Share Email Print
cover

Proceedings Paper

Novel method for handling vehicle occlusion in visual traffic surveillance
Author(s): Clement Chun Cheong Pang; William Wai Leung Lam; Nelson Hon Ching Yung
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a novel algorithm for handling occlusion in visual traffic surveillance (VTS) by geometrically splitting the model that has been fitted onto the composite binary vehicle mask of two occluded vehicles. The proposed algorithm consists of a critical points detection step, a critical points clustering step and a model partition step using the vanishing point of the road. The critical points detection step detects the major critical points on the contour of the binary vehicle mask. The critical points clustering step selects the best critical points among the detected critical points as the reference points for the model partition. The model partition step partitions the model by exploiting the information of the vanishing point of the road and the selected critical points. The proposed algorithm was tested on a number of real traffic image sequences, and has demonstrated that it can successfully partition the model that has been fitted onto two occluded vehicles. To evaluate the accuracy, the dimensions of each individual vehicle are estimated based on the partitioned model. The estimation accuracies in vehicle width, length and height are 95.5%, 93.4% and 97.7% respectively.

Paper Details

Date Published: 28 May 2003
PDF: 11 pages
Proc. SPIE 5014, Image Processing: Algorithms and Systems II, (28 May 2003); doi: 10.1117/12.473096
Show Author Affiliations
Clement Chun Cheong Pang, The Univ. of Hong Kong (China)
William Wai Leung Lam, The Univ. of Hong Kong (China)
Nelson Hon Ching Yung, The Univ. of Hong Kong (China)


Published in SPIE Proceedings Vol. 5014:
Image Processing: Algorithms and Systems II
Edward R. Dougherty; Jaakko T. Astola; Karen O. Egiazarian, Editor(s)

© SPIE. Terms of Use
Back to Top