MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization

We propose a multi-expert restoration scheme to address the model drift problem in online tracking. In the proposed scheme, a tracker and its historical snapshots constitute an expert ensemble, where the best expert is selected to restore the current tracker when needed based on a minimum entropy criterion, so as to correct undesirable model updates. The base tracker in our formulation exploits an online SVM on a budget algorithm and an explicit feature mapping method for efficient model update and inference. In experiments, our tracking method achieves substantially better overall performance than 32 trackers on a benchmark dataset of 50 video sequences under various evaluation settings. In addition, in experiments with a newly collected dataset of challenging sequences, we show that the proposed multi-expert restoration scheme significantly improves the robustness of our base tracker, especially in scenarios with frequent occlusions and repetitive appearance variations.

[1]  Jan-Olof Eklundh,et al.  Computer Vision — ECCV '94 , 1994, Lecture Notes in Computer Science.

[2]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

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

[4]  Takahiro Ishikawa,et al.  The template update problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Yoshua Bengio,et al.  Semi-supervised Learning by Entropy Minimization , 2004, CAP.

[6]  Horst Bischof,et al.  Real-Time Tracking via On-line Boosting , 2006, BMVC.

[7]  M. Shah,et al.  Object tracking: A survey , 2006, CSUR.

[8]  Horst Bischof,et al.  Learning Features for Tracking , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Shai Avidan,et al.  Ensemble Tracking , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Qi Zhao,et al.  Co-Tracking Using Semi-Supervised Support Vector Machines , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[11]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

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

[13]  Gérard G. Medioni,et al.  Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers , 2008, ECCV.

[14]  Vladimir Pavlovic,et al.  Face tracking and recognition with visual constraints in real-world videos , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Subhransu Maji,et al.  Max-margin additive classifiers for detection , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[16]  Junseok Kwon,et al.  Visual tracking decomposition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Arnold W. M. Smeulders,et al.  Thirteen Hard Cases in Visual Tracking , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[18]  Slobodan Vucetic,et al.  Online training on a budget of support vector machines using twin prototypes , 2010 .

[19]  Jiri Matas,et al.  P-N learning: Bootstrapping binary classifiers by structural constraints , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

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

[22]  Erik Blasch,et al.  Minimum Error Bounded Efficient L1 Tracker with Occlusion Detection (PREPRINT) , 2011 .

[23]  Junseok Kwon,et al.  Tracking by Sampling Trackers , 2011, 2011 International Conference on Computer Vision.

[24]  Gérard G. Medioni,et al.  Context tracker: Exploring supporters and distracters in unconstrained environments , 2011, CVPR 2011.

[25]  Philip H. S. Torr,et al.  Struck: Structured output tracking with kernels , 2011, 2011 International Conference on Computer Vision.

[26]  Narendra Ahuja,et al.  Low-Rank Sparse Learning for Robust Visual Tracking , 2012, ECCV.

[27]  Matthieu Guillaumin,et al.  Segmentation Propagation in ImageNet , 2012, ECCV.

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

[29]  Huchuan Lu,et al.  Robust object tracking via sparsity-based collaborative model , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Margrit Betke,et al.  Randomized Ensemble Tracking , 2013, 2013 IEEE International Conference on Computer Vision.

[31]  Deva Ramanan,et al.  Self-Paced Learning for Long-Term Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Huchuan Lu,et al.  Least Soft-Threshold Squares Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  Zhongfei Zhang,et al.  A survey of appearance models in visual object tracking , 2013, ACM Trans. Intell. Syst. Technol..

[34]  Ming-Hsuan Yang,et al.  Least Soft-thresold Squares Tracking , 2013 .

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

[36]  Rynson W. H. Lau,et al.  Visual Tracking via Locality Sensitive Histograms , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.