Motion characterization by temporal slices analysis
Research output: Journal Publications and Reviews › RGC 22 - Publication in policy or professional journal
Author(s)
Detail(s)
| Original language | English |
|---|---|
| Pages (from-to) | 768-773 |
| Journal / Publication | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
| Volume | 2 |
| Publication status | Published - 2000 |
| Externally published | Yes |
Conference
| Title | CVPR '2000: IEEE Conference on Computer Vision and Pattern Recognition |
|---|---|
| City | Hilton Head Island, SC, USA |
| Period | 13 - 15 June 2000 |
Link(s)
Abstract
This paper describes an approach to characterize camera and object motions based on the analysis of spatio-temporal image volumes. In the spatio-temporal slices of image volumes, motion is depicted as oriented patterns. We propose a tensor histogram computation algorithm to represent these patterns. The motion trajectories in a histogram are tracked to describe both the camera and object motions. In addition, we exploit the similarity of the temporal slices in a volume to reliably partition a volume into motion tractable units.
Citation Format(s)
Motion characterization by temporal slices analysis. / Ngo, Chong Wah; Pong, Ting Chuen; Zhang, Hong Jiang et al.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, 2000, p. 768-773.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, 2000, p. 768-773.
Research output: Journal Publications and Reviews › RGC 22 - Publication in policy or professional journal
