The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.05 - May (2003 vol.25)
pp: 604-615
ABSTRACT
<p><b>Abstract</b>—A new contour tracking algorithm is presented. Tracking is posed as a matching problem between curves constructed out of edges in the image, and some shape space describing the class of objects of interest. The main contributions of the paper are to present an algorithm which solves this problem accurately and efficiently, in a provable manner. In particular, the algorithm's efficiency derives from a novel tree-search algorithm through the shape space, which allows for much of the shape space to be explored with very little effort. This latter property makes the algorithm effective in highly cluttered scenes, as is demonstrated in an experimental comparison with a condensation tracker.</p>
INDEX TERMS
Contour tracking, tree-search, hybrid optimization, approximation algorithm, compact manifold.
CITATION
Daniel Freedman, "Effective Tracking through Tree-Search", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.25, no. 5, pp. 604-615, May 2003, doi:10.1109/TPAMI.2003.1195994
18 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool