Abstract
The use of adaptive Gaussian mixtures to model the colour distributions of objects is described. These models are used to perform robust, real-time tracking under varying illumination, viewing geometry and camera parameters. Observed log-likelihood measurements were used to perform selective adaptation.
Original language | English |
---|---|
Title of host publication | Computer Vision — ACCV'98 |
Subtitle of host publication | Third Asian Conference on Computer Vision Hong Kong, China, January 8–10, 1998 Proceedings |
Editors | Roland Chin, Ting-Chuen Pong |
Place of Publication | Berlin |
Publisher | Springer |
Pages | 615-622 |
Number of pages | 8 |
Volume | 1 |
ISBN (Electronic) | 9783540696698 |
ISBN (Print) | 9783540639305 |
DOIs | |
Publication status | Published - 1998 |
Event | 3rd Asian Conference on Computer Vision - Hong Kong University of Science & Technology (HKUST), Hong Kong, Hong Kong Duration: 8 Jan 1998 → 10 Jan 1998 http://www.cse.ust.hk/accv98/ |
Publication series
Name | Lecture notes in computer science |
---|---|
Publisher | Springer |
Volume | 1351 |
ISSN (Print) | 0302-9743 |
Conference
Conference | 3rd Asian Conference on Computer Vision |
---|---|
Abbreviated title | ACCV'98 |
Country/Territory | Hong Kong |
City | Hong Kong |
Period | 8/01/98 → 10/01/98 |
Internet address |