Robust vehicle tracking based on Scale Invariant Feature Transform

Author

Tu, Qiu ; Xu, Yiping ; Zhou, Manli

Author_Institution

Dept. of Electron. & Inf. Eng., Huazhong Univ. of Sci. & Technol., Wuhan

fYear

2008

fDate

20-23 June 2008

Firstpage

86

Lastpage

90

Abstract

Vehicle tracking is a challenging problem in Intelligent Transport System. This paper presents a vehicle tracking approach combining blob based tracking and feature based tracking. First objects are detected as blobs using codebook(CB) algorithm and scale invariant feature transform(SIFT) features are extracted from the blobs. Then vehicles are tracked by using SIFT to match the vehicles frame-by-frame. The method is robust to partial occlusion, partial affine distortion, changing in illumination, shape and size of vehicle. The experiments show that it is effective for vehicle tracking.

Keywords

automated highways; feature extraction; object detection; codebook algorithm; feature based tracking; intelligent transport system; object detection; partial afflne distortion; robust vehicle tracking; scale invariant feature transform; Clustering algorithms; Feature extraction; Intelligent systems; Interference; Lighting; Object detection; Robustness; Shape; Vehicles; Video surveillance;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Automation, 2008. ICIA 2008. International Conference on

Conference_Location

Changsha

Print_ISBN

978-1-4244-2183-1

Electronic_ISBN

978-1-4244-2184-8

Type

conf

DOI

10.1109/ICINFA.2008.4607973

Filename

4607973