The Library
Multiresolution Gaussian mixture models for visual motion estimation
Tools
Tools
Tools
UNSPECIFIED (2001) Multiresolution Gaussian mixture models for visual motion estimation. In: International Conference on Image Processing (ICIP 2001), OCT 07-10, 2001, THESSALONIKI, GREECE.
Full text not available from this repository.Abstract
This paper introduces a new generalisation of scale-space and pyramids, which combines statistical modelling with a spatial representation. The representation uses the familiar concept of multiple resolutions, but applied to a Gaussian mixture representation of the image - hence the title MGMM. It is shown that MGMM can approximate any probability density and can adapt to smooth motions. After a brief presentation of the theory, it is shown how MGMM can be applied to the estimation of visual motion.
| Item Type: | Conference Item (UNSPECIFIED) |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Journal or Publication Title: | 2001 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL II, PROCEEDINGS |
| Publisher: | IEEE |
| ISBN: | 0-7803-6725-1 |
| Date: | 2001 |
| Number of Pages: | 4 |
| Page Range: | pp. 921-924 |
| Publication Status: | Published |
| Title of Event: | International Conference on Image Processing (ICIP 2001) |
| Location of Event: | THESSALONIKI, GREECE |
| Date(s) of Event: | OCT 07-10, 2001 |
| URI: | http://wrap.warwick.ac.uk/id/eprint/10310 |
Data sourced from Thomson Reuters' Web of Knowledge
Actions (login required)
 |
View Item |
