Global motion identification for image sequence analysis and coding
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2825-2828 vol.4
- https://doi.org/10.1109/icassp.1991.150990
Abstract
A new method is proposed to estimate global motion parameters from an unusual initial dense velocity field. The authors first want to obtain a compact representation of a dense velocity field and compute a spatiotemporal motion-based segmentation; then these parameters are used as initial values of a cost-function minimization algorithm and applied within a motion compensation loop for image sequence coding. Promising results are obtained on real TV image sequences. A compact motion representation is generated at each frame, and a quite interpretable qualitative and quantitative motion field is synthesized. Moreover, high quality of reconstruction and motion interpretation is obtained using the minimization stage.Keywords
This publication has 5 references indexed in Scilit:
- Global motion identification for image sequence analysis and codingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Optic flowVision Research, 1986
- Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving ObjectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1985
- Improved Pel-Recursive Motion CompensationIEEE Transactions on Communications, 1984
- Determining optical flowArtificial Intelligence, 1981