Region tracking via level set PDEs without motion computation
- 7 August 2002
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 24 (7) , 947-961
- https://doi.org/10.1109/tpami.2002.1017621
Abstract
We propose an approach to region tracking that is derived from a Bayesian formulation. The novelty of the approach is twofold. First, no motion field or motion parameters need to be computed. This removes a major burden since accurate motion computation has been and remains a challenging problem and the quality of region tracking algorithms based on motion critically depends on the computed motion fields and parameters. The second novelty of this approach, is that very little a priori information about the region being tracked is used in the algorithm. In particular, unlike numerous tracking algorithms, no assumption is made on the strength of the intensity edges of the boundary of the region being tracked, nor is its shape assumed to be of a certain parametric form. The problem of region tracking is formulated as a Bayesian estimation problem and the resulting tracking algorithm is expressed as a level set partial differential equation. We present further extensions to this partial differential equation, allowing the possibility of including additional information in the tracking process, such as priors on the region's intensity boundaries and we present the details of the numerical implementation. Very promising experimental results are provided.Keywords
This publication has 13 references indexed in Scilit:
- Recovering and characterizing image features using an efficient model based approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Morphing active contours: a geometric approach to topology-independent image segmentation and trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A comparative evaluation of algorithms for fast computation of level set PDEs with applications to motion segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Mean shift and optimal prediction for efficient object trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Topology-independent region tracking with level setsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Geodesic active contours and level sets for the detection and tracking of moving objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Embedding Gestalt laws in Markov random fieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Tracking line segmentsPublished by Springer Nature ,1990
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988
- Finding Trajectories of Feature Points in a Monocular Image SequencePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987