A robust video object segmentation scheme with prestored background information

In this paper, we propose a robust video object extraction algorithm using background subtraction. The algorithm combines two statistical features of the background subtracted images to extract the objects. This method can produce satisfying results with pixel-wise precision. Furthermore, it is robust to the effects of camera noise and the changing of lighting condition. The proposed method is useful in applications with a still background which can be captured and analyzed beforehand, such as virtual conferencing and video surveillance