Enhanced Distribution Field Tracking Using Channel Representations

Visual tracking of objects under varying lighting conditions and changes of the object appearance, such as articulation and change of aspect, is a challenging problem. Due to its robustness and speed, distribution field tracking is among the state-of-the-art approaches for tracking objects with constant size in grayscale sequences. According to the theory of averaged shifted histograms, distribution fields are an approximation of kernel density estimates. Another, more efficient approximation are channel representations, which are used in the present paper to derive an enhanced computational scheme for tracking. This enhanced distribution field tracking method outperforms several state-of-the-art methods on the VOT2013 challenge, which evaluates accuracy, robustness, and speed.

[1]  D. W. Scott.  Averaged Shifted Histograms: Effective Nonparametric Density Estimators in Several Dimensions , 1985 .

[2]  David W. Scott,et al.  Multivariate Density Estimation: Theory, Practice, and Visualization , 1992, Wiley Series in Probability and Statistics.

[3]  D. W. Scott,et al.  Multivariate Density Estimation, Theory, Practice and Visualization , 1992 .

[4]  Alexandre Pouget,et al.  Probabilistic Interpretation of Population Codes , 1996, Neural Computation.

[5]  Gösta H. Granlund,et al.  An Associative Perception-Action Structure Using a Localized Space Variant Information Representation , 2000, AFPAC.

[6]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[7]  R. Zemel,et al.  Information processing with population codes , 2000, Nature Reviews Neuroscience.

[8]  Marcel Worring,et al.  Occlusion Robust Adaptive Template Tracking , 2001, ICCV.

[9]  Gregory D. Hager,et al.  Multiple kernel tracking with SSD , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[10]  Simon Baker,et al.  Lucas-Kanade 20 Years On: A Unifying Framework , 2004, International Journal of Computer Vision.

[11]  Per-Erik Forssén,et al.  Low and Medium Level Vision Using Channel Representations , 2004 .

[12]  Stanley T. Birchfield,et al.  Spatiograms versus histograms for region-based tracking , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[13]  Michael Felsberg,et al.  Channel smoothing: efficient robust smoothing of low-level signal features , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Erik Jonsson,et al.  Channel-Coded Feature Maps for Computer Vision and Machine Learning , 2008 .

[15]  Michael Felsberg,et al.  Efficient computation of channel-coded feature maps through piecewise polynomials , 2009, Image Vis. Comput..

[16]  Michael Felsberg,et al.  Integral P-channels for fast and robust region matching , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[17]  Michael Felsberg,et al.  Incremental Computation of Feature Hierarchies , 2010, DAGM-Symposium.

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

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

[20]  Jean-Paul Chilès,et al.  Wiley Series in Probability and Statistics , 2012 .

[21]  Luc Florack,et al.  Mathematical Methods for Signal and Image Analysis and Representation , 2012, Computational Imaging and Vision.

[22]  Hossein Mobahi,et al.  Seeing through the blur , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Michael Felsberg,et al.  Adaptive Filtering Using Channel Representations , 2012, Mathematical Methods for Signal and Image Analysis and Representation.

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