Title :
Tracking through changes in scale
Author :
Lankton, Shawn ; Malcolm, James ; Nakhmani, Arie ; Tannenbaum, Allen
Author_Institution :
Georgia Inst. of Technol., Atlanta, GA
Abstract :
We propose a tracking system that is especially well-suited to tracking targets which change drastically in size or appearance. To accomplish this, we employ a fast, two phase template matching algorithm along with a periodic template update method. The template matching step ensures accurate localization while the template update scheme allows the target model to change over time along with the appearance of the target. Furthermore, the algorithm can deliver real-time results even when targets are very large. We demonstrate the proposed method with good results on several sequences showing targets which exhibit large changes in size, shape, and appearance.
Keywords :
image matching; image registration; image sequences; target tracking; image registration; image sequence; periodic template update method; target tracking; template matching algorithm; template matching step; Bandwidth; Cameras; Histograms; Kernel; Parameter estimation; Robustness; Shape; Target tracking; Video sequences; Object tracking; registration; scale space; template update;
Conference_Titel :
Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-1765-0
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2008.4711736