Abstract
Pedestrian re-identification (re-ID) is a video surveillance technology for specific pedestrians in non-overlapping multi-camera scenes. However, due to the influence of dramatic changes in perspectives and pedestrian occasions, it is still a huge challenge to find a stable, reliable algorithm in high accuracy rate. In this paper, to increase the robustness and performance of re-ID, we proposed a re-ID method by re-ranking the refined re-ID results (i.e. initial lists) gotten from the kernel-Local Fisher Discriminant Analysis (kLFDA) and Marginal Fisher Analysis (MFA) metrics, which can improve the probability of the correct target on the initial result lists and also enhance the robustness. During the process of re-ranking, in order to distinguish pedestrians in high similarity, a rigorous distance constraint model named Perspective Distance Model (PDM) is designed to further reduce the intra-class variations and increase the distance of inter-class variations. By using the PDM, the concise results gotten from the kLFDA and MFA metrics are re-ranked in order to further recognize different individuals in high similarity and improve the re-ID rate. Experimental results on seven challenging re-ID datasets (VIPeR, CUHK01, Prid2011, iLIDS, CUHK03, Market-1501and DukeReID) show that the performance of proposed method is high and effective.







Similar content being viewed by others
References
Bai S, Bai X (2016) Sparse contextual activation for efficient visual re-ranking. IEEE Trans Image Process 25(3):1056–1069. https://doi.org/10.1109/TIP.2016.2514498
Bazzani, Loris et al (2010) Multiple-Shot Person Re-identification by HPE Signature. International Conference on Pattern Recognition IEEE Computer Society, p 1413-1416. https://doi.org/10.1109/ICPR.2010.349
Chen YC et al (2016) An asymmetric distance model for cross-view feature mapping in person re-identification. IEEE Trans Circuits Syst Video Technol 99-105. https://doi.org/10.1109/TCSVT.2016.2515309
Chen W, Chen X, Zhang J, Huang K (2017) Beyond triplet loss: a deep quadruplet network for person re-identification. IEEE Conf Comput Vis Pattern Recognit 1320-1329. https://doi.org/10.1109/CVPR.2017.145
Cheng D, Gong Y, Zhou S, Wang J, Zheng N (2016) Person re-identification by multi-channel parts-based CNN with improved triplet loss function. IEEE Conf Comput Vis Pattern Recognit 1335-1344. https://doi.org/10.1109/CVPR.2016.149
Cheng K, Hui K, Zhan Y et al (2017) Sparse representations based distributed attribute learning for person re-identification. Multimed Tools Appl 3:1–23. https://doi.org/10.1007/s11042-017-4967-4
Cheng D, Gong Y, Chang X, Shi W, Hauptmann A, Zheng N (2018) Deep feature learning via structured graph laplacian embedding for person re-identification. Pattern Recogn 82:94–104. https://doi.org/10.1016/j.patcog.2018.05.007
Cui J, Liu Y, Xu Y et al (2013) Tracking generic human motion via fusion of low- and high-dimensional approaches. IEEE Trans Syst Man Cybern Syst 43(4):996–1002. https://doi.org/10.1109/TSMCA.2012.2223670
Deng W, Zheng L, Kang G, Yang Y, Ye Q, Jiao J (2017) Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. Computer Vision and Pattern Recognition arXiv:1711.07027
Fan H, Zheng L, Yang Y (2017) Unsupervised person re-identification: clustering and fine-tuning. Computer Vision and Pattern Recognition. DOI: arXiv:1705.10444
Farenzena M et al (2010) Person re-identification by symmetry-driven accumulation of local features. Computer Vision and Pattern Recognition, p 2360-2367. https://doi.org/10.1109/CVPR.2010.5539926
Fedorov I, Giri R, Rao B D et al (2017) Relevance subject machine: a novel person re-identification framework. Computer Vision and Pattern Recognition. arXiv:1703.10645
