Re-identification by Covariance Descriptors

This chapter addresses the problem of appearance matching, while employing the covariance descriptor. We tackle the extremely challenging case in which the same nonrigid object has to be matched across disjoint camera views. Covariance statistics averaged over a Riemannian manifold are fundamental for designing appearance models invariant to camera changes. We discuss different ways of extracting an object appearance by incorporating various training strategies. Appearance matching is enhanced either by discriminative analysis using images from a single camera or by selecting distinctive features in a covariance metric space employing data from two cameras. By selecting only essential features for a specific class of objects (e.g., humans) without defining a priori feature vector for extracting covariance, we remove redundancy from the covariance descriptor and ensure low computational cost. Using a feature selection technique instead of learning on a manifold, we avoid the over-fitting problem. The proposed models have been successfully applied to the person re-identification task in which a human appearance has to be matched across nonoverlapping cameras. We carry out detailed experiments of the suggested strategies, demonstrating their pros and cons w.r.t. recognition rate and suitability to video analytics systems.

[1]  Jean-Marc Odobez,et al.  Fast human detection from joint appearance and foreground feature subset covariances , 2011, Comput. Vis. Image Underst..

[2]  Horst Bischof,et al.  Large scale metric learning from equivalence constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Slawomir Bak,et al.  Person Re-identification Using Spatial Covariance Regions of Human Body Parts , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[4]  Richard I. Hartley,et al.  Person Reidentification Using Spatiotemporal Appearance , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[5]  Bingpeng Ma,et al.  BiCov: a novel image representation for person re-identification and face verification , 2012, BMVC.

[6]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Slawomir Bak,et al.  Multiple-shot human re-identification by Mean Riemannian Covariance Grid , 2011, 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[9]  Anil K. Jain,et al.  Special Issue on Awards from ICPR 2010 , 2012, Pattern Recognit. Lett..

[10]  Matti Pietikäinen,et al.  Matching Groups of People by Covariance Descriptor , 2010, 2010 20th International Conference on Pattern Recognition.

[11]  René Vidal,et al.  Unsupervised Riemannian Clustering of Probability Density Functions , 2008, ECML/PKDD.

[12]  Xavier Pennec,et al.  A Riemannian Framework for Tensor Computing , 2005, International Journal of Computer Vision.

[13]  Usama M. Fayyad,et al.  Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning , 1993, IJCAI.

[14]  Gerald Schaefer,et al.  Illuminant and device invariant colour using histogram equalisation , 2005, Pattern Recognit..

[15]  Vittorio Murino,et al.  Symmetry-driven accumulation of local features for human characterization and re-identification , 2013, Comput. Vis. Image Underst..

[16]  Shaogang Gong,et al.  Person re-identification by probabilistic relative distance comparison , 2011, CVPR 2011.

[17]  Alessandro Perina,et al.  Multiple-shot person re-identification by chromatic and epitomic analyses , 2012, Pattern Recognit. Lett..

[18]  Hai Tao,et al.  Evaluating Appearance Models for Recognition, Reacquisition, and Tracking , 2007 .

[19]  Slawomir Bak,et al.  Learning to Match Appearances by Correlations in a Covariance Metric Space , 2012, ECCV.

[20]  Narendra Ahuja,et al.  Pedestrian Recognition with a Learned Metric , 2010, ACCV.

[21]  Fatih Murat Porikli,et al.  Covariance Tracking using Model Update Based on Lie Algebra , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[22]  Fatih Murat Porikli,et al.  Region Covariance: A Fast Descriptor for Detection and Classification , 2006, ECCV.

[23]  Slawomir Bak,et al.  Boosted human re-identification using Riemannian manifolds , 2012, Image Vis. Comput..

[24]  Shaogang Gong,et al.  Associating Groups of People , 2009, BMVC.

[25]  Fatih Murat Porikli,et al.  Pedestrian Detection via Classification on Riemannian Manifolds , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  W. Förstner,et al.  A Metric for Covariance Matrices , 2003 .

[27]  Vittorio Murino,et al.  Custom Pictorial Structures for Re-identification , 2011, BMVC.

[28]  Horst Bischof,et al.  Person Re-identification by Descriptive and Discriminative Classification , 2011, SCIA.