Efficient Adaptive Combination of Histograms for Real-Time Tracking

Autor: J. Denzler, Ch. Gräßl, B. Deutsch, F. Bajramovic
Jazyk: angličtina
Rok vydání: 2008
Předmět:
Zdroj: EURASIP Journal on Image and Video Processing, Vol 2008 (2008)
Druh dokumentu: article
ISSN: 1687-5176
1687-5281
DOI: 10.1155/2008/528297
Popis: We quantitatively compare two template-based tracking algorithms, Hager's method and the hyperplane tracker, and three histogram-based methods, the mean-shift tracker, two trust-region trackers, and the CONDENSATION tracker. We perform systematic experiments on large test sequences available to the public. As a second contribution, we present an extension to the promising first two histogram-based trackers: a framework which uses a weighted combination of more than one feature histogram for tracking. We also suggest three weight adaptation mechanisms, which adjust the feature weights during tracking. The resulting new algorithms are included in the quantitative evaluation. All algorithms are able to track a moving object on moving background in real time on standard PC hardware.
Databáze: Directory of Open Access Journals
Externí odkaz: