Using results from robust Kalman filtering, we present a new Kalman filter-based snake model for tracking of nonrigid objects in combined spatio-velocity space. The proposed model is the stochastic version of the velocity snake which is an active contour model for combined tracking of position and velocity of nonrigid boundaries. The proposed model uses image gradient and optical flow measurements along the contour as system measurements. An optical-flow based measurement error is used to detect and reject image measurements which correspond to image clutter or to other objects. The method was applied to object tracking of both rigid and nonrigid objects, resulting in good tracking results and robustness to image clutter, occlusions and numerical noise.
Robust tracking with spatio-velocity snakes: Kalman filtering approach
1998-01-01
1120985 byte
Conference paper
Electronic Resource
English
Robust Tracking with Spatio-Velocity Snakes: Kalman Filtering Approach
British Library Conference Proceedings | 1998
|Robust car tracking using Kalman filtering and Bayesian templates [3207-38]
British Library Conference Proceedings | 1998
|Particle Velocity Estimation Using Kalman Filtering
IEEE | 1985
|Robust car tracking using Kalman filtering and Bayesian templates [3207-38]
British Library Conference Proceedings | 1998
|