Gou M, Karanam S, Liu W, Camps O, Radke R J (2017) DukeMTMC4ReID: a large-scale multi-camera person re-identification dataset. Computer Vision and Pattern Recognition Workshops, p 1425-1434. https://doi.org/10.1109/CVPRW.2017.185
Hirzer M (2012) Large scale metric learning from equivalence constraints. IEEE Conference on Computer Vision and Pattern Recognition, p 2288-2295. https://doi.org/10.1109/CVPR.2012.6247939
Hu HM, Fang W, Zeng G et al (2016) A person re-identification algorithm based on pyramid color topology feature. Multimed Tools Appl 76(9):1–15. https://doi.org/10.1007/s11042-016-4070-2
Huo Z, Chen Y, Hua C (2015) Person re-identification based on multi-directional saliency metric learning. International Conference on Computer Vision Systems, p 45-55. https://doi.org/10.1007/978-3-319-20904-3_5
Jiang M, Yuan Y, Wang Q (2017) Asymmetric cross-view dictionary learning for person re-identification. IEEE International Conference on Acoustics, Speech and Signal Processing, p 1228-1232. https://doi.org/10.1109/ICASSP.2017.7952352
Karanam S, Gou M, Wu Z et al (2017) A comprehensive evaluation and benchmark for person re-identification: features, metrics, and datasets. Computer Vision and Pattern Recognition. arXiv:1605.09653
Leng Q, Hu R, Liang C et al (2015) Person re-identification with content and context re-ranking. Multimed Tools Appl 74(17):6989–7014. https://doi.org/10.1007/s11042-014-1949-7
Li W, Wang X (2013) Locally aligned feature transforms across views. Computer Vision and Pattern Recognition, p 3594-3601. https://doi.org/10.1109/CVPR.2013.461
Li D, Chen X, Zhang Z et al (2017) Learning deep context-aware features over body and latent parts for person re-identification. IEEE Conference on Computer Vision and Pattern Recognition, p 7398-7407. https://doi.org/10.1109/CVPR.2017.782
Liao S, Li S Z (2015) Efficient PSD Constrained Asymmetric Metric Learning for Person Re-identification. IEEE International Conference on Computer Vision, p 3685–3693. https://doi.org/10.1109/ICCV.2015.420
Liao S, Hu Y, Zhu X et al (2015) Person re-identification by Local Maximal Occurrence representation and metric learning. Computer Vision and Pattern Recognition 2197-2206. https://doi.org/10.1109/CVPR.2015.7298832
Lisanti G, Masi I, Bagdanov AD et al (2015) Person re-identification by iterative re-weighted sparse ranking. IEEE Trans Pattern Anal Mach Intell 37(8):1629–1642. https://doi.org/10.1109/TPAMI.2014.2369055
Lisanti G, Karaman S, Masi I (2017) Multichannel-Kernel Canonical Correlation Analysis for Cross-View Person Re-identification. ACM Trans Multimed Comput 13(2). https://doi.org/10.1145/3038916
Liu Y, Nie L, Han L, et al (2015) Action2Activity: recognizing complex activities from sensor data. International Conference on Artificial Intelligence. AAAI Press, p 1617-1623
Liu Y, Zhang L, Nie L et al (2016) Fortune Teller: Predicting Your Career Path. Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), p 201-207
Liu Y, Nie L, Liu L et al (2016) From action to activity: sensor-based activity recognition. Neurocomputing 181:108–115. https://doi.org/10.1016/j.neucom.2015.08.096
Liu Y, Zheng Y , Liang Y, Liu S, Rosenblum ADS (2016) Urbanwater quality prediction based on multi-task multi-view learning. Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, p 2576–2582
Liu L, Cheng L, Liu Y, et al. Recognizing complex activities by a probabilistic interval-based model. Thirtieth AAAI Conference on Artificial Intelligence, p 1266-1272
Ma X, Zhu X, Gong S et al (2017) Person re-identification by unsupervised video matching. Pattern Recogn 65(C):197–210. https://doi.org/10.1016/j.patcog.2016.11.018
Matsukawa T, Okabe T, Suzuki E et al (2016) Hierarchical Gaussian descriptor for person re-identification. Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, p 1363-1372. https://doi.org/10.1109/CVPR.2016.152
