Spatiograms versus Histograms for Region-Based Tracking
作者： S.T. Birchfield , S. Rangarajan
关键词: Histogram 、 Search engine indexing 、 Mean-shift 、 Histogram matching 、 Pattern recognition 、 Computer vision 、 Pixel 、 Mathematics 、 Artificial intelligence 、 Kernel (image processing) 、 Spatial analysis 、 Probability distribution
摘要: We introduce the concept of a spatiogram, which is generalization histogram that includes potentially higher order moments. A zeroth-order while second-order spatiograms contain spatial means and covariances for each bin. This information still allows quite general transformations, as in histogram, but captures richer description target to increase robustness tracking. show how use kernel-based trackers, deriving mean shift procedure individual pixels vote not only amount also its direction. Experiments improved tracking results compared with histograms, using both exhaustive local search.
acm.org 
sci-hub.se 参考文章(11)
Avinash C. Kak, Azriel Rosenfeld, Digital Picture Processing ,(1976)
Ying Wu, T.S. Huang, A co-inference approach to robust visual tracking international conference on computer vision. ,vol. 2, pp. 26- 33 ,(2001) , 10.1109/ICCV.2001.937590
R.T. Collins, Mean-shift blob tracking through scale space computer vision and pattern recognition. ,vol. 2, pp. 234- 240 ,(2003) , 10.1109/CVPR.2003.1211475
Z. Zivkovic, B. Krose, An EM-like algorithm for color-histogram-based object tracking computer vision and pattern recognition. ,vol. 1, pp. 798- 803 ,(2004) , 10.1109/CVPR.2004.1315113
Jianbo Shi, Tomasi, Good features to track computer vision and pattern recognition. pp. 593- 600 ,(1994) , 10.1109/CVPR.1994.323794
J. Ho, Kuang-Chih Lee, Ming-Hsuan Yang, D. Kriegman, Visual tracking using learned linear subspaces computer vision and pattern recognition. ,vol. 1, pp. 782- 789 ,(2004) , 10.1109/CVPR.2004.1315111
L. Sigal, S. Sclaroff, V. Athitsos, Estimation and prediction of evolving color distributions for skin segmentation under varying illumination computer vision and pattern recognition. ,vol. 2, pp. 2152- 2159 ,(2000) , 10.1109/CVPR.2000.854764
D. Comaniciu, V. Ramesh, P. Meer, Kernel-based object tracking IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 25, pp. 564- 575 ,(2003) , 10.1109/TPAMI.2003.1195991
G.D. Hager, M. Dewan, C.V. Stewart, Multiple kernel tracking with SSD computer vision and pattern recognition. ,vol. 1, pp. 790- 797 ,(2004) , 10.1109/CVPR.2004.1315112
S. Birchfield, Elliptical head tracking using intensity gradients and color histograms computer vision and pattern recognition. pp. 232- 237 ,(1998) , 10.1109/CVPR.1998.698614