Abstract
Person re-identification is a challenging task in the field of intelligent video surveillance because there are wide variations between pedestrian images. As a classical metric learning method, Keep It Simple and Straightforward (KISS) has shown good performance for person re-identification. However, when the dimension of data is high, the KISS method may perform poorly because of small sample size problem. A common solution to this problem is to apply dimensionality reduction technologies to original data before the KISS metric learning, such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). In this paper, to learn a discriminant and robust metric, we propose a novel two-stage metric learning via QR-Decomposition and KISS, named QRKISS. The first stage of QRKISS is to project original data into a lower dimensional space by QR decomposition. In this lower dimensional space, the trace of the covariance matrix of interpersonal differences can reach maximum. Based on KISS method, the second stage of QRKISS obtains a Mahalanobis matrix in the low-dimension space. We conduct thorough validation experiments on the VIPeR, PRID 450S and CUHK01 datasets, which demonstrate that QRKISS method is better than other KISS-based metric learning methods and achieves state-of-the-art performance.
Similar content being viewed by others
References
Vezzani R, Baltieri D, Cucchiara R (2013) People reidentification in surveillance and forensics: a survey. ACM Comput Surv CSUR 46(2):29
Bedagkar-Gala A, Shah SK (2014) A survey of approaches and trends in person re-identification. Image Vis Comput 32(4):270–286
Zheng L, Yang Y, Hauptmann AG (2016) Person re-identification: past, present and future. arXiv preprint arXiv:1610.02984
Plantinga A (1961) Things and persons. Rev Metaphys 14(3):493–519
Yang Y, Yang J, Yan J et al (2014) Salient color names for person re-identification. In: European conference on computer vision. Springer, Cham, pp 536–551
Liao S, Hu Y, Zhu X et al (2015) Person re-identification by local maximal occurrence representation and metric learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2197–2206
Wu S, Chen Y C, Li X et al (2016) An enhanced deep feature representation for person re-identification. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, pp 1–8
Chen YC, Zheng WS, Lai J (2015) Mirror representation for modeling view-specific transform in person re-identification. In: Twenty-fourth international joint conference on artificial intelligence
Matsukawa T, Okabe T, Suzuki E et al (2016) Hierarchical gaussian descriptor for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1363–1372
Shen F, Yang Y, Li Liu, Liu W, Tao D, Shen H (2017) Asymmetric binary coding for image search. IEEE Trans Multimed TMM 19(9):2022–2032
Weinberger KQ, Saul LK (2009) Distance metric learning for large margin nearest neighbor classification. J Mach Learn Res 10(Feb):207–244
Koestinger M, Hirzer M, Wohlhart P et al (2012) Large scale metric learning from equivalence constraints. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2288–2295
Pedagadi S, Orwell J, Velastin S et al (2013) Local fisher discriminant analysis for pedestrian re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3318–3325
Roth P M, Hirzer M, Koestinger M et al (2014) Mahalanobis distance learning for person re-identification. In: Person re-identification. Springer London, pp 247–267
Yang L, Jin R (2006) Distance metric learning: a comprehensive survey. Mich State Univ 2(2):1–51
Shen F, Shen C, Shi Q et al (2015) Hashing on nonlinear manifolds. IEEE Trans Image Process 24(6):1839–1851
Shen F, Zhou X, Yang Y et al (2016) A fast optimization method for general binary code learning. IEEE Trans Image Process 25(12):5610–5621
Lai Z, Wong W, Xu Y, Zhao C, Sun M (2014) Sparse alignment for robust tensor learning. IEEE Trans Neural Netw Learn Syst 25(10):1779–1792
Li W, Zhao R, Xiao T et al (2014) Deepreid: Deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 152–159
Varior RR, Shuai B, Lu J et al (2016) A siamese long short-term memory architecture for human re-identification. In: European conference on computer vision. Springer, Berlin, pp 135–153
Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemom Intell Lab Syst 2(1–3):37–52
