Abstract
Person re-identification is a challenging task due to the critical factors like illumination, occlusion, pose variation, view-points, low resolution, inter/intra-class variations, etc. Re-identification mainly treated as the target retrieval process, which can be improved by multi-query and re-ranking. Due to the high computational cost and consideration of fixed length gallery size, existing re-ranking approaches are not feasible for real-time re-identification applications, specifically with the variable-length gallery. We have proposed a fast yet effective re-ranking approach that utilize the pre-computed pair-wise distance used for initial ranking. We have integrated the advantages of nearest neighbors, hierarchical tree, and multi-query for re-ranking. We hypothesize that the hierarchy of k-nearest neighbors of an image leads to more positive matches in the child layer. Hence the aggregated distance decreases for true match and increases for false match images of the initial rank. We have structured k-nearest neighbor’s hierarchical tree and calculated the aggregated distance. Hierarchical nearest neighbors are treated as multi-query under distance aggregation. Final re-ranked distance is computed as the weighted sum of aggregated and actual distance. Our proposed re-ranking approach is computationally efficient, feasible for real-time applications, unsupervised, and completely automatic. The effectiveness of our proposed method (Source code isavailable upon request) has been verified by various experiments on MARS, Market-1501, DukeMTMC, and CUHK03 datasets.
Similar content being viewed by others
References
Abdolali M, Rahmati M (2019) Neither global nor local: A hierarchical robust subspace clustering for image data. Inf Sci 514:333–353. https://doi.org/10.1016/j.ins.2019.11.031
An L, Chen X, Liu S, Lei Y, Yang S (2017) Integrating appearance features and soft biometrics for person re-identification. Multimed Tools Appl 76(9):12117–12131. https://doi.org/10.1007/s11042-016-4070-2
Arandjelovic R, Zisserman A (2012) Multiple queries for large scale specific object retrieval. Paper presented at the BMVC
Arandjelovic R, Zisserman A (2012) Three things everyone should know to improve object retrieval. Paper presented at the CVPR
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
Bai S, Zhou Z, Wang J, Bai X, Latecki LJ, Tian Q (2017) Ensemble diffusion for retrieval. Paper presented at the ICCV
Bai S, Bai X, Tian Q (2017) Scalable person re-identification on supervised smoothed manifold. Paper presented at the CVPR
Bedagkar-Gala A, Shah SK (2014) A survey of approaches and trends in person re-identification. Image Vision Comput 32(4):270–286. doi:https://doi.org/10.1016/j.imavis.2014.02.001
Chen D, Yuan Z, Chen B, Zheng N (2016) Similarity learning with spatial constraints for person re-identification. Paper presented at the CVPR
Chen Y, Yuan J, Li Z, Wu Y, Nouioua M, Xie GJJo VC, Representation I, (2019) Person re-identification based on re-ranking with expanded k-reciprocal nearest neighbors. J Vis Commun Image 58:486–494
Chen X, Zheng L, Zhao C, Wang Q, Li M (2020) RRGCCAN: Re-ranking via graph convolution channel attention network for person re-identification. IEEE Access 8:131352–131360. https://doi.org/10.1109/ACCESS.2020.3009653
Chum O, Philbin J, Sivic J, Isard M, Zisserman A (2007) Total recall: Automatic query expansion with a generative feature model for object retrieval. In: IEEE 11th International Conference on Computer Vision, pp 1–8
Felzenszwalb PF, Girshick RB, McAllester DA, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645. https://doi.org/10.1109/TPAMI.2009.167
García J, Martinel N, Micheloni C, Vicente AG (2015) Person re-identification ranking optimisation by discriminant context information analysis. Paper presented at the ICCV
Hanif M, Hussain F, Yousaf MH, Velastin SA, Chen Z (2017) Shadow detection for vehicle classification in urban environments. In: Karray F, Campilho A, Cheriet F (eds) Image analysis and recognition, 2017. Springer International Publishing, Cham, pp 352–362
Hassaan O, Shamail A, Butt Z, Taj M (2019) Point cloud segmentation using hierarchical tree for architectural models. Paper presented at the ICASSP
Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification.
Hirzer M, Roth PM, Köstinger M, Bischof H (2012) Relaxed pairwise learned metric for person re-identification. Paper presented at the ECCV
Jarvis RA, Patrick EA (1973) Clustering using a similarity measure based on shared near neighbors. IEEE Trans Comput 22(11):1025–1034. https://doi.org/10.1109/T-C.1973.223640
Jégou H, Harzallah H, Schmid C (2007) A contextual dissimilarity measure for accurate and efficient image search. Paper presented at the CVPR
Kim K, Byeon M, Choi JYJPRL (2019) Re-ranking with ranking-reflected similarity for person re-identification. Pattern Recognit Lett 128:326–332
Köstinger M, Hirzer M, Wohlhart P, Roth PM, Bischof H (2012) Large scale metric learning from equivalence constraints. Paper presented at the CVPR
Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60(6):84–90. https://doi.org/10.1145/3065386
Ksibi S, Mejdoub M, Amar CB (2019) Deep salient-Gaussian Fisher vector encoding of the spatio-temporal trajectory structures for person re-identification. Multimed Tools Appl 78(2):1583–1611. https://doi.org/10.1007/s11042-018-6200-5
Lavi B, Serj MF, Ullah I (2018) Survey on deep learning techniques for person re-identification task.
