Abstract
Person Re-identification is aimed to identify a person through multiple camera views. The task has attained a huge research interest due to its apparent importance in surveillance systems from security aspects. This paper introduces a novel methodology based on Siamese architecture with multi-layer similarity constraints. The baseline model embraces two dense blocks to preserve feature maps at each convolutional layer. Besides, the model training is performed by applying distinct similarity constraints on low-level and high-level layers. Two important observations validate the robustness of the proposed model. First, the similarity constraints can synchronize with the model's classification constraints and produce a unified multi-tasking network. Second, the similarity patterns are encoded in the framework in terms of learning parameters during model training. Therefore, a single image is required at the test time instead of the image pair, which makes the method time-efficient and suitable for wide-scale real-time applications. Experimental outcomes on various distinct datasets show that the proposed method surpasses the existing performance benchmarks for person re-identification.
Similar content being viewed by others
References
Ahmed E, Jones M, Marks TK (2015) An improved deep learning architecture for person re-identification. In Proc IEEE Conf Comput Vis Pattern Recognit pp. 3908–3916
Basha SM, Rajput DS (2017) Evaluating the impact of feature selection on overall performance of sentiment analysis. In Proc 2017 Inter Conf Info Technol pp. 96–102
Chen C, Qi M, Huang G, Wu J, Jiang J, Li X (2021) Learning discriminative features with a dual-constrained guided network for video-based person re-identification. Multimed Tools Appl pp.1–24
Chen W, Chen X, Zhang J, Huang K (2016) A Multitask Deep Network for Person Re-identification. arXiv preprint. https://arxiv.org/abs/1607.05369
Chen YC, Zheng WS, Lai J (2015) Mirror Representation for Modeling View-Specific Transform in Person Re-Identification. In IJCAI. Citeseer, pp. 3402–3408
Soliman A, Terstriep J (2019) Keras Spatial: Extending deep learning frameworks for preprocessing and on-the-fly augmentation of geospatial data. In Proceedings of the 3rd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, pp. 69-76, ACM
Chopra S, Hadsell R, LeCun Y (2005) Learning a similarity metric discriminatively, with application to face verification. In Comput Vis Pattern Recognit pp. 539–546
Choudhary M, Tiwari V, Venkanna U (2019) An approach for iris contact lens detection and classification using ensemble of customized DenseNet and SVM. Future Gener Compu Syst 101, pp.1259–1270, Elsevier
Choudhary M, Tiwari V, Venkanna U (2019) Enhancing human iris recognition performance in unconstrained environment using ensemble of convolutional and residual deep neural network models. Soft Computing 1–15, Springer
Choudhary M, Tiwari V, Venkanna U (2020) CCRNet: A novel data-driven approach to improve cross-domain Iris recognition. Multimed Tools Appl 79(43), pp. 32807–32831, Springer
Choudhary M, Tiwari V, Venkanna U (2020) Iris anti-spoofing through score-level fusion of handcrafted and data-driven features. Appl Soft Comput 91, p.106206, Elsevier
Choudhary M, Tiwari V, Venkanna U (2020) Iris Liveness Detection Using Fusion of Domain-Specific Multiple BSIF and DenseNet Features. IEEE Trans Cybern
Choudhary M, Tiwari V, Uduthalapally V (2021) Iris presentation attack detection based on best-k feature selection from YOLO inspired RoI. Neural Comput App 33(11), pp.5609–5629, Springer
Galiyawala H, Raval MS (2021) Person retrieval in surveillance using textual query: a review. Multimed Tools Appl pp.1–41
Gheissari N, Sebastian TB, Hartley R (2006) Person reidentification using spatiotemporal appearance. Comput Vision Pattern Recognit, IEEE 2:1528–1535
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In Proc IEEE Conf Comput Vis Pattern Recognit pp. 770–778
Huang Y, Zha ZJ, Fu X, Hong R, Li L (2020) Real-world person re-identification via degradation invariance learning. In Proc IEEE/CVF Conf Computer Vis Pattern Recognit pp. 14084–14094
Jose C, Fleuret F (2016) Scalable metric learning via weighted approximate rank component analysis. In European Conf Comput Vis. Springer, pp. 875–890
Khan MA, Mittal M, Goyal LM, Roy S (2021) A deep survey on supervised learning based human detection and activity classification methods. Multimed Tools Appl pp.1–57
Koestinger M, Hirzer M, Wohlhart P, Roth PM, Bischof H (2012) Large scale metric learning from equivalence constraints. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2288–2295
Li S, Shao M, Fu Y (2015) Cross-View Projective Dictionary Learning for Person Re-Identification. In IJCAI. pp. 2155–2161
Li W, Zhao R, Wang X (2012) Human reidentification with transferred metric learning. In Asian Conf Comput Vis. Springer, pp. 31–44
Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identication. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. (pp. 152–159).
