Skip to main content
SpringerLink
Log in

Trajectory Association for Person Re-identification

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Person re-identification (reID) aims at finding the same person in different camera views. In real-world scenarios, it is quite often that the suspect’s appearance is not known while the suspect’s escape route is known. This paper introduces a new person reID setting, where the query includes both the real suspect’s trajectory and several possible suspects. The goal is to identify the actual suspect and retrieve images of the real suspect. Prior work focuses on extracting pedestrians’ discriminative visual features or using spatial-temporal information while neglecting the importance of cross-camera trajectory information. Due to the spatial-temporal consistency, the trajectory and image complement each other and the trajectory is associated with the image data. Therefore, we consider retrieving the suspect’s image based on the trajectory and introducing a Hidden Markov Model based trajectory framework to jointly analyze image data and trajectory information. We evaluate our methods on two datasets containing person images and trajectory information, demonstrating our approach’s effectiveness.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Li J, Zhang S, Wang J, Gao W, Tian Q (2019) Global-local temporal representations for video person re-identification. In: IEEE international conference on computer vision (ICCV). Seoul, Korea, pp 3957–3966

  2. Yao H, Zhang S, Zhang D, Zhang Y, Li J, Wang Y, Tian Q (2017) Large-scale person re-identification as retrieval. In: ICME Hong Kong, China, pp 1440-1445

  3. Huang Y, Zha Z, Fu X, Hong R, Li L (2020) Real-world person re-identification via degradation invariance learning. CVPR. Seattle, USA, pp 14072–14082

    Google Scholar 

  4. Zeng Z, Wang Z, Wang Z, Chuang Y, Satoh S (2020) Illumination-adaptive person re-identification abs/1905.04525

  5. Cong DNT, Khoudour L, Achard C, Bruyelle J (2011) Intelligent distributed surveillance system for people reidentification in a transportation environment. J Intell Transp Syst 15(3):133–146

    Article  Google Scholar 

  6. Zheng Y, Capra L, Wolfson O, Yang H (2014) Urban computing: concepts, methodologies, and applications. ACM TIST 5(3):38:1-38:55

    Google Scholar 

  7. Huang Y, Zha Z, Fu X, Hong R, Li L (2020) Real-world person re-identification via degradation invariance learning, in: CVPR 2020, Seattle, USA,2020, pp 14072-14082

  8. Fu M, Sun S, Chen N, Wang D, Tong X (2019) Deep fusion feature presentations for nonaligned person re-identification. IEEE Access 7:73253–73261

    Article  Google Scholar 

  9. Sun Y, Xu Q, Li Y, Zhang C, Li Y, Wang S, Sun J (2019) Perceive where to focus: Learning visibility-aware part-level features for partial person re-identification. CVPR. Long Beach, USA, pp 393–402

    Google Scholar 

  10. Chen Y, Zhu X, Gong S (2017) Person re-identification by deep learning multi-scale representations. ICCV Workshops. Venice, Italy, pp 2590–2600

    Google Scholar 

  11. 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 Recognit 95:151–161

    Article  Google Scholar 

  12. Sanakoyeu A, Tschernezki V, Buchler U, Ommer B (2019) Divide and conquer the embedding space for metric learning. CVPR. Long Beach, USA, pp 471–480

    Google Scholar 

  13. Zhong Z, Zheng L, Luo Z, Li S, Yang Y (2019) Invariance matters: exemplar memory for domain adaptive person re-identification. CVPR. Long Beach, USA, pp 598–607

    Google Scholar 

  14. Wang Z, Hu R, Chen C, Yu Y, Jiang J, Liang C, Satoh S (2018) Person reidentification via discrepancy matrix and matrix metric. IEEE Trans Cybern 48(10):3006–3020

    Article  Google Scholar 

  15. Wang Z, Jiang J, Yu Y, Satoh S (2019) Incremental re-identification by cross-direction and cross-ranking adaption. IEEE Trans Multimed 21(9):2376–2386

    Article  Google Scholar 

  16. Wang N, Ma S, Li J, Zhang Y, Zhang L (2020) Multistage attention network for image inpainting. Pattern Recognit 106:107448