Leng Q, Hu R, Liang C, Wang Y, Chen J (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, Wu Y, Mukunoki M, Minoh M (2012) Common-near-neighbor analysis for person re-identification. Paper presented at the ICIP
Li W, Zhao R, Xiao T, Wang X (2014) DeepReID: Deep Filter Pairing Neural Network for Person Re-identification. Paper presented at the CVPR
Li W, Zhu X, Gong S (2017) Person Re-Identification by Deep Joint Learning of Multi-Loss Classification. Paper presented at the IJCAI
Li D, Chen X, Zhang Z, Huang K (2017) Learning deep context-aware features over body and latent parts for person re-identification. Paper presented at the CVPR
Li W, Zhu X, Gong S (2018) Harmonious attention network for person re-identification. Paper presented at the CVPR
Liao S, Li SZ (2015) Efficient PSD constrained asymmetric metric learning for person re-identification. Paper presented at the ICCV
Liao S, Hu Y, Zhu X, Li SZ (2015) Person re-identification by Local Maximal Occurrence representation and metric learning. Paper presented at the CVPR
Ling H, Wang Z, Li P, Shi Y, Chen J, Zou F (2019) Improving person re-identification by multi-task learning. Neurocomputing 347:109–118. doi:https://doi.org/10.1016/j.neucom.2019.01.027
Liu C, Loy CC, Gong S, Wang G (2013) POP: Person re-identification post-rank optimisation. Paper presented at the ICCV
Liu J, Sun C, Xu X, Xu B, Yu S (2019) A spatial and temporal features mixture model with body parts for video-based person re-identification. Appl Intell 49(9):3436–3446. doi:https://doi.org/10.1007/s10489-019-01459-8
Mignon A, Jurie F (2012) PCCA: A new approach for distance learning from sparse pairwise constraints. Paper presented at the CVPR
Qin D, Gammeter S, Bossard L, Quack T, Gool LV (2011) Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors. Paper presented at the CVPR
Ristani E, Solera F, Zou RS, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. Paper presented at the ECCV
Sarfraz MS, Schumann A, Eberle A, Stiefelhagen R (2018) A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. Paper presented at the CVPR
Shen X, Lin Z, Brandt J, Avidan S, Wu Y (2012) Object retrieval and localization with spatially-constrained similarity measure and k-NN re-ranking. Paper presented at the CVPR
Syed MA, Han Z, Li Z, Jiao J (2018) Impostor Resilient Multimodal Metric Learning for Person Reidentification. Adv Multimed 2018:3202495:3202491–3202495:3202411. https://doi.org/10.1155/2018/3202495
Wang H, Gong S, Zhu X, Xiang T (2016) Human-in-the-loop person re-identification. Paper presented at the ECCV
Xing EP, Ng AY, Jordan MI, Russell SJ (2002) Distance metric learning with application to clustering with side-information. Paper presented at the NIPS
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
Ye M, Liang C, Yu Y, Wang Z, Leng Q, Xiao C, Chen J, Hu R (2016) Person reidentification via ranking aggregation of similarity pulling and dissimilarity pushing. IEEE Trans Multimed 18(12):2553–2566. https://doi.org/10.1109/TMM.2016.2605058
Ye M, Chen J, Leng Q, Liang C, Wang Z, Sun K (2015) Coupled-view based ranking optimization for person re-identification. In: He X, Luo S, Tao D, Xu C, Yang J, Hasan MA (eds) MultiMedia Modeling, Cham, 2015. Springer International Publishing, Berlin, pp 105–117
Yuan C, Xu C, Wang T, Liu F, Zhao Z, Feng P, Guo J (2018) Deep multi-instance learning for end-to-end person re-identification. Multimed Tools Appl 77(10):12437–12467. https://doi.org/10.1007/s11042-017-4896-2
Zhang G, Kato J, Wang Y, Mase K (2014) People re-identification with local distance comparison using learned metric. IEICE Trans 97-D (9):2461–2472. https://doi.org/10.1587/transinf.2013EDP7424
Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: A benchmark. Paper presented at the ICCV
Zheng L, Yang Y, Hauptmann AG (2016) Person re-identification: past, present and future.
Zheng L, Bie Z, Sun Y, Wang J, Su C, Wang S, Tian Q (2016) MARS: A video benchmark for large-scale person re-identification. Paper presented at the ECCV
Zheng L, Zhang H, Sun S, Chandraker M, Yang Y, Tian Q (2017) Person re-identification in the wild. Paper presented at the CVPR
Zhong Z, Zheng L, Cao D, Li S (2017) Re-ranking person re-identification with k-reciprocal encoding. Paper presented at the CVPR
Acknowledgements
This work was supported in part by the Natural Science Foundation of China under Grant U1536203 and 61972169, in part by the National key research and development program of China (2016QY01W0200), in part by the Major Scientific and Technological Project of Hubei Province (2018AAA068 and 2019AAA051).
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
Hanif, M., Ling, H., Tian, W. et al. Re-ranking person re-identification using distance aggregation of k-nearest neighbors hierarchical tree. Multimed Tools Appl 80, 8015–8038 (2021). https://doi.org/10.1007/s11042-020-10123-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-10123-0