Object Tracking in Video Based on SIFT with Normalized Cross Correlation

Detection and tracking of moving objects in video is the first relevant step of information extraction in many computer vision applications. In this paper a tracking algorithm based on Scale Invariant Feature Transform (SIFT), features for a given image sequence is developed. For each point feature extracted using SIFT algorithm a descriptor is computed using information from its neighborhood. Computation of feature points matching throughout image sequences has been done based on Normalized Cross Correlation. Experimental results, obtained from image sequences that capture scaling of various geometrical kind objects, reveal the performances of the tracking algorithm.