ABSTRACT Title of dissertation: ROBUST TECHNIQUES FOR VISUAL SURVEILLANCE

The work described here aims at improving the performance of three building blocks of visual surveillance systems: foreground detection, object tracking and event detection. First, a new background subtraction algorithm is presented for foreground de-tection. The background model is built with a set of codewords for every pixel. The codeword contains the pixel’s principle color and a tangent vector that represents the color variation at that pixel. As the scene illumination changes, a pixel’s color is predicted using a linear model of the codeword and the codeword, in turn, is updated using the new observation. We carried out a number of experiments on se-quences that have extensive lighting change and compare with previously developed algorithms. Second, we describe a multi-resolution tracking framework developed with ef-ficiency and robustness in mind. Efficiency is achieved by processing low resolution data whenever possible. Robustness results from multiple level coarse-to-fine search-ing in the tracking state space. We combine sequential filtering both in time an