Abstract
Recently, Mahalanobis metric learning has gained a considerable interest for single-shot person re-identification. The main idea is to build on an existing image representation and to learn a metric that reflects the visual camera-to-camera transitions, allowing for a more powerful classification. The goal of this chapter is twofold. We first review the main ideas of Mahalanobis metric learning in general and then give a detailed study on different approaches for the task of single-shot person re-identification, also comparing to the state of the art. In particular, for our experiments, we used Linear Discriminant Metric Learning (LDML), Information Theoretic Metric Learning (ITML), Large Margin Nearest Neighbor (LMNN), Large Margin Nearest Neighbor with Rejection (LMNN-R), Efficient Impostor-based Metric Learning (EIML), and KISSME. For our evaluations we used four different publicly available datasets (i.e., VIPeR, ETHZ, PRID 2011, and CAVIAR4REID). Additionally, we generated the new, more realistic PRID 450S dataset, where we also provide detailed segmentations. For the latter one, we also evaluated the influence of using well-segmented foreground and background regions. Finally, the corresponding results are presented and discussed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The dataset is publicly available under https://lrs.icg.tugraz.at/download.php.
- 2.
The dataset is publicly available under https://lrs.icg.tugraz.at/download.php.
- 3.
The more detailed segmentations were actually not used for this study, but as they could be beneficial for others they are also provided.
References
Alipanahi, B., Biggs, M., Ghodsi, A.: Distance metric learning vs. fisher discriminant analysis. Proceedings of the AAAI Conference on Artificial Intelligence (2008)
Avraham, T., Gurvich, I., Lindenbaum, M., Markovitch, S.: Learning implicit transfer for person re-identification. In: Proceedings of the ECCV Workshop on Re-Identification (2012)
Bak, S., Corvee, E., Brémond, F., Thonnat, M.: Person re-idendification using Haar-based and DCD-based signature. In: Workshop on Activity Monitoring by Multi-Camera Surveillance Systems (2010)
Bazzani, L., Cristani, M., Murino, V.: Symmetry-driven accumulation of local features for human characterization and re-identification. Comput. Vision Image Underst. 117(2), 130–144 (2013)
Burer, S., Monteiro, R.: A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization. Math. Program. 95(2), 329–357 (2003)
Cheng, D.S., Cristani, M., Stoppa, M., Bazzani, L., Murino, V.: Custom pictorial structures for re-identification. In: Proceedings of the British Machine Vision Conference (2011)
Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: Proceedings of the Int’l Conference on Machine Learning (2007)
Dikmen, M., Akbas, E., Huang, T.S., Ahuja, N.: Pedestrian recognition with a learned metric. In: Proceedings of the Asian Conference on Computer Vision (2010)
Ess, A., Leibe, B., Gool, L.V.: Depth and appearance for mobile scene analysis. In: Proceedings of the IEEE Int’l Conference on Computer Vision (2007)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugenics 7, 179–188 (1936)
Gheissari, N., Sebastian, T.B., Hartley, R.: Person reidentification using spatiotemporal appearance. In: Proceedings of the IEEE Conference on Computer Vision and, Pattern Recognition (2006)
Ghodsi, A., Wilkinson, D.F., Southey, F.: Improving embeddings by flexible exploitation of side information. In: Proceedings of the Int’l Joint Conference on, Artificial Intelligence (2007)
Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking. In: Proceedings of the IEEE Workshop on Performance Evaluation of Tracking and Surveillance (2007)
Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Proceedings of the European Conference on Computer Vision (2008)
Guillaumin, M., Verbeek, J., Schmid, C.: Is that you? Metric learning approaches for face identification. In: Proceedings of the IEEE Int’l Conference on Computer Vision (2009)
Hirzer, M., Beleznai, C., Roth, P.M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: Proceedings of the Scandinavian Conference on Image, Analysis (2011)
Hirzer, M., Roth, P.M., Bischof, H.: Person re-identification by efficient imposter-based metric learning. In: Proceedings of the IEEE Int’l Conference on Advanced Video and Signal-Based Surveillance (2012)
Hirzer, M., Roth, P.M., Köstinger, M., Bischof, H.: Relaxed pairwise learned metric for person re-identification. In: Proceedings of the European Conference on Computer Vision (2012)
Journée, M., Bach, F., Absil, P.A., Sepulchre, R.: Low-rank optimization of the cone of positive semidefinite matrices. SIAM J. Optim. 20(5), 2327–2351 (2010)
Köstinger, M., Hirzer, M., Wohlhart, P., Roth, P.M., Bischof, H.: Large scale metric learning from equivalence constraints. In: Proceedings of the IEEE Conference on Computer Vision and, Pattern Recognition (2012)
Li, W., Zhao, R., Wang, X.: Human reidentification with transferred metric learning. In: Proceedings of the Asian Conference on Computer Vision (2012)
Lin, Z., Davis, L.S.: Learning pairwise dissimilarity profiles for appearance recognition in visual surveillance. In: Advances Int’l Visual Computing, Symposium (2008)
Loog, M., Duin, R.P.W., Haeb-Umbach, R.: Multiclass linear dimension reduction by weighted pairwise fisher criteria. IEEE Trans. Pattern Anal. Mach. Intell. 23(7), 762–766 (2001)
Mignon, A., Jurie, F.: PCCA: A new approach for distance learning from sparse pairwise constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2012)
Porikli, F.: Inter-camera color calibration by correlation model function. In: Proceedings of the Int’l Conference on Image Processing (2003)
Prosser, B., Zheng, W.S., Gong, S., Xiang, T.: Person re-identification by support vector ranking. In: Proceedings of the British Machine Vision Conference (2010)
Rahimi, A., Dunagan, B., Darrell, T.: Simultaneous calibration and tracking with a network of non-overlapping sensors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2004)
Schwartz, W.R., Davis, L.S.: Learning discriminative appearance-based models using partial least squares. In: Proceedings of the Brazilian Symposium on, Computer Graphics and Image Processing (2009)
Wang, X., Doretto, G., Sebastian, T.B., Rittscher, J., Tu, P.H.: Shape and appearance context modeling. In: Proceedings of the IEEE Int’l Conference on Computer Vision (2007)
Weinberger, K.Q., Saul, L.K.: Fast solvers and efficient implementations for distance metric learning. In: Proceedings of the Int’l Conference on, Machine Learning (2008)
Zheng, W.S., Gong, S., Xiang, T.: Reidentification by relative distance comparison. IEEE Trans Pattern Anal. Mach. Intell. 35(3), 653–668 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag London
About this chapter
Cite this chapter
Roth, P.M., Hirzer, M., Köstinger, M., Beleznai, C., Bischof, H. (2014). Mahalanobis Distance Learning for Person Re-identification. In: Gong, S., Cristani, M., Yan, S., Loy, C. (eds) Person Re-Identification. Advances in Computer Vision and Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-4471-6296-4_12
Download citation
DOI: https://doi.org/10.1007/978-1-4471-6296-4_12
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-4471-6295-7
Online ISBN: 978-1-4471-6296-4
eBook Packages: Computer ScienceComputer Science (R0)