Structural keypoints voting for global visual tracking

This paper proposes a patch-based keypoints clustering method for long term robust visual tracking. We plan to employ a parallel framework with keypoints matching and estimation for tracking purpose. Patch-based method is implemented in our algorithm to improve the flexibility of system. The template is divided into patches to ensure the spatial constraint of local keypoints. The motion cue of patches is calculated with optical flow for consensus clustering and the outliers are suppressed for the final voting. To eliminate the error, we propose a two-step voting from global to local scope. The effective keypoints in global vote for a center and estimate the patch centers which will be compared with the voting centers from each individial patch keypoints. The final voting is determined by the voting with minimum error, which could robustly reduce the error due to the misclassified outliers. Finally, the experiments will be followed to validate the performance of proposed algorithm on the public benchmark.

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

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

[3]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[4]  Laura Sevilla-Lara,et al.  Distribution fields for tracking , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Shuzhi Sam Ge,et al.  Parameterized Distortion-Invariant Feature for Robust Tracking in Omnidirectional Vision , 2016, IEEE Transactions on Automation Science and Engineering.

[6]  Yi Wu,et al.  Online Object Tracking: A Benchmark , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Qing Wang,et al.  Online discriminative object tracking with local sparse representation , 2012, 2012 IEEE Workshop on the Applications of Computer Vision (WACV).

[8]  Haibin Ling,et al.  Robust Visual Tracking and Vehicle Classification via Sparse Representation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Yanxi Liu,et al.  Online Selection of Discriminative Tracking Features , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Huchuan Lu,et al.  L2-RLS-Based Object Tracking , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[11]  Shai Avidan,et al.  Support Vector Tracking , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  Shai Avidan,et al.  Locally Orderless Tracking , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Huchuan Lu,et al.  Robust Object Tracking via Sparse Collaborative Appearance Model , 2014, IEEE Transactions on Image Processing.

[14]  Zdenek Kalal,et al.  Tracking-Learning-Detection , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Youfu Li,et al.  Contour coding based rotating adaptive model for human detection and tracking in thermal catadioptric omnidirectional vision. , 2012, Applied optics.

[16]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[17]  Lei Zhang,et al.  Fast Compressive Tracking , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  David J. Fleet,et al.  Robust online appearance models for visual tracking , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[19]  Roman P. Pflugfelder,et al.  Consensus-based matching and tracking of keypoints for object tracking , 2014, IEEE Winter Conference on Applications of Computer Vision.