Abstract
Since humans concentrate more on differences between relatively small but salient body regions in matching person across disjoint camera views, we propose these differences to be the most significant character in person re-identification (Re-ID). Unlike existing methods focusing on learning discriminative features to adapt viewpoint variation using global visual similarity, we propose a learning visual similarity algorithm via corresponding patch pairs (CPPs) for person Re-ID. The novel CPPs method is introduced to represent the corresponding body patches of the same person in different images with good robustness to body pose, viewpoint and illumination variations. The similarity between two people is measured by an improved bi-directional weight mechanism with a TF-IDF like patches weight. At last, a complementary similarity measure and a mutually-exclusive regulation are presented to enhance the performance of Re-ID. With quantitative evaluation on public datasets, the best rank-1 matching rate on the VIPeR dataset is improved by 4.14%.
Preview
Unable to display preview. Download preview PDF.
References
Weiming, H., Min, H., Zhou, X., Tan, T., Lou, J., Maybank, S.J.: Principal axis-based correspondence between multiple cameras for people tracking. PAMI 28, 663–671 (2006)
Tao, H., Tao, H., Gray, D., Gray, D.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Forsyth, D., Forsyth, D., Zisserman, A., Zisserman, A., Torr, P., Torr, P. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 262–275. Springer, Heidelberg (2008)
Schwartz, W.R., Davis, L.S.: Learning discriminative appearance-based models using partial least squares. In: SIBGRAPI. IEEE, vol. XXII, pp. 322–329 (2009)
Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: CVPR, pp. 2360–2367. IEEE (2010)
Cheng, D.S., Cristani, M., Stoppa, M., Bazzani, L., Murino, V.: Custom pictorial structures for re-identification. In: BMVC. BMVA, pp. 1–11 (2011)
Ma, B., Su, Y., Jurie, F.: Bicov: a novel image representation for person re-identification and face verification. In: BMVC. BMVA, pp. 1–11 (2012)
Bingpeng Ma, Y.S., Jurie, F.: Covariance descriptor based on bio-inspired features for person re-identification and face verification. Image Vision Computing 32, 379–390 (2014)
Zheng, W., Gong, S., Xiang, T.: Reidentification by relative distance comparison. PAMI 35, 653–668 (2013)
Bak, S., Suresh, S., Brmond, F., Thonnat, M.: Fusion of motion segmentation with online adaptive neural classifier for robust tracking. In: VISAPP, vol. II, pp. 410–416. INSTICC (2009)
Luo, P., Wang, X., Tang, X.: Pedestrian parsing via deep decompositional network. In: ICCV, pp. 2648–2655. IEEE (2013)
Jojic, N., Perina, A., Cristani, M., Murino, V., Frey, B.J.: Stel component analysis: modeling spatial correlations in image class structure. In: CVPR, pp. 2044–2051. IEEE (2009)
Bak, S., Corvee, E., Brmond, F., Thonnat, M.: Person re-identification using haar-based and dcd-based signature. In: AVSS, pp. 1–8. IEEE (2010)
Prosser, B., Zheng, W., Gong, S., Xiang, T.: Person re-identification by support vector ranking. In: BMVC. BMVA, vol. I, pp. 1–11 (2010)
Fogel, I., Sagi, D.: Gabor filters as texture discriminator. Biological Cybernetics 61, 103–113 (1989)
Schmid, C.: Constructing models for content-based image retrieval. In: CVPR, pp. 39–45 (2001)
Ma, B., Ma, B., Li, Q., Li, Q., Chang, H., Chang, H.: Gaussian descriptor based on local features for person re-identification. In: Jawahar, C.V., Shan, S., Shan, S., Jawahar, C.V., Jawahar, C.V., Jawahar, C.V. (eds.) ACCV 2014 Workshops. LNCS, vol. 9010, pp. 505–518. Springer, Heidelberg (2015)
Cai, Y., Huang, K., Tan, T.: Human appearance matching across multiple non-overlapping cameras. In: ICPR, pp. 1–4. IEEE (2008)
Zhao, R., Ouyang, W., Wang, X.: Unsupervised salience learning for person re-identification. In: CVPR, pp. 3586–3593. IEEE (2013)
Zhao, R., Ouyang, W., Wang, X.: Learning mid-level filters for person re-identification. In: CVPR, pp. 144–151. IEEE (2014)
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. Citeseer (2007)
Zhao, R., Ouyang, W., Wang, X.: Person re-identification by salience matching. In: ICCV, pp. 2528–2535. IEEE (2013)
Zhang, W., Zhang, W., Wang, X., Wang, X., Zhao, D., Zhao, D., Tang, X., Tang, X.: Graph degree linkage: agglomerative clustering on a directed graph. In: Fitzgibbon, A., Fitzgibbon, A., Lazebnik, S., Lazebnik, S., Perona, P., Perona, P., Sato, Y., Sato, Y., Schmid, C., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 428–441. Springer, Heidelberg (2012)
Li, Z., Chang, S., Liang, F., Huang, T.S., Cao, L., Smith, J.R.: Learning locally-adaptive decision functions for person verification. In: CVPR, pp. 3610–3617. IEEE (2013)
Bazzani, L., Cristani, M., Perina, A., Murino, V.: Multiple-shot person re-identification by chromatic and epitomic analyses. Pattern Recognition Letters 33(7), 898–903 (2012)
Wang, X., Doretto, G., Sebastian, T., Rittscher, J., Tu, P.: Shape and appearance context modeling. In: ICCV, pp. 1–8. IEEE (2007)
Loy, C.C., Liu, C., Gong, S.: Person re-identification by manifold ranking. In: ICIP, vol. 1, p. 5. Citeseer (2013)
Zhou, X., Cui, N., Li, Z., Liang, F., Huang, T.S.: Hierarchical gaussianization for image classification. In: ICCV, pp. 1971–1977. IEEE (2009)
Weinberger, K.Q., Blitzer, J., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. In: NIPS, pp. 1473–1480 (2005)
Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: ICML, pp. 209–216. ACM (2007)
Mignon, A., Jurie, F.: Pcca: A new approach for distance learning from sparse pairwise constraints. In: CVPR, pp. 2666–2672. IEEE (2012)
Pedagadi, S., Orwell, J., Velastin, S.A., Boghossian, B.A.: Local fisher discriminant analysis for pedestrian re-identification. In: CVPR, pp. 3318–3325. IEEE (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Sheng, H., Huang, Y., Zheng, Y., Chen, J., Xiong, Z. (2015). Person Re-identification via Learning Visual Similarity on Corresponding Patch Pairs. In: Zhang, S., Wirsing, M., Zhang, Z. (eds) Knowledge Science, Engineering and Management. KSEM 2015. Lecture Notes in Computer Science(), vol 9403. Springer, Cham. https://doi.org/10.1007/978-3-319-25159-2_73
Download citation
DOI: https://doi.org/10.1007/978-3-319-25159-2_73
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25158-5
Online ISBN: 978-3-319-25159-2
eBook Packages: Computer ScienceComputer Science (R0)