Method for estimating number of people in public place based on two cameras

Abstract

The invention discloses a method for estimating the number of people in a public place based on two cameras. According to the method, at first a multivariate linear model which is used for estimating is set up, a training sample set of the multivariate linear model is acquired in a scene, and then model parameters are acquired through the analysis of multiple linear regression, so that a complete multiple linear regression equation is acquired. Only corresponding characters are extracted from a surveillance video image to be substituted into the set multiple linear regression equation so that people flow density estimation can be carried out in real time. According to the method for estimating the number of people in the public place, the estimation of the number of people can be carried out according to a multivariate linear relation of prospect pixels, face area pixels, prospect outer / inner edge pixels and people flow density, the method for estimating the number of people in the public place based on the two cameras is suitable for a low-density crowd, and estimation accuracy under the condition of a high-density crowd is improved.

Description

technical field [0001] The invention relates to a method for estimating the number of people in a public place with dual cameras, which can be widely used in places such as subways and stations for monitoring and estimating the density of people. Background technique [0002] With the rapid development of the economy and the improvement of people's living standards, more and more people are pouring into cities. For many public facilities in the city, such as shopping malls and subways, there will be a peak flow of people in a short period of time. In recent years, stampede casualties have also occurred in various places due to overcrowded flow of people. Therefore, it is very important to conduct real-time statistics and analysis of passenger flow density in these places. In addition, crowd density estimation technology plays an important role in the fields of public safety, control and service of transportation hubs such as airports and stations, and can also provide a bas...

AI Technical Summary

Problems solved by technology

Among them, the method based on pixel analysis is based on the approximate linear relationship between the crowd density and the number of pixels, and the estimated result of the crowd density can be directly obtained, but it cannot solve the problem of overlapping of high-density crowds, because the larger the crowd density, the greater the overlap. The more serious, the crowd density and the number of pixels at this time are no longer the previous linear relationship

The method based on texture analysis is based on the fact that there is a corresponding relationship between the density of the crowd and the thickness of the texture pattern, which can well solve the problem of overlapping occlusion of high-density crowds, but there is a large error in low-density monitoring

The method based on individual target analysis is mainly to identify and track targets to distinguish different target individuals, but when the crowd density is too large, target segmentation is very difficult, and this method is very complicated and difficult to meet real-time requirements

Images