An adaptive statistical features modeling tracking algorithm based on locally statistical ROI

In this paper, a novel method for object tracking proposes an adaptive modeling algorithm based on locally statistical ROI algorithm and statistical analysis of multilateral features algorithm. The main improvement of the proposed system with respect to the others present in literature is that we do not use any a priori knowledge about how objects look like. This no a-priori model has been carried out by computing a model that takes into account the statistical behavior of the most important objects features over the whole video sequence. The most important region of interest features can be detected by using the locally statistical ROI algorithm. Moreover, an adaptive mechanism allows us to reset the statistical model creation when such a model is too much dissimilar from the real blobs features. The experiment result show that the average rate of accuracy is higher at least 15%, and the time complexity was lower at least 3% than the similar algorithms. The performance is higher than others.