A Method of People Gathering Detection Based on Video Image

Abstract

The invention discloses a method for detecting people gathering based on video images, which includes: performing background learning of a monitoring area according to continuous video images to obtain a static current background image of the monitoring area; and selecting n consecutive video frames from the video images Each video frame in is subjected to a pixel-by-pixel background difference operation and an image segmentation operation, and an accumulation operation is performed on the segmented binary images corresponding to continuous video frames to obtain an accumulated image matrix; threshold segmentation is performed on the accumulated image matrix to obtain a segmented image; Segment the noise in the image, fill in the holes, and form the target image; perform pixel count statistics on the connected regions with a pixel value of 1 in the target image, and set the number of pixels in the connected region as the area of ​​the connected region; according to each connected region in the target image area and the preset area threshold to determine whether there is a crowd gathering area. By using the above method, the fast detection of people gathering phenomenon can be realized with less calculation cost.

Description

technical field [0001] The invention relates to camera technology, in particular to a method for detecting people gathering based on video images. Background technique [0002] In the video surveillance in the prior art, when people gather in the surveillance scene, the management risk and control difficulty of the surveillance area will increase, and it is necessary to adopt a different scheme from the normal state to manage the surveillance scene. Due to the huge deployment of modern video surveillance systems and the large number of cameras, it takes a lot of manpower to monitor all the cameras for a long time if people gather in all monitoring scenes, which is not only labor-intensive, but also likely to cause false positives. Therefore, through the means of video analysis, it becomes the demand of the intelligent monitoring system to automatically detect the phenomenon of people gathering in the monitoring scene. [0003] In the video-based moving target detection and ...

AI Technical Summary

Problems solved by technology

This method needs to calculate the density of people in all areas when detecting people gathering, and the calculation efficiency is low. The counting process is inaccurate due to complex people movement phenomena such as occlusion, intersection, and companionship.

Images