TR2009-061
Regressed Importance Sampling on Manifolds for Efficient Object Tracking
-
- , "Regressed Importance Sampling on Manifolds for Efficient Object Tracking", IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), DOI: 10.1109/AVSS.2009.95, September 2009, pp. 406-411.BibTeX TR2009-061 PDF
- @inproceedings{Porikli2009sep,
- author = {Porikli, F.M. and Pan, P.},
- title = {Regressed Importance Sampling on Manifolds for Efficient Object Tracking},
- booktitle = {IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)},
- year = 2009,
- pages = {406--411},
- month = sep,
- doi = {10.1109/AVSS.2009.95},
- url = {https://www.merl.com/publications/TR2009-061}
- }
- , "Regressed Importance Sampling on Manifolds for Efficient Object Tracking", IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), DOI: 10.1109/AVSS.2009.95, September 2009, pp. 406-411.
-
Research Areas:
Abstract:
In this paper, a new integrated particle filter is proposed for video object tracking. After particles are generated by importance sampling, each particle is regressed on the transformation space where the mapping function is learned offline by regression on pose manifold using Lie algebra, leading to a more effective allocation of particles. Experimental results on synthetic and real sequences clearly demonstrated the improved pose (affine) tracking performance of the proposed method compared with the original regression tracker and particle filters.
Related News & Events
-
NEWS AVSS 2009: publication by MERL researchers and others Date: September 2, 2009
Where: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
Research Area: Machine LearningBrief- The paper "Regressed Importance Sampling on Manifolds for Efficient Object Tracking" by Porikli, F.M. and Pan, P. was presented at the IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).