Back to Search
Start Over
Particle Video: Long-Range Motion Estimation Using Point Trajectories.
- Source :
- International Journal of Computer Vision; Oct2008, Vol. 80 Issue 1, p72-91, 20p, 5 Color Photographs, 2 Diagrams, 5 Charts, 4 Graphs
- Publication Year :
- 2008
-
Abstract
- This paper describes 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 particle trajectories we measure appearance consistency 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. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09205691
- Volume :
- 80
- Issue :
- 1
- Database :
- Complementary Index
- Journal :
- International Journal of Computer Vision
- Publication Type :
- Academic Journal
- Accession number :
- 34114677
- Full Text :
- https://doi.org/10.1007/s11263-008-0136-6