Abstract
Person re-identification, which is to match people across areas covered by multiple non-overlap** surveillance cameras, has drawn great research interests in the video surveillance domain. Previous research mainly focus on feature extraction and distance measure, where the former aims to find robust feature representation while the latter seeks to learn an optimal metric space. Because of the introduction of supervised information, metric learning methods can usually achieve better performance over feature based methods. As one of the most representative metric learning method, the Large Margin Nearest Neighbor (LMNN) algorithm was recently applied in person re-identification task and achieved satisfactory results [1]. However, LMNN uses a standard hinge loss function, which is neither differentiable everywhere nor time-efficiency due to the usage of all training samples. In this paper, we propose to replace hinge loss function with the logistic loss function, which transforms LMNN to a smooth unconstrained convex optimization problem easily solved with gradient descent algorithm. Thereafter, we further design a stochastic sampling scheme to accelerate the optimization process of the above problem with randomly selected training samples. Extensive comparative experiments conducted on two standard datasets have shown the effectiveness and efficiency of the proposed algorithm over a series of standard baseline methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Hirzer, M., Beleznai, C., Kstinger, M., Roth, P.M., Bischof, H.: Dense appearance modeling and efficient learning of camera transitions for person re-identification. In: ICIP (2012)
Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: Computer Vision and Pattern Recognition (CVPR) (2010)
Prosser, B., Zheng, W.S., Gong, S., **ang, T.: Person re-identification by support vector ranking. In: British Machine Vision Conference (BMVC) (2010)
Zheng, W.S., Gong, S., **ang, T.: Person re-identification by probabilistic relative distance comparison. In: Computer Vision and Pattern Recognition (CVPR) (2011)
Kostinger, M., Hirzer, M., Wohlhart, P., Roth, P., Bischof, H.: Large scale metric learning from equivalence constraints. In: Computer Vision and Pattern Recognition (CVPR) (2012)
Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking. In: IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS) (2007)
Wang, X., Doretto, G., Sebastian, T., Rittscher, J., Tu, P.: Shape and appearance context modeling. In: International Conference on Computer Vision (ICCV) (2007)
Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 262–275. Springer, Heidelberg (2008)
Weinberger, K.Q., Blitzer, J., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research 10, 207–244 (2009)
Zhang, T.: Solving large scale linear prediction problems using stochastic gradient descent algorithms. In: Proceedings of the Twenty-First International Conference on Machine Learning (ICML) (2004)
Dikmen, M., Akbas, E., Huang, T.S., Ahuja, N.: Pedestrian recognition with a learned metric. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part IV. LNCS, vol. 6495, pp. 501–512. Springer, Heidelberg (2011)
Tao, D., **, L., Wang, Y., Yuan, Y., Li, X.: Person re-identification by regularized smoothing kiss metric learning. IEEE Trans. on Circuits and Systems for Video Technology (2013)
Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: International Conference on Machine learning (ICML) (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, Y., Hu, R., Liang, C., Zhang, C., Leng, Q. (2013). Person Re-identification by Smooth Metric Learning. In: Huet, B., Ngo, CW., Tang, J., Zhou, ZH., Hauptmann, A.G., Yan, S. (eds) Advances in Multimedia Information Processing – PCM 2013. PCM 2013. Lecture Notes in Computer Science, vol 8294. Springer, Cham. https://doi.org/10.1007/978-3-319-03731-8_52
Download citation
DOI: https://doi.org/10.1007/978-3-319-03731-8_52
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-03730-1
Online ISBN: 978-3-319-03731-8
eBook Packages: Computer ScienceComputer Science (R0)