cvpr cvpr2013 cvpr2013-270 cvpr2013-270-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Sateesh Pedagadi, James Orwell, Sergio Velastin, Boghos Boghossian
Abstract: Metric learning methods, , forperson re-identification, estimate a scaling for distances in a vector space that is optimized for picking out observations of the same individual. This paper presents a novel approach to the pedestrian re-identification problem that uses metric learning to improve the state-of-the-art performance on standard public datasets. Very high dimensional features are extracted from the source color image. A first processing stage performs unsupervised PCA dimensionality reduction, constrained to maintain the redundancy in color-space representation. A second stage further reduces the dimensionality, using a Local Fisher Discriminant Analysis defined by a training set. A regularization step is introduced to avoid singular matrices during this stage. The experiments conducted on three publicly available datasets confirm that the proposed method outperforms the state-of-the-art performance, including all other known metric learning methods. Furthermore, the method is an effective way to process observations comprising multiple shots, and is non-iterative: the computation times are relatively modest. Finally, a novel statistic is derived to characterize the Match Characteris- tic: the normalized entropy reduction can be used to define the ’Proportion of Uncertainty Removed’ (PUR). This measure is invariant to test set size and provides an intuitive indication of performance.
[1] K.-E. Aziz, D. Merad, and B. Fertil. Person re-identification using appearance classification. In ICIAR (2), pages 170– 179, 2011.
[2] S. Bak, E. Corvee, F. Bremond, and M. Thonnat. Person reidentification using haar-based and dcd-based signature. In Proc. Seventh IEEE Int Advanced Video and Signal Based Surveillance (AVSS) Conf, pages 1–8, 2010.
[3] D. Baltieri, R. Vezzani, and R. Cucchiara. 3dpes: 3d people dataset for surveillance and forensics. In Proceedings of the 1st International ACM Workshop on Multimedia access to 3D Human Objects, pages 59–64, Scottsdale, Arizona, USA, Nov. 2011. 333333222422
[4] M. Bauml and R. Stiefelhagen. Evaluation of local features for person re-identification in image sequences. In Proc.
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12]
[13] 8th IEEE Int Advanced Video and Signal-Based Surveillance (AVSS) Conf, pages 291–296, 2011. L. Bazzani, M. Cristani, A. Perina, M. Farenzena, and V. Murino. Multiple-shot person re-identification by hpe signature. In ICPR, pages 1413–1416, 2010. L. Bazzani, M. Cristani, A. Perina, and V. Murino. Multipleshot person re-identification by chromatic and epitomic analyses. Pattern Recognition Letters, 33(7):898–903, 2012. A. Bedagkar-Gala and S. K. Shah. Multiple person reidentification using part based spatio-temporal color appearance model. In Proc. IEEE Int Computer Vision Workshops (ICCV Workshops) Conf, pages 1721–1728, 2011. M. Dikmen, E. Akbas, T. Huang, and N. Ahuja. Pedestrian recognition with a learned metric. Computer Vision–ACCV 2010, pages 501–512, 2011. M. S. L. B. Dong Seon Cheng, Marco Cristani and V. Murino. Custom pictorial structures for re-identification. In British Machine Vision Conference (BMVC), page 68. 168. 11, 2011. http://dx.doi.org/10.5244/C.25.68. M. Farenzena, L. Bazzani, A. Perina, V. Murino, and M. Cristani. Person re-identification by symmetry-driven accumulation of local features. In CVPR, pages 2360–2367, 2010. R. A. FISHER. The use of multiple measurements in taxonomic problems. Annals of Eugenics, 7(2): 179–188, 1936. N. Gheissari, T. Sebastian, and R. Hartley. Person reidentification using spatiotemporal appearance. In Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, volume 2, pages 1528–1535. IEEE, 2006. D. Gray, S. Brennan, and H. Tao. Evaluating appearance models for recognition, reacquisition, and tracking. In 10th