    Article  Google Scholar 

  17. Wang N, Zhang Y, Zhang L (2021) Dynamic selection network for image inpainting. IEEE Trans Image Process 30:1784–1798

    Google Scholar 

  18. Lian G, Lai J, Zheng W (2011) Spatial-temporal consistent labeling of tracked pedestrians across non-overlapping camera views. Pattern Recognit 44(5):1121–1136

    Article  Google Scholar 

  19. Meng J, Yuan J, Yang J, Wang G, Tan Y (2016) Object instance search in videos via spatio-temporal trajectory discovery. IEEE Trans Multimed 18(1):116–127

    Article  Google Scholar 

  20. Martinel N, Foresti GL, Micheloni C (2017) Person reidentification in a distributed camera network framework. IEEE Trans Cybern 47(11):3530–3541

    Article  Google Scholar 

  21. Li D, Hu R, Huang W, Wang X, Li D, Zheng F (2020) Hmm-based person re-identification in large-scale open scenario. MMM. Daejeon, South Korea, pp 813–825

    Google Scholar 

  22. Lv J, Lin H, Yang C, Yu Z, Chen Y, Deng M (2014) Identify and trace criminal suspects in the crowd aided by fast trajectories retrieval. In: DASFAA, Bali, Indonesia, pp 16-30

  23. Montjoye YAD, Hidalgo CA, Verleysen M, Blondel VD (2013) Unique in the crowd: The privacy bounds of human mobility. entific Reports 3(3):1376

  24. Niu X, Li M, Cui X, Liu J, Liu S, Chowdhury KR (2014) Wtrack: Hmm-based walk pattern recognition and indoor pedestrian tracking using phone inertial sensors. Pers Ubiquitous Comput 18(8):1901–1915

    Article  Google Scholar 

  25. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. CVPR. Las Vegas, USA, pp 770–778

    Google Scholar 

  26. Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. CVPR. Honolulu, USA, pp 2261–2269

    Google Scholar 

  27. Sun Y, Zheng L, Yang Y, Tian Q, Wang S (2018) Beyond part models: Person retrieval with refined part pooling (and A strong convolutional baseline). ECCV. Munich, Germany, pp 501–518

    Google Scholar 

  28. Yuan Y, Zhang J, Wang Q (2020) Deep gabor convolution network for person re-identification. Neurocomputing 378:387–398

    Article  Google Scholar 

  29. Wei L, Zhang S, Yao H, Gao W, Tian Q (2017) GLAD: global-local-alignment descriptor for pedestrian retrieval. MM. Mountain View, USA, pp 420–428

    Google Scholar 

  30. Luo H, Jiang W, Zhang X, Fan X, Zhang C (2019) Alignedreid++: Dynamically matching local information for person re-identification. Pattern Recognit 94:53–61

    Article  Google Scholar 

  31. Zhang Z, Lan C, Zeng W, Jin X, Chen Z (2020) Relation-aware global attention for person re-identification. CVPR 2020. Seattle, USA, pp 3183–3192

  32. Fu C, Zhao Y, Feng F, Song J, Ji R, Yang Y (2020) Salience-guided cascaded suppression network for person re-identification. CVPR 2020. Seattle, USA, pp 3297–3307

  33. Zheng Z, Zheng L, Yang Y (2019) Pedestrian alignment network for large-scale person re-identification. IEEE Trans Circuits Syst Video Tech 29(10):3037–3045

    Article  Google Scholar 

  34. Zheng Z, Zheng L, Yang Y (2018) A discriminatively learned CNN embedding for person reidentification. ACM Trans Multim Comput Commun Appl 14(1):13:1-13:20

    Article  MathSciNet  Google Scholar 

  35. Wang G, Lin L, Ding S, Li Y, Wang Q (2016) DARI: distance metric and representation integration for person verification. AAAI. Arizona, USA, Phoenix, pp 3611–3617

    Google Scholar 

  36. Wu D, Zheng S, Bao W, Zhang XS, Yuan C, Huang D (2019) A novel deep model with multi-loss and efficient training for person re-identification. Neurocomputing 324:69–75

