Unscented feature tracking

  title={Unscented feature tracking},
  author={Leyza Baldo Dorini and Siome Goldenstein},
  journal={Computer Vision and Image Understanding},
Accurate feature tracking is the foundation of many high level tasks in computer vision, such as 3D reconstruction and motion analysis. Although there are many feature tracking algorithms, most of them do not maintain information about the error of the data being tracked. Also, due to the difficulty and spatial locality of the problem, existing methods can generate grossly incorrect correspondences, making outlier rejection an essential post-processing step. We propose a new generic framework… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 28 references

Bundle adjustment – a modern synthesis

  • P. Torr, A. Zisserman, S. Maybank
  • in: Proceedings of the International Workshop on…
  • 1999
Highly Influential
3 Excerpts

An Invitation to 3D Vision-From Images to Geometric Models

  • Y. Ma, S. Soatto, J. Kosecka, S. Sastry
  • Springer
  • 2004
2 Excerpts

Similar Papers

Loading similar papers…