An Appearance Model and Feature Selection in Kernelized Correlation Filter Based Visual Object Tracking

In this chapter, we propose an eigenbasis vector based appearance model in kernelized correlation filter based visual object tracking by detection. The proposed appearance is learned using reconstructed targets in successive video frames. This learned appearance is used in KCF-based tracker in addition to raw pixel based appearance, i.e., without subspace reconstruction. The 2c number of HOG features are extracted from both the appearance models. Using a feature selection strategy, the number of feature channels is reduced to c. The kernel correlation for tracking by detection is computed for only c number of channels. To further improve the tracking accuracy, a discriminative parameter vector is learned in each video frame. This parameter vector is used to compute the scores of two intermediate tracked instances. The proposed method performs better than KCF-based tracker in a number of challenging video sequences.

[1]  Jiri Matas,et al.  Discriminative Correlation Filter with Channel and Spatial Reliability , 2017, CVPR.

[2]  Philip H. S. Torr,et al.  Struck: Structured output tracking with kernels , 2011, ICCV.

[3]  Rui Caseiro,et al.  High-Speed Tracking with Kernelized Correlation Filters , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Kaihua Zhang,et al.  Real-time visual tracking via online weighted multiple instance learning , 2013, Pattern Recognit..

[5]  Shengping Zhang,et al.  Robust visual tracking based on online learning sparse representation , 2013, Neurocomputing.

[6]  Shai Avidan,et al.  Support vector tracking , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[8]  Lei Zhang,et al.  Object Tracking via Dual Linear Structured SVM and Explicit Feature Map , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Ming-Hsuan Yang,et al.  Hierarchical Convolutional Features for Visual Tracking , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[11]  Zhan Song,et al.  An Incremental PCA-HOG Descriptor for Robust Visual Hand Tracking , 2010, ISVC.

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

[13]  Youfu Li,et al.  Robust visual tracking with structured sparse representation appearance model , 2012, Pattern Recognit..

[14]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

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

[16]  Vijay Kumar Sharma,et al.  Visual object tracking based on sequential learning of SVM parameter , 2018, Digit. Signal Process..

[17]  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).

[18]  Jing Peng,et al.  SVM vs regularized least squares classification , 2004, ICPR 2004.

[19]  Takio Kurita,et al.  Selection of Histograms of Oriented Gradients Features for Pedestrian Detection , 2007, ICONIP.

[20]  Vijay Kumar Sharma,et al.  MIL based visual object tracking with kernel and scale adaptation , 2017, Signal Process. Image Commun..

[21]  Michel Bierlaire,et al.  Sample and Pixel Weighting Strategies for Robust Incremental Visual Tracking , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[22]  Guillaume-Alexandre Bilodeau,et al.  Exploiting structural constraints for visual object tracking , 2015, Image Vis. Comput..

[23]  David Zhang,et al.  Fast Visual Tracking via Dense Spatio-temporal Context Learning , 2014, ECCV.

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

[25]  Aurobinda Routray,et al.  Recognizing Subtle Micro-facial Expressions Using Fuzzy Histogram of Optical Flow Orientations and Feature Selection Methods , 2018 .

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

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