Robust tracking of stochastic deformable models in long image sequences
- 17 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 88-92
- https://doi.org/10.1109/icip.1994.413882
Abstract
In this paper, we describe a method for the temporal trackingof stochastic deformable models in long image sequences.The object representation relies on a hierarchical statisticaldescription of the deformations applied to a template. Abayesian estimate of the deformations is obtained by maximizinga highly non-linear joint probability distribution.Time consuming global (stochastic) optimization techniquesare necessary to obtain optimal solutions unless a good initialguess is available. A ...Keywords
This publication has 12 references indexed in Scilit:
- Fast segmentation, tracking, and analysis of deformable objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Tracking complex primitives in an image sequencePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Region-Based Tracking Using Affine Motion Models in Long Image SequencesCVGIP: Image Understanding, 1994
- A framework for spatiotemporal control in the tracking of visual contoursInternational Journal of Computer Vision, 1993
- Shape and nonrigid motion estimation through physics-based synthesisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Feature extraction from faces using deformable templatesInternational Journal of Computer Vision, 1992
- Training Models of Shape from Sets of ExamplesPublished by British Machine Vision Association and Society for Pattern Recognition ,1992
- Recovery of nonrigid motion and structurePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Tracking line segmentsPublished by Springer Nature ,1990
- Inference about the change-point from cumulative sum testsBiometrika, 1971