Loading...
Please wait, while we are loading the content...
Similar Documents
Real-Time, GPU-based Foreground-Background Segmentation
| Content Provider | Semantic Scholar |
|---|---|
| Author | Grießer, Andreas |
| Copyright Year | 2005 |
| Abstract | This report presents a GPU-based foreground-background segmentation that processes image sequences in less than 4ms per frame. Change detection wrt. the background is based on a color similarity test in a small pixel neighbourhood, and is integrate d into a Bayesian estimation framework. An iterative MRF-based model is applied, exploiting parallelism on modern graphics hardware. Resulting segmentation exhibits compactness and smoothness in foreground areas as well as for inter-frame temporal contiguity. Further refinements extend the coline arity criterion with compensation for dark foreground and background areas and thus improving overall performance. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.gpucomputing.net/sites/default/files/papers/3083/eth_biwi_00365.pdf |
| Alternate Webpage(s) | http://www.vision.ee.ethz.ch/en/publications/papers/techreports/eth_biwi_00365.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |