A novel method of crowd estimation in public locations

Author

Fei, Tang ; SunDong, Liu ; Sen, Guo

Author_Institution

Shenzhen Inst. of Inf. Technol., Shenzhen, China

fYear

2009

fDate

13-14 Dec. 2009

Firstpage

339

Lastpage

342

Abstract

A novel method of crowd estimation is proposed in this paper: Firstly, surveillance image is divided into bit planes by OSTU algorithm, the pixel ratio of foreground to background and complexity of bit planes are taken as feature vectors of crowd estimation. The degree of crowd density of the scene is classified into several grades, BP neural network is used for training and then the classification model is constructed, through which the estimation of crowd density can be obtained. Experiments were taken based on video of two real scenes, the result show that this proposed approach is able to judge the levels of congestion with accuracy higher than 85%.

Keywords

backpropagation; image classification; neural nets; surveillance; video signal processing; BP neural network; OSTU algorithm; bit planes; classification model; crowd density; crowd estimation; feature vector; pixel ratio; public location; surveillance image; video; Biomedical engineering; Image processing; Image reconstruction; Information technology; Layout; Neural networks; Pixel; Robustness; Statistics; Surveillance; OSTU algorithm; bit planes; crowd estimation; neural network1.Introduction;

fLanguage

English

Publisher

ieee

Conference_Titel

BioMedical Information Engineering, 2009. FBIE 2009. International Conference on Future

Conference_Location

Sanya

Print_ISBN

978-1-4244-4690-2

Electronic_ISBN

978-1-4244-4692-6

Type

conf

DOI

10.1109/FBIE.2009.5405848

Filename

5405848