Mignon A (2012) PCCA: a new approach for distance learning from sparse pairwise constraints. Computer Vision and Pattern Recognition 2666-2672. https://doi.org/10.1109/CVPR.2012.6247987
Paisitkriang S, Wu L, Shen C et al (2017) Structured learning of metric ensembles with application to person re-identification. Computer Vision & Image Understanding 156(C) 51-65 DOI: https://doi.org/10.1016/j.cviu.2016.10.015
Pedagadi S, Orwell J, Velastin S et al (2013) Local fisher discriminant analysis for pedestrian re-identification. IEEE Conference on Computer Vision and Pattern Recognition, 3318-3325. https://doi.org/10.1109/CVPR.2013.426
Prates R (2016) Kernel hierarchical PCA for person re-identification. Int Conf Pattern Recog 21(3):1061–1066. https://doi.org/10.1109/ICPR.2016.7899944
Prosser B, Zheng W, Gong S, Xiang T (2010) Person re-identification by support vector ranking. British Machine Vision Conference BMVC, p 1-11. https://doi.org/10.5244/C.24.21
Qin D, Gammeter S, Bossard L et al (2011) Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors. Computer Vision and Pattern Recognition, p 777-784. https://doi.org/10.1109/CVPR.2011.5995373
Shet V, Khamis S, Kuo C H (2013) Person re-identification using semantic color names and RankBoost. IEEE Workshop on Applications of Computer Vision, p 281-287. https://doi.org/10.1109/WACV.2013.6475030
Si J, Zhang H, Li CG et al (2017) Spatial pyramid-based statistical features for person re-identification: a comprehensive evaluation. IEEE Transactions on Systems Man & Cybernetics Systems 1-15. https://doi.org/10.1109/TSMC.2016.2645660
Su C, Yang F, Zhang S et al (2015) Multi-task learning with low rank attribute embedding for person re-identification. IEEE International Conference on Computer Vision, p 3739-3747. https://doi.org/10.1109/ICCV.2015.426
Su C, Yang F, Zhang S, Tian Q, Davis LS, Gao W (2018) Multi-task learning with low rank attribute embedding for multi-camera person re-identification. IEEE Trans Pattern Anal Mach Intell 1167-1181. https://doi.org/10.1109/TPAMI.2017.2679002
Ustinova E, Ganin Y, Lempitsky V (2017) Multiregion bilinear convolutional neural networks for person re-identification. AVSS 48(10):2993–3003. https://doi.org/10.1109/AVSS.2017.8078460
Varior RR, Haloi M, Wang G (2016) Gated Siamese convolutional neural network architecture for human re-identification. European Conference on Computer Vision, p 791-808. https://doi.org/10.1007/978-3-319-46484-8_48
Varior RR, Shuai B, Lu J, Xu D, Wang G (2016) A Siamese long short-term memory architecture for human re-identification. Computer Vision ECCV, p 135-153. https://doi.org/10.1007/978-3-319-46478-7_9
Wang T, Gong S, Zhu X, Wang S (2014) Person re-identification by video ranking. Comput Vis ECCV 14:688–703. https://doi.org/10.1007/978-3-31910593-2_45
Wang G, Lin L, Ding S et al (2016) DARI: Distance metric And Representation Integration for Person Verification. Computer Vision and Pattern Recognition. arXiv e-print (arXiv:1604.04377)
Wang Q, Wan J, Yuan Y (2017) Deep Metric Learning for Crowdedness Regression. IEEE Transactions on Circuits & Systems for Video Technology, p 1-11. https://doi.org/10.1109/TCSVT.2017.2703920
Wang Q, Wan J, Yuan Y (2018) Locality constraint distance metric learning for traffic congestion detection. Pattern Recogn 75:272–281. https://doi.org/10.1016/j.patcog.2017.03.030
Xie Y, Yu H, Gong X et al (2017) Adaptive metric learning and probe-specific re-ranking for person re-identification. IEEE Signal Process Lett 24(6):853–857. https://doi.org/10.1109/LSP.2017.2679208
Xiong F, Gou M, Camps O et al (2014) Person re-identification using kernel-based metric learning methods. Lect Notes Comput Sci 8695:1–16. https://doi.org/10.1007/978-3-319-10584-0_1
