Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 5, pp 5843–5861 | Cite as

Cross-dataset person re-identification using deep convolutional neural networks: effects of context and domain adaptation

  • Anıl GençEmail author
  • Hazım Kemal Ekenel
Article
  • 156 Downloads

Abstract

Over the past years, the impact of surveillance systems on public safety increases dramatically. One significant challenge in this domain is person re-identification, which aims to detect whether a person has already been captured by another camera in the surveillance network or not. Most of the work that has been conducted on person re-identification problem uses a single dataset, in which the training and test data are coming from the same source. However, as we have shown in this work, there is a strong bias among the person re-identification datasets, therefore, a method that has been trained and optimized on a specific person re-identification dataset may not generalize well and perform successfully on the other datasets. This is a problem for many real-world applications, since it is not feasible to collect and annotate sufficient amount of data from the target application to train or fine-tune a deep convolutional neural network model. Taking this issue into account, in this work, we have focused on cross-dataset person re-identification problem and first explored and analyzed in detail the use of the state-of-the-art deep convolutional neural network architectures, namely AlexNet, VGGNet, GoogLeNet, ResNet, and DenseNet that have been developed for generic image classification task. These deep CNN models have been adapted to the person re-identification domain by fine-tuning them for each human body part separately, as well as on the entire body, with the two relatively large person re-identification datasets: CUHK03 and Market-1501. Then, the performance of each adapted model has been evaluated on two different publicly available datasets: VIPeR and PRID2011. We have shown that, even just a domain adaptation leads comparable results to the state-of-the-art cross-dataset approaches. Another point that we have addressed in this paper is context adaptation. It has been known that person re-identification approaches implicitly utilizes background as context information. Therefore, to have a consistent background across different camera views, we have employed the cycle-consistent generative adversarial network. We have shown that this further improves the performance.

Keywords

Person re-identification Context adaptation Domain adaptation Cross-dataset Convolutional neural networks CycleGAN 

Notes

References

  1. 1.
    Ahmed E, Jones M, Marks TK (2015) An improved deep learning architecture for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3908–3916Google Scholar
  2. 2.
    Barbosa IB, Cristani M, Caputo B, Rognhaugen A, Theoharis T (2017) Looking beyond appearances: synthetic training data for deep CNNs in re-identification. CoRR. arXiv:1701.03153
  3. 3.
    Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: CVPR09Google Scholar
  4. 4.
    Fan H, Zheng L, Yang Y (2017) Unsupervised person re-identification: clustering and fine-tuning. arXiv:1705.10444
  5. 5.
    Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9):1627–1645CrossRefGoogle Scholar
  6. 6.
    Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensemble of localized features. Comput. Vis.–ECCV 2008:262–275Google Scholar
  7. 7.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778Google Scholar
  8. 8.
    Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. CoRR. arXiv:1703.07737
  9. 9.
    Hirzer M, Beleznai C, Roth PM, Bischof H (2011) Person re-identification by descriptive and discriminative classification. In: Scandinavian conference on image analysis. Springer, pp 91–102Google Scholar
  10. 10.
    Hu Y, Yi D, Liao S, Lei Z, Li SZ (2014) Cross dataset person re-identification. In: Asian Conference on computer vision. Springer, pp 650–664Google Scholar
  11. 11.
    Hu J, Lu J, Tan YP (2015) Deep transfer metric learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 325–333Google Scholar
  12. 12.
    Huang G, Liu Z, Weinberger KQ, van der Maaten L (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, vol 1, p 3Google Scholar
  13. 13.
    Koestinger M, Hirzer M, Wohlhart P, Roth PM, Bischof H (2012) Large scale metric learning from equivalence constraints. In: 2012 IEEE Conference on computer vision and pattern recognition (CVPR). IEEE, pp 2288–2295Google Scholar
  14. 14.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105Google Scholar
  15. 15.
    Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 152–159Google Scholar
  16. 16.
    Liao S, Hu Y, Li S (2014) Joint dimension reduction and metric learning for person re-identificationGoogle Scholar
  17. 17.
    Ma AJ, Yuen PC, Li J (2013) Domain transfer support vector ranking for person re-identification without target camera label information. In: Proceedings of the IEEE international conference on computer vision, pp 3567–3574Google Scholar
  18. 18.
    Ma AJ, Li J, Yuen PC, Li P (2015) Cross-domain person reidentification using domain adaptation ranking svms. IEEE Trans Image Process 24(5):1599–1613MathSciNetCrossRefGoogle Scholar
  19. 19.
    McLaughlin N, Rincon JMD, Miller P (2015) Data-augmentation for reducing dataset bias in person re-identification. In: 2015 12th IEEE International conference on advanced video and signal based surveillance (AVSS), pp 1–6.  https://doi.org/10.1109/AVSS.2015.7301739
  20. 20.
    Nanda A, Chauhan DS, Sa KP, Bakshi S (2017) Illumination and scale invariant relevant visual features with hypergraph-based learning for multi-shot person re-identification. Multimedia Tools and Applications.  https://doi.org/10.1007/s11042-017-4875-7 CrossRefGoogle Scholar
  21. 21.
    Nanda A, Sa PK, Choudhury SK, Bakshi S, Majhi B (2017) A neuromorphic person re-identification framework for video surveillance. IEEE Access 5:6471–6482.  https://doi.org/10.1109/ACCESS.2017.2686438 Google Scholar
  22. 22.
    Peng P, Xiang T, Wang Y, Pontil M, Gong S, Huang T, Tian Y (2016) Unsupervised cross-dataset transfer learning for person re-identification. In: 2016 IEEE Conference on computer vision and pattern recognition (CVPR), pp 1306–1315.  https://doi.org/10.1109/CVPR.2016.146
  23. 23.
    Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252MathSciNetCrossRefGoogle Scholar
  24. 24.
    Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: International Conference on learning representations (ICLR)Google Scholar
  25. 25.
    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):1929–1958MathSciNetzbMATHGoogle Scholar
  26. 26.
    Sun Y, Zheng L, Deng W, Wang S (2017) Svdnet for pedestrian retrievalGoogle Scholar
  27. 27.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9Google Scholar
  28. 28.
    Torralba A, Efros AA (2011) Unbiased look at dataset bias. In: CVPR 2011, pp 1521–1528.  https://doi.org/10.1109/CVPR.2011.5995347
  29. 29.
    Wu Q (2017) Multi-scale convolutional network for person re-identification.  https://doi.org/10.2991/cnct-16.2017.115
  30. 30.
    Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1249–1258Google Scholar
  31. 31.
    Yi D, Lei Z, Liao S, Li SZ (2014) Deep metric learning for person re-identification. In: 2014 22nd International conference on pattern recognition (ICPR). IEEE, pp 34–39Google Scholar
  32. 32.
    Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Advances in neural information processing systems, pp 3320–3328Google Scholar
  33. 33.
    Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. In: IEEE International conference on computer visionGoogle Scholar
  34. 34.
    Zheng L, Yang Y, Hauptmann AG (2016) Person re-identification: past, present and future. CoRR. arXiv:1610.02984
  35. 35.
    Zheng Z, Zheng L, Yang Y (2017) Unlabeled samples generated by gan improve the person re-identification baseline in vitro CoRRGoogle Scholar
  36. 36.
    Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921–2929Google Scholar
  37. 37.
    Zhu JY, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networksGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Istanbul Technical UniversityIstanbulTurkey

Personalised recommendations