Scene Analysis for Human Silhoutte Extraction

This paper affords a method to extract human silhouette from video scenes using background modeling and subtraction method. The main objective of this work is to develop an algorithm that is capable of detecting the presence of human based on motion and post-morphology processes to extract the foreground pixels from its background thus separating the human silhouette for extraction purpose and in turn, the extracted silhouette information can later be used for other purposes such as traffic monitoring and analysis, human tracking and monitoring, video surveillance etc. Results obtained thus far clearly indicate that the developed algorithm achieves its objective and successfully extract human silhouette from the analyzed video scenes.