Translator Disclaimer
30 July 1998 Model-based car tracking through the integration of search and estimation
Author Affiliations +
Abstract
In this work we address the problem of detecting and tracking moving vehicles in image sequences on highway scenes recorded by a moving camera. The proposed method uses a simple parameterized vehicle shape (object-model) and vehicle motion model for an intra-frame matching and a recursive estimation of position, orientation, velocity and shape parameters of the tracked vehicle. In our approach the vehicle detection/identification (matching) is tackled in an optimization framework, implemented as a hypothesis generation and testing method, in which the current set of hypotheses (vehicle shape) are evaluated and modified until a maximum cost instantiation is found. The estimation of the vehicle position, orientation and velocity is based on a ground plane motion constraint and a Kalman Filtering approach. Results on real world highway scenes are presented and open problems are discussed.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hichem Sahli, Mark J. W. Mertens, and Jan P.H. Cornelis "Model-based car tracking through the integration of search and estimation", Proc. SPIE 3364, Enhanced and Synthetic Vision 1998, (30 July 1998); https://doi.org/10.1117/12.317465
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Model-Based Vision: Using Cues To Select Hypotheses
Proceedings of SPIE (November 16 1986)
Recognizing parameterized three-dimensional objects
Proceedings of SPIE (October 02 1994)
Model-based multiple-sensor dynamic scene interpretation
Proceedings of SPIE (January 31 1992)
Feature selection for object tracking in traffic scenes
Proceedings of SPIE (January 05 1995)

Back to Top