Transfer Learning Based Visual Tracking with Gaussian Processes Regression

Modeling the target appearance is critical in many modern visual tracking algorithms. Many tracking-by-detection algorithms formulate the probability of target appearance as exponentially related to the confidence of a classifier output. By contrast, in this paper we directly analyze this probability using Gaussian Processes Regression (GPR), and introduce a latent variable to assist the tracking decision. Our observation model for regression is learnt in a semi-supervised fashion by using both labeled samples from previous frames and the unlabeled samples that are tracking candidates extracted from the current frame. We further divide the labeled samples into two categories: auxiliary samples collected from the very early frames and target samples from most recent frames. The auxiliary samples are dynamically re-weighted by the regression, and the final tracking result is determined by fusing decisions from two individual trackers, one derived from the auxiliary samples and the other from the target samples. All these ingredients together enable our tracker, denoted as TGPR, to alleviate the drifting issue from various aspects. The effectiveness of TGPR is clearly demonstrated by its excellent performances on three recently proposed public benchmarks, involving 161 sequences in total, in comparison with state-of-the-arts.

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

[2]  Ming-Hsuan Yang,et al.  Incremental Learning for Robust Visual Tracking , 2008, International Journal of Computer Vision.

[3]  Yanning Zhang,et al.  Part-Based Visual Tracking with Online Latent Structural Learning , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Zoubin Ghahramani,et al.  Semi-supervised learning : from Gaussian fields to Gaussian processes , 2003 .

[5]  Pietro Perona,et al.  Self-Tuning Spectral Clustering , 2004, NIPS.

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

[7]  Isabelle Bloch,et al.  Fragments based tracking with adaptive cue integration , 2012, Comput. Vis. Image Underst..

[8]  Qing Wang,et al.  Transferring Visual Prior for Online Object Tracking , 2012, IEEE Transactions on Image Processing.

[9]  Yuan Li,et al.  Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans , 2007, CVPR.

[10]  Lei Zhang,et al.  Real-Time Compressive Tracking , 2012, ECCV.

[11]  Shuicheng Yan,et al.  Robust Object Tracking with Online Multi-lifespan Dictionary Learning , 2013, 2013 IEEE International Conference on Computer Vision.

[12]  Zoubin Ghahramani,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

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

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

[15]  Michael Felsberg,et al.  The Visual Object Tracking VOT2013 Challenge Results , 2013, ICCV 2013.

[16]  Rui Caseiro,et al.  Exploiting the Circulant Structure of Tracking-by-Detection with Kernels , 2012, ECCV.

[17]  Wuzhen Shi,et al.  Visual Tracking with Online Multiple Instance Learning Based on Background Classification , 2014 .

[18]  Jianxiong Xiao,et al.  Tracking Revisited Using RGBD Camera: Unified Benchmark and Baselines , 2013, 2013 IEEE International Conference on Computer Vision.

[19]  Li Bai,et al.  Minimum error bounded efficient ℓ1 tracker with occlusion detection , 2011, CVPR 2011.

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

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

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

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

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

[25]  Dit-Yan Yeung,et al.  Learning a Deep Compact Image Representation for Visual Tracking , 2013, NIPS.

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

[27]  Yi Yao,et al.  Boosting for transfer learning with multiple sources , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[29]  Ralf Herbrich,et al.  Kernel Classifiers from a Bayesian Perspective , 2001 .

[30]  Michael Felsberg,et al.  The Visual Object Tracking VOT2015 Challenge Results , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

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

[32]  Yuan Li,et al.  Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  Ehud Rivlin,et al.  Robust Fragments-based Tracking using the Integral Histogram , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

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

[35]  Haibin Ling,et al.  Real time robust L1 tracker using accelerated proximal gradient approach , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[36]  Junseok Kwon,et al.  Minimum Uncertainty Gap for Robust Visual Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Haibin Ling,et al.  Finding the Best from the Second Bests - Inhibiting Subjective Bias in Evaluation of Visual Tracking Algorithms , 2013, 2013 IEEE International Conference on Computer Vision.

[38]  Junzhou Huang,et al.  Robust tracking using local sparse appearance model and K-selection , 2011, CVPR 2011.

[39]  Lu Zhang,et al.  Structure Preserving Object Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[40]  Xiaoqin Zhang,et al.  Single and Multiple Object Tracking Using Log-Euclidean Riemannian Subspace and Block-Division Appearance Model , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Ralf Herbrich,et al.  Learning Kernel Classifiers: Theory and Algorithms , 2001 .

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

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

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

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

[46]  Anton van den Hengel,et al.  Learning Compact Binary Codes for Visual Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

[48]  Narendra Ahuja,et al.  Robust Visual Tracking via Structured Multi-Task Sparse Learning , 2012, International Journal of Computer Vision.

[49]  Qingming Huang,et al.  Treat samples differently: Object tracking with semi-supervised online CovBoost , 2011, 2011 International Conference on Computer Vision.

[50]  N. Ahuja,et al.  Robust Visual Tracking via MultiTask Sparse Learning , 2012 .

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

[52]  Anton van den Hengel,et al.  Non-sparse linear representations for visual tracking with online reservoir metric learning , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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