Feature clustering for vehicle detection and tracking in road traffic surveillance

Author

Yang, Jun ; Wang, Yang ; Ye, Getian ; Sowmya, Arcot ; Zhang, Bang ; Xu, Jie

Author_Institution

Sch. of Comput. Sci. & Eng., Univ. of New South Wales, Sydney, NSW, Australia

fYear

2009

fDate

7-10 Nov. 2009

Firstpage

1145

Lastpage

1148

Abstract

In this paper, we formulate the feature clustering problem for vehicle detection and tracking as a general MAP problem and solve it using MCMC. The proposed approach exhibits two advantages over existing methods: general Bayesian model can handle arbitrary objective functions and MCMC guarantees global optimal solution. Our algorithm is validated on real-world traffic video sequences, and is shown to outperform the state-of-the-art approach.

Keywords

Bayes methods; Markov processes; Monte Carlo methods; image sequences; object detection; road traffic; traffic engineering computing; Markov chain Monte Carlo; feature clustering; general Bayesian model; general MAP problem; objective functions; road traffic surveillance; traffic video sequences; vehicle detection; vehicle tracking; Australia; Bayesian methods; Clustering algorithms; Computer science; Object detection; Roads; Shape; Surveillance; Trajectory; Vehicle detection; Clustering methods; MAP estimation; Monte Carlo methods; Object detection; Tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2009 16th IEEE International Conference on

Conference_Location

Cairo

ISSN

1522-4880

Print_ISBN

978-1-4244-5653-6

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2009.5413526

Filename

5413526