Loading...
Please wait, while we are loading the content...
Similar Documents
Skin Color-Based Video Segmentation under Time-Varying Illumination (2004)
| Content Provider | CiteSeerX |
|---|---|
| Author | Sclaroff, Stan Athitsos, Vassilis Sigal, Leonid |
| Abstract | A novel approach for real-time skin segmentation in video sequences is described. The ap-proach enables reliable skin segmentation despite wide variation in illumination during track-ing. An explicit second order Markov model is used to predict evolution of the skin-color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and predictions of the Markov model. The evolution of the skin-color distribution at each frame is parameterized by translation, scaling and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and re-sampling the histogram. The parameters of the discrete-time dynamic Markov model are esti-mated using Maximum Likelihood Estimation, and also evolve over time. The accuracy of the new dynamic skin color segmentation algorithm is compared to that obtained via a static color model. Segmentation accuracy is evaluated using labeled ground-truth video sequences taken from staged experiments and popular movies. An overall increase in segmentation accuracy of up to 24 % is observed in 17 out of 21 test sequences. In all but one case the skin-color classi-fication rates for our system were higher, with background classification rates comparable to those of the static segmentation. |
| File Format | |
| Journal | IEEE Trans. Pattern Analysis and Machine Intelligence |
| Publisher Date | 2004-01-01 |
| Access Restriction | Open |
| Content Type | Text |
