Method for analyzing and predicting large-scale crowd density

Abstract

The invention provides a method for analyzing and predicting large-scale crowd density. The method comprises the following steps: performing crowd density analysis on an input video based on crowd density analysis with statistical characteristics, and acquiring a crowd density value of a single monitoring point; realizing the mutual conversion of the crowd density and the number of people through multi-stage linear fit; calculating the flow speed and the flow direction of crowd in the single monitoring point by an optical flow method, and acquiring the information of the flow speed and the flow direction of the crowd in the single monitoring point; and establishing a structure of a directed graph according to the relation between the spatial positions of each of monitoring points and the flow direction and the flow speed of the crowd, and performing the prediction of the number of the people and the crowd density in a period of time on an import monitoring hub node. Due to the method, the crowd density and the distribution of the number of the people in a large area can be automatically monitored in real time, and the prediction of the crowd density and the number of the people can be performed on an import place; and the information provided by the method has important reference value for a crowd monitoring department.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a large-scale crowd density analysis and prediction method. Background technique [0002] With the increasing enrichment of human social life, large-scale social activities such as sports games, exhibitions and theatrical performances are often held. While these large-scale social activities bring happiness to people, they also bring potential safety hazards. When tens of thousands of crowds gather, once an emergency occurs, the crowd panics, and a stampede is likely to occur, endangering people's lives. In the traditional public area video surveillance system, the monitoring personnel often watch the display screen in the monitoring room to find abnormal situations. There are many disadvantages in such manual monitoring mode. First of all, when there are many monitoring points, due to the limited monitoring personnel, it often leads to failure to detect dangerous ...

AI Technical Summary

Problems solved by technology

[0004] 1) The obtained crowd density is a decimal between 0 and 1, indicating the degree of crowding, and the specific number of people concerned cannot be obtained

[0005] 2) It is impossible to get the flow rate and flow information of the crowd

[0006] 3) It does not involve the prediction of crowd density in key hub areas

Images