Robust Silhouette Extraction Technique Using Background Subtraction

摘要: We propose a robust method to extract silhouettes of foreground objects from color video sequences. To cope with various changes in the background, background is modeled as generalized Gaussian Family distributions and updated by selective running average static pixel observation. All pixels input image are classified into four initial regions using subtraction multiple thresholds, after which shadow eliminated components. The final silhouette extracted refining region morphological processes. have verified that proposed algorithm works very well situations through experiments. Keyword Foreground segmentation, Silhouette extraction, Background subtraction, Generalized model