Li Z, Tao X, Shaogang G (2016) Learning a discriminative null space for person re-identification. In Proc IEEE Conf Comput Vis Pattern Recognit pp. 1239–1248
Liao S, Hu Y, Zhu X, Li SZ (2015) Person reidentification by local maximal occurrence representation and metric learning. In Proc IEEE Conf Comput Vis Pattern Recognit 2197–2206
Liao S, Li SZ (2015) Efficient psd constrained asymmetric metriclearning for person re-identification. In Proc IEEE Inter Conf Computer Vis pp. 3685–3693
Lin Y, Dong X, Zheng L, Yan Y, Yang Y (2019) A bottom-up clustering approach to unsupervised person re-identification. Proc AAAI Conf Artif Intell 33(01):8738–8745
Lin Y, Xie L, Wu Y, Yan C, Tian Q (2020) Unsupervised person re-identification via softened similarity learning. In Proc IEEE/CVF Conf Comput Vis Pattern Recognit pp. 3390–3399
Lin Y, Zheng L, Zheng Z, Wu Y, Hu Z, Yan C, Yang Y (2019) Improving person re-identification by attribute and identity learning. Pattern Recogn 95:151–161
Liu X, Wang H, Wu Y, Yang J, Yang MH (2015) An ensemble color model for human re-identification. In Appl Comput Vis (WACV), IEEE , pp. 868–875
Liu J, Zha ZJ, Tian QI, Liu D, Yao T, Ling Q, Mei T (2016) Multi-Scale Triplet CNN for Person Re-Identication. In Proceedings of the 2016 ACM on Multimedia Conference. ACM, pp. 192–196
Luo H, Gu Y, Liao X, Lai S, Jiang W (2019) Bag of tricks and a strong baseline for deep person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops pp. 1487–1495
Ma X, Zhu X, Gong S, Xie X, Hu J, Lam KM, Zhong Y (2017) Person re-identification by unsupervised video matching. Pattern Recogn 65:197–210
Matsukawa T, Okabe T, Suzuki E, Sato Y (2016) Hierarchical gaussian descriptor for person re-identification. In Proc IEEE Conf Compu Vis Pattern Recognit pp. 1363–1372
Mignon A, Jurie F (2012) Pcca: a new approach for distance learning from sparse pairwise constraints. In Comput Vis Pattern Recognit (CVPR), IEEE, pp. 2666–2672
Moon H, Phillips PJ (2001) Computational and performance aspects of PCA-based face-recognition algorithms. Perception 30(3):303–321
Paisitkriangkrai S, Shen C, Hengel AVD (2015) Learning to rank in person re-identification with metric ensembles. In Proc IEEE Conf Comput Vis Pattern Recognit 1846–1855
Prosser B, Zheng WS, Gong S, Xiang T, Mary Q (2010) Person Re-Identification by Support Vector Ranking. In BMVC, pp. 1–11
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In Proc IEEE Conf Comput Vis Pattern Recognit pp. 815–823
Shen C, Jin Z, Zhao Y, Fu Z, Jiang R, Chen Y, Hua XS (2017) Deep siamese network with multi-level similarity perception for person re-identification. In Proceedings of the 25th ACM international conference on Multimedia pp. 1942–1950
Shi H, Yang Y, Zhu X, Liao S, Lei Z, Zheng W, Li SZ (2016) Embedding deep metric for person re-identification: A study against large variations. In European Conf Comput Vis. Springer, pp. 732–748
Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Subramaniam A, Chatterjee M, Mittal A (2016) December. Deep neural networks with inexact matching for person re-identification. In Proceedings of the 30th International Conference. Adv Neural Inf Process Syst pp. 2675–2683
Varior RR, Haloi M, Wang G (2016) Gated siamese convolutional neural network architecture for human re-identication. In European Conf Comput Vis. Springer, pp. 791–808
Wang D, Zhang S (2020) Unsupervised person re-identification via multi-label classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 10981–10990
Wang F, Zuo W, Lin L, Zhang D, Zhang L (2016) Joint learning of single-image and cross-image representations for person reidentification. In Proc IEEE Conf Comput Vis Pattern Recognit pp.1288–1296
Wang GA, Yang S, Liu H, Wang Z, Yang, Y, Wang S, Yu G, Zhou E, Sun J (2020) High-order information matters: learning relation and topology for occluded person re-identification. In Proc IEEE/CVF Conf Comput Vis Pattern Recognit pp. 6449–6458
Wang H, Gong S, Xiang T (2016) Highly efficient regression for scalable person re-identification. In British Machine Vision Conference. https://arxiv.org/abs/1612.01341v1 pp. 1–14
Wang J, Zhang T, Song J, Sebe N, Shen HT (2016) A survey on learning to hash. arXiv preprint. https://arxiv.org/abs/1606.00185
Wang Y, Chen Z, Wu F, Wang G (2018) Person re-identification with cascaded pairwise convolutions. In Proc IEEE Conf Comput Vis Pattern Recognit pp. 1470–1478
Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In IEEE Conf Comput Vis Pattern Recognit. https://arxiv.org/abs/1604.07528v1pp. 1–10
Ye M, Shen J, Lin G, Xiang T, Shao L, Hoi SC (2021) Deep learning for person re-identification: A survey and outlook. IEEE Trans Pattern Anal Mach Intell. https://arxiv.org/abs/2001.04193, pp. 1–25
Yi D, Lei Z, Liao S, Li SZ (2014) Deep metric learning for person re-identification. In Pattern Recognition (ICPR), IEEE pp. 34–39
Zhang Y, Li B, Lu H, Irie A, Ruan X (2016) Sample specific svm learning for person re-identification. In Proc IEEE Conf Comput Vis Pattern Recognit pp. 1278–1287
Zhao R, Ouyang W, Wang X (2013) Person re-identification by salience matching. In Proc IEEE Inter Conf Comput Vis pp. 2528–2535
Zhao R, Ouyang W, Wang X (2014) Learning mid-level filters for person re-identification. In Proc IEEE Conf Comput Vis Pattern Recognit pp. 144–151
Zheng L, Yang Y, Tian Q (2016) SIFT meets CNN: a decade survey of instance retrieval. arXiv preprint. https://arxiv.org/abs/1608.01807
Zheng Z, Yang X, Yu Z, Zheng L, Yang Y, Kautz J (2019) Joint discriminative and generative learning for person re-identification. In Proc IEEE/CVF Conf Comput Vis Pattern Recognit pp. 2138–2147
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.
Rights and permissions
About this article
Cite this article
Choudhary, M., Tiwari, V. & Jain, S. Person re-identification using deep siamese network with multi-layer similarity constraints. Multimed Tools Appl 81, 42099–42115 (2022). https://doi.org/10.1007/s11042-021-11292-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11292-2