The approach proposed in this section requires a preprocessing phase to filter out image areas changing in time. The results of this initial filtering are fed into the classifier to improve the detection rate and reduce the probability of misclassification. Most existing algorithms for detection of changing regions in video sequences do not consider illumination changes inherent to exterior conditions (Fathy, 1995), (Skifstad, 1989), (Zeljkovic, 2003). For this reason the algorithms frequently fail when applied to natural outdoor scenes. The model presented in this section initially assumes that the background is static. However, this limitation has been released in the actual implementation by assuming that global motion parameters of background objects are known. Motion compensation is applied using conventional approaches. Under this assumption the outcome of the preprocessing technique described below is the same if global motion parameters are used to compensate global changes of rigid background objects.