A background subtraction algorithm for a pan-tilt camera

This paper is concerned with the detection of moving objects using a pan-tilt camera and a background subtraction algorithm. Traditionally, motion compensation is performed on the current image to align its pixels with their background models in previous frames. Pixel misalignment however can occur during motion compensation. Although this problem can be alleviated by using pixel motion such as the optic flow, motion information itself can be inaccurate and, together with pixel misalignment, contributes to false positive foreground detection. In this paper, we exploit the fact that pixel misalignment and inaccurate optic flow tend not to occur simultaneously for a pixel. Consequently, we can substantially improve the performance of the background subtraction algorithm by evaluating the marginal statistical models of appearance and motion separately - rather than jointly - in classifying whether a pixel is foreground. We will use experiments to validate our approach and establish its superiority to other competing algorithms in the literature.