GPU-Based Foreground-Background Segmentation Using an Extended Colinearity Criterion
Swiss Federal Institute of Technology (ETH), Computer Vision Lab, Zurich, Switzerland
Proceedings of Vision, Modeling, and Visualization (VMV) 2005
We present 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 integrated 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 colinearity criterion with compensation for dark foreground and background areas and thus improving overall performance.
February 26, 2011 by hgpu