We introduce the concept of a spatiogram, which is a generalization of a histogram that includes potentially higher order moments. A histogram is a zeroth-order spatiogram, while second-order spatiograms contain spatial means and covariances for each histogram bin. This spatial information still allows quite general transformations, as in a histogram, but captures a richer description of the target to increase robustness in tracking. We show how to use spatiograms in kernel-based trackers, deriving a mean shift procedure in which individual pixels vote not only for the amount of shift but also for its direction. Experiments show improved tracking results compared with histograms, using both mean shift and exhaustive local search.
Spatiograms versus histograms for region-based tracking
2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) ; 2 ; 1158-1163 vol. 2
2005-01-01
233704 byte
Conference paper
Electronic Resource
English
Fast tracking using edge histograms [3028-11]
British Library Conference Proceedings | 1997
|Online visual tracking with histograms and articulating blocks
British Library Online Contents | 2010
|Mean Shift tracking with multiple reference color histograms
British Library Online Contents | 2010
|NTRS | 1979
|