Particle Video
Abstract
This project presents a new approach to motion estimation in video. We
represent video motion using a set of particles. Each particle is an
image point sample with a long-duration trajectory and other
properties. To optimize these particles, we measure point-based
matching along the particle trajectories and distortion between the
particles. The resulting motion representation is useful for a
variety of applications and cannot be directly obtained using existing
methods such as optical flow or feature tracking. We demonstrate the
algorithm on challenging real-world videos that include complex scene
geometry, multiple types of occlusion, regions with low texture, and
non-rigid deformations.
References
Peter Sand and Seth Teller, Particle Video: Long-Range Motion Estimation using Point Trajectories, IJCV (issue: best papers of CVPR 2006), 2008
Peter Sand and Seth Teller, Particle Video: Long-Range Motion Estimation using Point Trajectories, CVPR, 2006
(CVPR Talk Slides, Videos)
Peter Sand, Long-Range Video Motion Estimation using Point
Trajectories, PhD Thesis, 2006
Code
A simplified particle video implementation can be downloaded here. This is an alpha release. Please let us know if you have any trouble with it.
Data