Abstract
We discuss some of the practical issues concerning the use of mixtures of Gaussians for background segmentation in outdoor scenes, including the choice of parameters. Different covariance representations and their performance impact are examined. In addition, we propose a simple, yet efficient method for coping with sudden global illumination changes based on smoothing brightness and contrast changes over time. All of the discussed methods are capable of running in real time at reasonable resolution on current generation PCs.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004 |
| Pages | 423-428 |
| Number of pages | 6 |
| State | Published - Dec 1 2004 |
| Event | Proceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004 - Washington, DC, United States Duration: Oct 3 2004 → Oct 6 2004 |
Other
| Other | Proceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004 |
|---|---|
| Country/Territory | United States |
| City | Washington, DC |
| Period | 10/3/04 → 10/6/04 |
Keywords
- Background segmentation
- Illumination monitoring
- Mixture models