A color histogram based people tracking system

Author

Lu, Wenmiao ; Tan, Yap-Peng

Author_Institution

Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst., Singapore

Volume

2

fYear

2001

fDate

6-9 May 2001

Firstpage

137

Abstract

A system using color histogram based recognition technique is presented for tracking of moving people. The proposed system aims to resolve the identity of each tracked person after an occlusion, which is a common problem encountered in tracking of multiple objects. The system recognizes and keeps track of moving people with the aid of their color histograms. To make the recognition more robust against change of background illumination, a shadow-removal scheme is designed to select only those pixels belonging to the tracked people for constructing their color histograms. Experimental results of real video data are reported to show the efficacy of the proposed system

Keywords

image colour analysis; image recognition; image sequences; object recognition; optical tracking; background illumination; color histogram; multiple objects; occlusion; people tracking system; real video data; recognition technique; shadow-removal scheme; Histograms; Image converters; Layout; Lighting; Man machine systems; Motion detection; Robustness; Shape; Surveillance; Tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2001. ISCAS 2001. The 2001 IEEE International Symposium on

Conference_Location

Sydney, NSW

Print_ISBN

0-7803-6685-9

Type

conf

DOI

10.1109/ISCAS.2001.921025

Filename

921025