Mika S, Ratsch G, Weston J et al (1999) Fisher discriminant analysis with kernels. In: Neural networks for signal processing IX, 1999. Proceedings of the 1999 IEEE signal processing society workshop. IEEE, pp 41–48
Xiong F, Gou M, Camps O et al (2014) Person re-identification using kernel-based metric learning methods. In: European conference on computer vision. Springer, Cham, pp 1–16
Mignon A, Jurie F (2012) PCCA: a new approach for distance learning from sparse pairwise constraints. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR), pp 2666–2672
Li Z, Chang S, Liang F et al (2013) Learning locally-adaptive decision functions for person verification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3610–3617
Zhang L, Xiang T, Gong S (2016) Learning a discriminative null space for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1239–1248
Lisanti G, Masi I, Del Bimbo A (2014) Matching people across camera views using kernel canonical correlation analysis. In: Proceedings of the international conference on distributed smart cameras. ACM, p 10
Wang W, Taalimi A, Duan K et al (2016) Learning patch-dependent kernel forest for person re-identification. In: 2016 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 1–9
Lisanti G, Karaman S, Masi I (2017) Multichannel-kernel canonical correlation analysis for cross-view person reidentification. ACM Trans Multi Comput Commun Appl TOMM 13(2):13
Liu H, Qi M, Jiang J (2015) Kernelized relaxed margin components analysis for person re-identification. IEEE Signal Process Lett 22(7):910–914
Tao D, Jin L, Wang Y et al (2013) Person re-identification by regularized smoothing kiss metric learning. IEEE Trans Circuits Syst Video Technol 23(10):1675–1685
Tao D, Guo Y, Song M et al (2016) Person re-identification by dual-regularized kiss metric learning. IEEE Trans Image Process 25(6):2726–2738
Liao S, Zhao G, Kellokumpu V et al (2010) Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR), pp 1301–1306. IEEE
Davis JV, Kulis B, Jain P et al (2007) Information-theoretic metric learning. In: Proceedings of the 24th international conference on machine learning, pp 209–216
Liong V E, Lu J, Ge Y (2014) Regularized Bayesian metric learning for person re-identification. In: ECCV workshops (3), pp 209–224
Golub GH, Van Loan CF (2012) Matrix computations, vol 3. JHU Press, Baltimore
Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. In: Proceedings of the IEEE international workshop on performance evaluation for tracking and surveillance (PETS), vol 3, No 5. Citeseer, pp 1–7
Li W, Zhao R, Wang X (2012) Human reidentification with transferred metric learning. In: Asian conference on computer vision. Springer, Berlin, pp 31–44
Paisitkriangkrai S, Shen C, van den Hengel A (2015) Learning to rank in person re-identification with metric ensembles. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1846–1855
Liao S, Li SZ (2015) Efficient psd constrained asymmetric metric learning for person re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 3685–3693
Acknowledgements
The authors would like to thank the anonymous reviewers for their critical and constructive comments and suggestions. This work is supported by China National Natural Science Foundation under Grant No. 61673299, 61203247 and The Hong Kong Polytechnic University (Project account: G-UC42). This work is also partially supported by China National Natural Science Foundation under Grant No. 61573259, 61573255, 61375012. It is also supported by the Fundamental Research Funds for the Central Universities (Grant No. 0800219327). It is also partially supported by Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) and by the Open Project Program of Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education under Grant No. 30920130122005. It is also partially supported by the program of Further Accelerating the Development of Chinese Medicine Three Year Action of Shanghai Grant No. ZY3-CCCX-3-6002.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Zhao, C., Chen, Y., Wei, Z. et al. QRKISS: A Two-Stage Metric Learning via QR-Decomposition and KISS for Person Re-Identification. Neural Process Lett 49, 899–922 (2019). https://doi.org/10.1007/s11063-018-9820-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-018-9820-x