainly includes the following steps: acquiring video frame images, and performing grayscale processing on the images;...

AI Technical Summary

Problems solved by technology

[0004] 1 The optical flow algorithm has a large amount of calculation, and it is basically impossible to realize real-time on the general hardware platform at present; this method calculates the optical flow globally, which requires a large amount of calculation and is not easy to promote;

[0005] 2 This method generates a violent motion history map based on the direction change of a single pixel point, which is prone to large noise interference, resulting in false detection;

[0006] 3 In many actual monitoring scenarios, there will be a depth of field, that is, the phenomenon that the target is far away and the distance is large. In this kind of scene, it is obviously not suitable to apply the same motion entropy calculation method in the distance and near, which will cause the target to be far away. Prone to false positives and distant false negatives

Images