1 January 1998 Locating and recognizing road vehicles
Author Affiliations +
Abstract
This paper concerns model-based vision for road traffic scene analysis. A traffic vision system is described. The three main modules of the system are movement detection, vehicle localization and discrimination, and vehicle tracking. This paper outlines our work on the localization and discrimination module. Emphasis is on recovering 3-D poses of road vehicles in given image regions. Two classes of algorithms are described, one based on symbolic image features (line segments), and the other simply on image intensity gradients. A priori knowledge about traffic scenes and vehicles is exploited to improve the performance and efficiency of the algorithms. The algorithms are tested extensively with routine outdoor traffic images, and examples are included to demonstrate their principles.
Tieniu Tan, "Locating and recognizing road vehicles," Optical Engineering 37(1), (1 January 1998). https://doi.org/10.1117/1.601607 . Submission:
JOURNAL ARTICLE
6 PAGES


SHARE
RELATED CONTENT

Model-Based Vision: Using Cues To Select Hypotheses
Proceedings of SPIE (November 17 1986)
Fast algorithms for object orientation determination
Proceedings of SPIE (June 16 1995)
View interpolation and synthesis by KLT feature tracker
Proceedings of SPIE (January 17 2005)
Model-based tracking using a real-time laser rangefinder
Proceedings of SPIE (November 29 1993)
Model-based matching using elliptical features
Proceedings of SPIE (May 24 1996)
Visual robot guidance for an insertion task
Proceedings of SPIE (August 11 1995)

Back to Top