Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

6-2000

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 oriented 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.

Keywords

Motion analysis, Cameras, Image analysis, Image motion analysis, Histograms, Tensile stress, Partitioning algorithms, Indexing, Layout, Algorithm design and analysis

Discipline

Computer Sciences | Numerical Analysis and Scientific Computing | Theory and Algorithms

Research Areas

Intelligent Systems and Optimization

Publication

2000 IEEE Conference on Computer Vision and Pattern Recognition CVPR: Hilton Head, SC, June 15: Proceedings

Volume

2

First Page

768

Last Page

773

ISBN

9780769506623

Identifier

10.1109/CVPR.2000.854952

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/CVPR.2000.854952

Share

COinS