Human Reidentification with Transferred Metric Learning
Conference paper
- 102 Citations
- 7.3k Downloads
Abstract
Human reidentification is to match persons observed in non-overlapping camera views with visual features for inter-camera tracking. The ambiguity increases with the number of candidates to be distinguished. Simple temporal reasoning can simplify the problem by pruning the candidate set to be matched. Existing approaches adopt a fixed metric for matching all the subjects. Our approach is motivated by the insight that different visual metrics should be optimally learned for different candidate sets. We tackle this problem under a transfer learning framework. Given a large training set, the training samples are selected and reweighted according to their visual similarities with the query sample and its candidate set. A weighted maximum margin metric is online learned and transferred from a generic metric to a candidate-set-specific metric. The whole online reweighting and learning process takes less than two seconds per candidate set. Experiments on the VIPeR dataset and our dataset show that the proposed transferred metric learning significantly outperforms directly matching visual features or using a single generic metric learned from the whole training set.
Keywords
Training Sample Visual Feature Camera View Transfer Learning Temporal Reasoning
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Gheissari, N., Sebastian, T.B., Rittscher, J., Hartley, R.: Person reidentification using spatiotemporal appearance. In: CVPR (2006)Google Scholar
- 2.Schwartz, W., Davis, L.: Learning discriminative appearance-based models using partial least sqaures. In: Proc. XXII SIBGRAPI (2009)Google Scholar
- 3.Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: CVPR (2010)Google Scholar
- 4.Zheng, W., Gong, S., Xiang, T.: Person re-identification by probabilistic relative distance comparison. In: CVPR (2011)Google Scholar
- 5.Park, U., Jain, A., Kitahara, I., Kogure, K., Hagita, N.: Vise: Visual search engine using multiple networked cameras. In: ICPR (2006)Google Scholar
- 6.van de Weijer, J., Schmid, C.: Coloring Local Feature Extraction. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part II. LNCS, vol. 3952, pp. 334–348. Springer, Heidelberg (2006)CrossRefGoogle Scholar
- 7.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
- 8.Wang, X., Doretto, G., Sebastian, T., Rittscher, J., Tu, P.: Shape and appearance context modeling. In: ICCV (2007)Google Scholar
- 9.Daugman, J.G.: Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A 2, 1160–1169 (1985)CrossRefGoogle Scholar
- 10.Ojala, T., Pietikäinen, M., Mäenpää, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. on PAMI, 971–987 (2002)Google Scholar
- 11.Torralba, A., Murphy, K., Freeman, W., Rubin, M.: Context-based vision system for place and object recognition. In: ICCV (2003)Google Scholar
- 12.Porikli, F.: Inter-camera color calibration by correlation model function. In: ICIP (2003)Google Scholar
- 13.Javed, O., Shafique, K., Shah, M.: Appearance modeling for tracking in multiple non-overlapping cameras. In: CVPR (2005)Google Scholar
- 14.Gilbert, A., Bowden, R.: Tracking Objects Across Cameras by Incrementally Learning Inter-camera Colour Calibration and Patterns of Activity. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part II. LNCS, vol. 3952, pp. 125–136. Springer, Heidelberg (2006)CrossRefGoogle Scholar
- 15.Prosser, B., Gong, S., Xiang, T.: Multi-camera matching using bi-directional cumulative brightness transfer function. In: BMVC (2008)Google Scholar
- 16.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)CrossRefGoogle Scholar
- 17.Shan, Y., Sawhney, H.S., Kumar, R.: Unsupervised Learning of Discriminative Edge Measures for Vehicle Matching between Nonoverlapping Cameras. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 700–711 (2008)CrossRefGoogle Scholar
- 18.Lin, Z., Davis, L.S.: Learning Pairwise Dissimilarity Profiles for Appearance Recognition in Visual Surveillance. In: Bebis, G., Boyle, R., Parvin, B., Koracin, D., Remagnino, P., Porikli, F., Peters, J., Klosowski, J., Arns, L., Chun, Y.K., Rhyne, T.-M., Monroe, L. (eds.) ISVC 2008, Part I. LNCS, vol. 5358, pp. 23–34. Springer, Heidelberg (2008)CrossRefGoogle Scholar
- 19.Prosser, B., Zheng, W., Gong, S., Xiang, T., Mary, Q.: Person re-identification by support vector ranking. In: BMVC (2010)Google Scholar
- 20.Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research 6, 1453–1484 (2005)MathSciNetzbMATHGoogle Scholar
- 21.Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition and tracking (2007)Google Scholar
- 22.Dai, W., Yang, Q., Xue, G., Yu, Y.: Boosting for transfer learning. In: Proc. of ICML (2007)Google Scholar
- 23.Wu, X., Srihari, R.: Incorporating prior knowledge with weighted margin support vector machines. In: Proc. of SIGKDD (2004)Google Scholar
- 24.Jiang, W., Zavesky, E., Chang, S., Loui, A.: Cross-domain learning methods for high-level visual concept classification. In: ICIP (2008)Google Scholar
- 25.Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting Visual Category Models to New Domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 26.Yao, Y., Doretto, G.: Boosting for transfer learning with multiple sources. In: CVPR (2010)Google Scholar
- 27.Qi, G., Aggarwal, C., Huang, T.: Towards semantic knowledge propagation from text corpus to web images. In: Proc. of WWW (2011)Google Scholar
- 28.Yang, J., Yan, R., Hauptmann, A.G.: Cross-domain video concept detection using adaptive svms. In: Proc. of ACM Multimedia (2007)Google Scholar
- 29.Duan, L., Tsang, I.W., Xu, D., Maybank, S.J.: Domain transfer svm for video concept detection. In: CVPR (2009)Google Scholar
- 30.Qi, G., Aggarwal, C., Rui, Y., Tian, Q., Chang, S., Huang, T.: Towards cross-category knowledge propagation for learning visual concepts. In: CVPR (2011)Google Scholar
- 31.Zhan, D.C., Li, M., Li, Y.F., Zhou, Z.H.: Learning instance specific distances using metric propagation. In: Proc. of ICML, p. 154 (2009)Google Scholar
- 32.Sande, K., Gevers, T., Snoek, C.G.M.: Evaluating color descriptors for object and scene recognition. IEEE Trans. on PAMI 32, 1582–1596 (2010)CrossRefGoogle Scholar
- 33.Liu, T., Moore, A.W., Gray, A.G., Yang, K.: An investigation of practical approximate nearest neighbor algorithms. In: Proc. of NIPS (2004)Google Scholar
- 34.Fletcher, R.: Semi-definite matrix constraints in optimization. SIAM J. Control Optim. 23, 493–513 (1985)MathSciNetzbMATHCrossRefGoogle Scholar
- 35.Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin distance metric learning for large margin. Journal of Machine Learning Research 10, 207–244 (2009)zbMATHGoogle Scholar
- 36.Luenberger, D.G., Ye, Y.: Linear and Nonlinear Programming. Springer (2008)Google Scholar
- 37.Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine Learning 3, 1–122 (2011)CrossRefGoogle Scholar
- 38.Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: Proc. of ICML (2007)Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2013