Segmentation of hybrid motions via hybrid quadratic surface analysis

@article{Rao2005SegmentationOH,
  title={Segmentation of hybrid motions via hybrid quadratic surface analysis},
  author={Shankar R. Rao and Allen Y. Yang and Andrew Wagner and Yi Ma},
  journal={Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1},
  year={2005},
  volume={1},
  pages={2-9 Vol. 1}
}
In this paper, we investigate the mathematical problem underlying segmentation of hybrid motions: given a series of tracked feature correspondences between two (perspective) images, we seek to segment and estimate multiple motions, possibly of different types (e.g., affine, epipolar, and homography). In order to accomplish this task, we cast the problem into a more general mathematical framework of segmenting data samples drawn from a mixture of linear subspaces and quadratic surfaces. The… CONTINUE READING

From This Paper

Topics from this paper.