Method for classifying crowd density degrees in video image

Abstract

The invention provides a method for classifying crowd density degrees in a video image. The method comprises the steps that firstly, an interest region is selected from the video image and is subjected to image block division and analysis according to a perspective model; secondly, multi-scale textural features are obtained for each image block; the video image is subjected to clustering analysis, a classifier model based on confidence degree analysis is established, multiple binary classifiers are optimized and combined by designing error correction output codes based on a binary-tree classification idea, confidence samples are extracted, and SVM binary classifiers are trained; finally, a channel transmission model is utilized to conduct decoding, and the crowd density degrees which the samples belong to are obtained according to the posterior probability maximum rule. According to the method, classification is conducted on the premise that sample sets and features are identical, the accuracy and generalization performance are both superior to those of a transmission classification model, and an idea is provided for solutions to various classification problems represented by crowd density estimation.

Description

technical field [0001] The invention relates to the technical field of intelligent video analysis and computer vision, in particular to a method for classifying crowd density levels in video images. Background technique [0002] Crowd density level estimation is based on computer vision and pattern recognition technology, through the analysis and calculation of surveillance images or videos, the quantitative level of crowd density can be obtained. Crowd density information is a powerful basis for large-scale crowd monitoring and management. It can provide shopping malls or retail outlets with crowd density information distributed in different time periods inside the mall, and assist the management to allocate services and management resources reasonably. It can be widely used in the access passages of bus stations, passenger transport, railway stations, airports and other facilities and crowd monitoring in important areas. It can obtain accurate data on the number and distri...

AI Technical Summary

Problems solved by technology

In China CNKI, Wanfang, VIP, China Patent and other databases, relevant papers and patents on current abnormal group event detection are searched. CN101751553A, CN101587537A and CN102044073A respectively propose a method for crowd density analysis and prediction, but there are the following disadvantages: 1 ) cannot adapt to scene changes, and the model parameters need to be learned repeatedly; 2) In the case of high crowd density and serious occlusion, the linear relationship no longer holds true, resulting in increased error; 3) The method based on foreground detection can only be used for moving crowds

Images