PhD forum: correlation coefficient based template matching for indoor people tracking
Junzhi Guan, Peter Van Hese, Jorge Oswaldo Niño-Castañeda, Sebastian Gruenwedel, Dirk Van Haerenborgh, Dimitri Van Cauwelaert, Peter Veelaert, Wilfried R. Philips · Ghent University Academic Bibliography (Ghent University) · 2012
Abstract—One of the most popular methods to extract information from an image sequence is template matching. The principle of template matching is tracking a certain feature or target over time based on the comparison of the content of each frame with a simple template. In this article, we propose an correlation coefficient based template matching which is invariant to linear intensity distortions to do correction or verification of our existing indoor people tracking system.