Detection and Tracking over Image Pyramids using Lucas and Kanade Algorithm

摘要

Image registration finds a variety of application in computer vision, such as image matching for stereo vision, pattern recognition and motion analysis. This paper focuses on pyramid LK algorithm, which tracks starting from highest level of an image pyramid (lowest detail) and working down to lower levels (finer detail). Tracking over image pyramids allows track points of interest despite large disparity between photos.