Xu X, Li W, Xu D (2015) Distance metric learning using privileged information for face verification and person re-identification. IEEE Trans Neural Netw Learn Syst 26(12):3150–3162. https://doi.org/10.1109/TNNLS.2015.2405574
Xue M, Liu W, Liu X (2013) A novel weighted fuzzy LDA for face recognition using the genetic algorithm. Neural Comput Applic 22(7-8):1531–1541. https://doi.org/10.1007/s00521-012-0962-x
Yang Y, Yang J, Yan J et al (2014) Salient color names for person re-identification. European Conference on Computer Vision, p 536-551. https://doi.org/10.1007/978-3-319-10590-1_35
Yang Y, Liao S, Lei Z et al (2017) Learning Efficient Image Representation for Person Re-identification. arXiv:1707.02319
Yang X, Wang M, Hong R et al (2017) Enhancing person re-identification in a self-trained subspace. ACM Trans Multimed Comput Commun Appl 13(3). https://doi.org/10.1145/3089249
Ye M, Liang C, Wang Z et al (2015) Ranking optimization for person re-identification via similarity and dissimilarity. ACM International Conference on Multimedia, p 1239-1242. https://doi.org/10.1145/2733373.2806326
Ye M, Chen J, Leng Q et al (2015) Coupled-view based ranking optimization for person re-identification. International Conference on Multimedia Modeling 8935:105–117. https://doi.org/10.1007/978-3-319-14445-0_10
Ye M, Liang C, Yu Y et al (2016) Person re-identification via ranking aggregation of similarity pulling and dissimilarity pushing. IEEE Trans Multimedia 2553-2566. https://doi.org/10.1109/TMM.2016.2605058
You J, Wu A, Li X et al (2016) Top-push video-based person re-identification. Computer Vision and Pattern Recognition 1345-1353.arXiv e-print (arXiv:1604.08683)
Zhang L, Xiang T, Gong S (2016) Learning a discriminative null space for person re-identification. IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, p 1239-1248. https://doi.org/10.1109/CVPR.2016.139
Zhang L, Xiang T, Gong S (2016) Learning a discriminative null space for person re-identification. Computer Vision and Pattern Recognition, 1239-1248. https://doi.org/10.1109/CVPR.2016.139
Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. Computer Vision and Pattern Recognition 3586-3593. https://doi.org/10.1109/CVPR.2013.460
Zhao R, Ouyang W, Wang X (2017) Person re-identification by saliency learning. IEEE Trans Pattern Anal Mach Intell 39(2):356–370. https://doi.org/10.1109/TPAMI.2016.2544310
Zhen L, Chang S, Liang F et al (2013) Learning locally-adaptive decision functions for person verification. IEEE Conference on Computer Vision and Pattern Recognition, p 3610-3617. https://doi.org/10.1109/CVPR.2013.463
Zheng WS, Gong S, Xiang T (2013) Re-identification by relative distance comparison. IEEE Trans Pattern Anal Mach Intell 35(3):653–658. https://doi.org/10.1109/TPAMI.2012.138
Zhong Z, Zheng L, Cao D et al (2017) Re-ranking person re-identification with k-reciprocal encoding. Computer Vision and Pattern Recognition. arXiv e-print (arXiv:1701.08398)
Acknowledgements
This work was granted by Tianjin Sci-tech Planning Projects (Grant No. 14RCGFGX00846), the Natural Science Foundation of Hebei Province, China (Grant No. F2015202239), Tianjin Sci-tech Planning Projects (Grant No. 15ZCZDNC00130) and Joint Doctoral Training Foundation of HEBUT (Grant No. 2017GN0009).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
(Our code is available: https://github.com/gengshuze/RPDM_RE-ID.git).
Rights and permissions
About this article
Cite this article
Geng, S., Yu, M., Liu, Y. et al. Re-ranking pedestrian re-identification with multiple Metrics. Multimed Tools Appl 78, 11631–11653 (2019). https://doi.org/10.1007/s11042-018-6654-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6654-5