Moving cast shadow elimination for robust vehicle extraction based on 2D joint vehicle/shadow models

Author

Yoneyama, Akio ; Yeh, Chia H. ; Kuo, C. C Jay

Author_Institution

Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA, USA

fYear

2003

fDate

21-22 July 2003

Firstpage

229

Lastpage

236

Abstract

A new algorithm to eliminate moving cast shadow for robust vehicle detection and extraction in a vision-based highway monitoring system is investigated. The proposed algorithm is based on a simplified 2D vehicle/shadow model of six types projected on to a 2D image plane. Parameters of the joint 2D vehicle/shadow models can be estimated from the input video without light source and camera calibration information. Simulations are performed to verify that the proposed technique is effective for vision-based highway surveillance systems.

Keywords

feature extraction; image motion analysis; object detection; road vehicles; surveillance; video signal processing; 2D joint vehicle/shadow models; camera calibration; highway monitoring system; highway surveillance systems; intelligent transportation systems; light source information; moving cast shadow elimination; vehicle detection; vehicle extraction; video processing; Calibration; Cameras; Data mining; Intelligent vehicles; Light sources; Monitoring; Road transportation; Robustness; Surveillance; Vehicle detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Video and Signal Based Surveillance, 2003. Proceedings. IEEE Conference on

Print_ISBN

0-7695-1971-7

Type

conf

DOI

10.1109/AVSS.2003.1217926

Filename

1217926