Kernel-based motion-blurred target tracking
作者： Yi Wu , Jing Hu , Feng Li , Erkang Cheng , Jingyi Yu
DOI: 10.1007/978-3-642-24031-7_49
关键词:
摘要: Motion blurs are pervasive in real captured video data, especially for hand-held cameras and smartphone because of their low frame rate material quality. This paper presents a novel Kernel-based motion-Blurred target Tracking (KBT) approach to accurately locate objects motion blurred sequence, without explicitly performing deblurring. To model the underlying blurs, we first augment by synthesizing set templates from with different blur directions strengths. These then represented color histograms regularized an isotropic kernel. optimal position each template, choose use mean shift method iterative optimization. Finally, region maximum similarity its corresponding template is considered as target. demonstrate effectiveness efficiency our method, collect several sequences severe compare KBT other traditional trackers. Experimental results show that can robustly reliably track strong targets.
springer.com
acm.org 
sci-hub.st 参考文章(22)
P. Pérez, C. Hue, J. Vermaak, M. Gangnet, Color-Based Probabilistic Tracking european conference on computer vision. pp. 661- 675 ,(2002) , 10.1007/3-540-47969-4_44
Haibin Ling, Li Bai, Yi Wu, Xue Mei, Erik Blasch, Minimum error bounded efficient ℓ1 tracker with occlusion detection. computer vision and pattern recognition. pp. 1257- 1264 ,(2011)
Cynthia Owsley, Aging and vision. Vision Research. ,vol. 51, pp. 1610- 1622 ,(2011) , 10.1016/J.VISRES.2010.10.020
Alper Yilmaz, Omar Javed, Mubarak Shah, Object tracking: A survey ACM Computing Surveys. ,vol. 38, pp. 13- ,(2006) , 10.1145/1177352.1177355
N. Anantrasirichai, J. Burn, David R. Bull, Robust texture features for blurred images using Undecimated Dual-Tree Complex Wavelets 2014 IEEE International Conference on Image Processing (ICIP). pp. 5696- 5700 ,(2014) , 10.1109/ICIP.2014.7026152
Xue Mei, Haibin Ling, Yi Wu, Erik Blasch, Li Bai, Minimum error bounded efficient ℓ 1 tracker with occlusion detection computer vision and pattern recognition. pp. 1257- 1264 ,(2011) , 10.1109/CVPR.2011.5995421
Shengyang Dai, Ming Yang, Ying Wu, Aggelos K. Katsaggelos, Tracking Motion-Blurred Targets in Video international conference on image processing. pp. 2389- 2392 ,(2006) , 10.1109/ICIP.2006.312943
Yifei Lou, Andrea L. Bertozzi, Stefano Soatto, Direct Sparse Deblurring Journal of Mathematical Imaging and Vision. ,vol. 39, pp. 1- 12 ,(2011) , 10.1007/S10851-010-0220-8
Yi Wu, Bo Wu, Jia Liu, Hanqing Lu, Probabilistic tracking on Riemannian manifolds international conference on pattern recognition. pp. 1- 4 ,(2008) , 10.1109/ICPR.2008.4761046
Rob Fergus, Barun Singh, Aaron Hertzmann, Sam T. Roweis, William T. Freeman, Removing camera shake from a single photograph international conference on computer graphics and interactive techniques. ,vol. 25, pp. 787- 794 ,(2006) , 10.1145/1141911.1141956