[14]
[15]
[16]
[17]
[20]
[21]
[22]
[23]
[24] IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS), 09/2007 2007. D. Gray and H. Tao. Viewpoint invariant pedestrian recognition with an ensemble of localized features. Computer Vision–ECCV 2008, pages 262–275, 2008. O. Hamdoun, F. Moutarde, B. Stanciulescu, and B. Steux. Person re-identification in multi-camera system by signature based on interest point descriptors collected on short video sequences. In ICDSC, pages 1–6, 2008. M. T. Harandi, C. Sanderson, A. Wiliem, and B. C. Lovell. Kernel analysis over riemannian manifolds for visual recognition of actions, pedestrians and textures. In Proc. IEEE Workshop Applications of Computer Vision (WACV), pages 433–439, 2012. X. He and P. Niyogi. Locality preserving projections. In Advances in Neural Information Processing Systems 16. MIT I. Jolliffe. Principal Component Analysis. John Wiley Sons, Ltd, 2005. K. Jungling and M. Arens. View-invariant person reidentification with an implicit shape model. In Proc. 8th IEEE Int Advanced Video and Signal-Based Surveillance (AVSS) Conf, pages 197–202, 2011. K. Jungling, C. Bodensteiner, and M. Arens. Person reidentification in multi-camera networks. In Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition Workshops (CVPRW), pages 55–61, 2011. M. Kostinger, M. Hirzer, P. Wohlhart, P. M. Roth, and H. Bischof. Large scale metric learning from equivalence constraints. In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pages 2288–2295, 2012. T. Kozakaya, S. Ito, and S. Kubota. Random ensemble met-
[25]
[26]
[27]
[28]
[29]
[30] [3 1]
[32]
[33] rics for object recognition. In ICCV’11, pages 1959–1966, 2011. C. Liu, G. Wang, X. Lin, and L. Li. Person re-identification by spatial pyramid color representation and local region matching. IEICE Transactions, 95-D(8):2154–2157, 2012. B. Ma, Y. Su, and F. Jurie. Local Descriptors Encoded by Fisher Vectors for Person Re-identification. In 12th European Conference on Computer Vision (ECCV) Workshops, pages 413–422, Italy, 2012. A. Mignon and F. Jurie. Pcca: A new approach for distance learning from sparse pairwise constraints. In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pages 2666–2672, 2012. B. Prosser, W.-S. Zheng, S. Gong, and T. Xiang. Person reidentification by support vector ranking. In BMVC, pages 1–1 1, 2010. M. Sugiyama. Local fisher discriminant analysis for supervised dimensionality reduction. In Proceedings of23rdInternational Conference on Machine Learning, pages 905–912. ACM, 2006. M. J. Swain and D. H. Ballard. Indexing via color histograms. In ICCV’90, pages 390–393, 1990. Y. Wu, M. Mukunoki, T. Funatomi, M. Minoh, and S. Lao. Optimizing mean reciprocal rank for person re-identification. In Proc. 8th IEEE Int Advanced Video and Signal-Based Surveillance (AVSS) Conf, pages 408–413, 2011. J. Yang, Z. Shi, and P. A. Vela. Person reidentification by kernel pca based appearance learning. In CRV’11, pages 227– 233, 2011. L. Zelnik-manor and P. Perona. Self-tuning spectral clustering. In Advances in Neural Information Processing Systems 17, pages 1601–1608. MIT Press, 2004.
[34] Y. Zhang and S. Li. Gabor-lbp based region covariance descriptor for person re-identification. In Proc. Sixth Int Image
[189]3fIrMtOpPEoeiu-.ndsJtIEHrae,vinCVmcztoEdkfeas,irgmncKope2ab0.utCrAionSde5hrgBa.mlbSufye,osiPqMctdzape,nAlstyciar,2gCndeP0optRs.niM4vef9-oc1.r–Seathgn0lc,di2etap.onsdicA0,1gHrpv2om.celuBa0in5rs.etcChv2ao,sVf.pPcmlRIanogsdeC2i0rflocnm65ag–.-[3]bWipCdnayVeo.-gPpSGtrf.siRoZ,6Cbachp4oe9mtng–ilc6psu,5:tS2ie(c.I6FrCG5S2e0V.ol–1ianmG)2stg6o.v,Cpne5a7gdr,sif2onTtp0ad.1Xg2PcoeaistTn3.og6rm-8bXPp–aiRe3srn7dcgo1.,vn2re0iI-1tfTdo.crPenati(sCcf.eVrIaPEtRio)n-, 333333222533