Building an Effective Template Dictionary for Robust Offline Video Tracking

Sparse representation is one of most influential framework for visual tracking. However, how to build an effective template dictionary for tracking is less investigated. In this paper, we propose a template dictionary construction method which is effective for offline video tracking. The template dictionary is constructed including several non-polluted templates, and their offsprings. These templates are selectively updated to absorb the appearance variations and prevent the model from drifting. Furthermore, our tracking algorithm is conducted in a bi-directional way, and the optimization process employed in our work is efficiently solved by two-stage sparse representation, which can greatly improve the tracking performance. Experimental results demonstrate that the proposed template dictionary is robust for offline video tracking.

[1]  Rama Chellappa,et al.  Visual tracking and recognition using appearance-adaptive models in particle filters , 2004, IEEE Transactions on Image Processing.

[2]  Hujun Bao,et al.  Robust Head Tracking Based on Multiple Cues Fusion in the Kernel-Bayesian Framework , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[3]  Huchuan Lu,et al.  Visual tracking via adaptive structural local sparse appearance model , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  David Salesin,et al.  Panoramic video textures , 2005, SIGGRAPH 2005.

[5]  Harry Shum,et al.  Interactive Offline Tracking for Color Objects , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Gregory D. Hager,et al.  Efficient Region Tracking With Parametric Models of Geometry and Illumination , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Kjersti Engan,et al.  Recursive Least Squares Dictionary Learning Algorithm , 2010, IEEE Transactions on Signal Processing.

[8]  Guillermo Sapiro,et al.  Online dictionary learning for sparse coding , 2009, ICML '09.

[9]  Chunhua Shen,et al.  Real-time visual tracking using compressive sensing , 2011, CVPR 2011.

[10]  Xiaoqin Zhang,et al.  Block covariance based l1 tracker with a subtle template dictionary , 2013, Pattern Recognit..

[11]  Jinxiang Chai,et al.  Interactive Tracking of 2D Generic Objects with Spacetime Optimization , 2008, ECCV.

[12]  David J. Fleet,et al.  Robust Online Appearance Models for Visual Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  David Suter,et al.  Adaptive Object Tracking Based on an Effective Appearance Filter , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  David Salesin,et al.  Keyframe-based tracking for rotoscoping and animation , 2004, SIGGRAPH 2004.

[15]  Junzhou Huang,et al.  Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization , 2010, ECCV.

[16]  Ming-Hsuan Yang,et al.  Robust Object Tracking with Online Multiple Instance Learning , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Narendra Ahuja,et al.  Robust visual tracking via multi-task sparse learning , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Ming-Hsuan Yang,et al.  Incremental Learning for Visual Tracking , 2004, NIPS.

[19]  Haibin Ling,et al.  Robust visual tracking using ℓ1 minimization , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[20]  Hujun Bao,et al.  A Robust Tracking System for Low Frame Rate Video , 2015, International Journal of Computer Vision.

[21]  Michael J. Black,et al.  EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation , 1996, International Journal of Computer Vision.

[22]  Laurent D. Cohen,et al.  Combination of Piecewise-Geodesic Paths for Interactive Segmentation , 2014, International Journal of Computer Vision.

[23]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[24]  Horst Bischof,et al.  Semi-supervised On-Line Boosting for Robust Tracking , 2008, ECCV.

[25]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[26]  Mike E. Davies,et al.  Dictionary Learning for Sparse Approximations With the Majorization Method , 2009, IEEE Transactions on Signal Processing.

[27]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Michael Lindenbaum,et al.  Sequential Karhunen-Loeve basis extraction and its application to images , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[29]  Xianchuan Yu,et al.  Multi-scale hybrid saliency analysis for region of interest detection in very high resolution remote sensing images , 2015, Image Vis. Comput..

[30]  Xiaoqin Zhang,et al.  Graph-Embedding-Based Learning for Robust Object Tracking , 2014, IEEE Transactions on Industrial Electronics.

[31]  Jan Flusser,et al.  Moment Forms Invariant to Rotation and Blur in Arbitrary Number of Dimensions , 2003, IEEE Trans. Pattern Anal. Mach. Intell..