    Article  Google Scholar 

  37. Yu H, Zheng W, Wu A, Guo X, Gong S, Lai J (2019) Unsupervised person re-identification by soft multilabel learning. CVPR. Long Beach, USA, pp 2148–2157

    Google Scholar 

  38. Luo C, Song C, Zhang Z (2020) Generalizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain Mixup. ECCV. Glasgow, UK, pp 224–241

    Google Scholar 

  39. Huang Y, Peng P, Jin Y, Li Y, Xing J (2020) Domain adaptive attention learning for unsupervised person re-identification. In: AAAI, New York, USA, pp 11069-11076

  40. Huang W, Hu R, Liang C, Yu Y, Zhang C (2016) Camera network based person re-identification by leveraging spatial-temporal constraint and multiple cameras relations. In: International Conference on Multimedia Modeling, 2016

  41. Lv J, Chen W, Li Q, Yang C (2018) Unsupervised cross-dataset person re-identification by transfer learning of spatial-temporal patterns. CVPR. Salt Lake City, USA, pp 7948–7956

    Google Scholar 

  42. Wang G, Lai J, Huang P, Xie X (2019) Spatial-temporal person re-identification. Proc AAAI Conf Artif Intell 33:8933–8940

    Google Scholar 

  43. Xiang X, Lv N, Zhai M, Abdeen R, Saddik A (2020) Dual-Path Part-Level Method for Visible-Infrared Person Re-identification. Neural Process Lett 52(1):313–328

    Article  Google Scholar 

  44. Marras M, Reyes P, Navarro J, Santana M, Fenu G (2019) Deep multi-biometric fusion for audio-visual user re-identification and verification. ICPRAM. Czech Republic, Prague, pp 136–157

    Google Scholar 

  45. Chen A, Abgari M, Wang K (2019) Investigating fast re-identification for multi-camera indoor person tracking. Comput Electr Eng 77:273–288

    Article  Google Scholar 

  46. Jiang N, Bai S, Xu Y, Xing C, Zhou Z, Wu W (2018) Online inter-camera trajectory association exploiting person re-identification and camera topology. MM. Seoul, Korea, pp 1457–1465

    Google Scholar 

  47. Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: A benchmark. ICCV. Santiago, Chile, pp 1116–1124

    Google Scholar 

  48. Zheng Z, Zheng L, Yang Y (2017) Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. ICCV. Venice, Italy, pp 3774–3782

    Google Scholar 

  49. Felzenszwalb PF, McAllester DA, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: CVPR, Anchorage, Alaska, USA

  50. Bolle RM, Connell JH, Pankanti S, Ratha NK, Senior AW (2005) The relation between the ROC curve and the CMC. In: Proceedings of the Fourth IEEE workshop on automatic identification advanced technologies, Buffalo,NY, USA

  51. Zhong Z, Zheng L, Cao D, Li S (2017) Re-ranking person re-identification with k-reciprocal encoding. In: CVPR

Download references

Acknowledgements

This work was supported by National Nature Science Foundation of China (No. U1736206, U1803262, No. 61701194) and National Key R&D Program of China (No. 2017YFB1002803).

Author information

Author notes

  1. D. Li and W. Huang: contribute the same.

Authors and Affiliations

  1. National Engineering Research Center for Multimedia Software, Computer School of Wuhan University, Wuhan, 430072, Hubei Province, China

    Dongyang Li, Ruimin Hu, Wenxin Huang, Xiaochen Wang & Chenhao Hu

  2. Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, 430072, China

    Dongyang Li, Ruimin Hu, Wenxin Huang, Xiaochen Wang & Chenhao Hu

  3. School of Mathematics and Computer, Jianghan University, Wuhan, 430072, China

    Dengshi Li

Authors
  1. Dongyang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ruimin Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wenxin Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dengshi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaochen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chenhao Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ruimin Hu.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, D., Hu, R., Huang, W. et al. Trajectory Association for Person Re-identification. Neural Process Lett 53, 3267–3285 (2021). https://doi.org/10.1007/s11063-021-10540-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-021-10540-8

Keywords

Search

Navigation