The Community for Technology Leaders
Computer Vision, IEEE International Conference on (2007)
Rio de Janeiro, Brazil
Oct. 14, 2007 to Oct. 21, 2007
ISBN: 978-1-4244-1630-1
pp: 1-8
Qi Zhao , Department of Computer Engineering, University of California at Santa Cruz, 1156 High Street, Santa Cruz, CA 95064. zhaoqi@soe.ucsc.edu
Shane Brennan , Department of Computer Engineering, University of California at Santa Cruz, 1156 High Street, Santa Cruz, CA 95064. shanerb@soe.ucsc.edu
Hai Tao , Department of Computer Engineering, University of California at Santa Cruz, 1156 High Street, Santa Cruz, CA 95064. tao@soe.ucsc.edu
ABSTRACT
Illumination changes cause object appearance to change drastically and many existing tracking algorithms lack the capability to handle this problem. The Earth Mover's Distance (EMD) is a similarity measure that is more robust against illumination changes. However, EMD is computationally expensive and we therefore propose the Differential EMD (DEMD) algorithm which computes the derivative of the EMD with respect to the object location so that the EMD does not need to be computed for every location in the tracking window. The fast differential formula is derived based on the sensitivity analysis of the simplex method as applied to the EMD formula. To further reduce the computation, signatures, i.e., variable-size descriptions of distributions, are employed as an object representation. The new algorithm models local background scenes as well as foreground objects to handle scale changes in a principled way. Extensive quantitative evaluation of the proposed algorithm has been carried out using benchmark sequences and the improvement over the standard Mean Shift tracker is demonstrated.
INDEX TERMS
CITATION

S. Brennan, H. Tao and Q. Zhao, "Differential EMD Tracking," 2007 11th IEEE International Conference on Computer Vision(ICCV), Rio de Janeiro, 2007, pp. 1-8.
doi:10.1109/ICCV.2007.4409033
93 ms
(Ver 3.3 (11022016))