Existing person re-identification (re-id) models mainly focus on still-image-based module, namely matching person images across non-overlapping camera views. Since video sequence contains much more information than still images and can be easily achieved by tracking algorithms in practical applications, the video re-id has attracted increasing attention in recent years. Distance learning is crucial for a re-id system. However, the computed distances in traditional video-based methods are easily distracted by the randomness of data distribution, especially with small sample size for training. To preferably distinguish different people, a novel regularised hull distance learning video-based person re-id method is proposed. It is advantageous in two aspects: robustness is guaranteed due to expanded video samples by regularised affine hull with limited ones, discriminability is ensured due to penalised hard negative samples more severely. Hence, the discriminability and robustness of the learnt metric are strengthened. Comparisons with the state-of-the-art video-based methods as well as related methods on PRID 2011, iLIDS-VID and MARS datasets demonstrate the superiority of the authors’ method.

References

1. 1)
  - 17. Hirzer, M., Roth, P.M., Köstinger, M., et al: ‘Relaxed pairwise learned metric for person re-identification’. European Conf. on Computer Vision, Florence, Italy, 2012, pp. 780–793.
2. 2)
  - 21. Ye, M., Liang, C., Yu, Y., et al: ‘Person reidentification via ranking aggregation of similarity pulling and dissimilarity pushing’, IEEE Trans. Multimed., 2016, 18, (12), pp. 2553–2566.
3. 3)
  - 19. Weinberger, K.Q., Saul, L.K.: ‘Distance metric learning for large margin nearest neighbor classification’, J. Mach. Learn. Res., 2009, 10, pp. 207–244.
4. 4)
  - 22. Ye, M., Ma, A.J., Zheng, L., et al: ‘Dynamic label graph matching for unsupervised video re-identification’. Int. Conf. on Computer Vision (ICCV), Venice, Italy, 2017, pp. 5152–5160.
5. 5)
  - 29. Li, N., Jin, R., Zhou, Z.-H.: ‘Top rank optimization in linear time’. Advances in Neural Information Processing Systems, Montreal, Canada, 2014, pp. 1502–1510.
6. 6)
  - 36. Pedagadi, S., Orwell, J., Velastin, S., et al: ‘Local fisher discriminant analysis for pedestrian re-identification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Portland, OR, USA, 2013, pp. 3318–3325.
7. 7)
  - 14. Wu, Z., Li, Y., Radke, R.J.: ‘Viewpoint invariant human re-identification in camera networks using pose priors and subject-discriminative features’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37, (5), pp. 1095–1108.
8. 8)
  - 7. Ahmed, E., Jones, M., Marks, T.K.: ‘An improved deep learning architecture for person re-identification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Boston, MA, USA, 2015, pp. 3908–3916.
9. 9)
  - 31. Hirzer, M., Beleznai, C., Roth, P.M., et al: ‘Person re-identification by descriptive and discriminative classification’. Scandinavian Conf. on Image Analysis, Ystad, weden, 2011, pp. 91–102.
10. 10)
  - 42. Zheng, L., Shen, L., Tian, L., et al: ‘Scalable person reidentification: a benchmark’. Proc. of the IEEE Int. Conf. on Computer Vision, Santiago, Chile, 2015, pp. 1116–1124.
11. 11)
  - 24. Karanam, S., Li, Y., Radke, R.J.: ‘Person re-identification with discriminatively trained viewpoint invariant dictionaries’. Proc. of the IEEE Int. Conf. on Computer Vision, Santiago, Chile, 2015, pp. 4516–4524.
12. 12)
  - 20. Dikmen, M., Akbas, E., Huang, T.S., et al: ‘Pedestrian recognition with a learned metric’. Asian Conf. on Computer Vision, Queenstown, New Zealand, 2010, pp. 501–512.
13. 13)
  - 10. Simonnet, D., Lewandowski, M., Velastin, S.A., et al: ‘Reidentification of pedestrians in crowds using dynamic time warping’. European Conf. on Computer Vision, Florence, Italy, 2012, pp. 423–432.
14. 14)
  - 35. He, K., Zhang, X., Ren, S., et al: ‘Deep residual learning for image recognition’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 770–778.
15. 15)
  - 39. Zhu, P., Zhang, L., Zuo, W., et al: ‘From point to set: extend the learning of distance metrics’. Proc. of the IEEE Int. Conf. on Computer Vision, Sydney, Australia, 2013, pp. 2664–2671.
16. 16)
  - 30. Boyd, S., Vandenberghe, L.: ‘Convex optimization’ (Cambridge university press, UK, 2004).
17. 17)
  - 9. Karanam, S., Li, Y., Radke, R.J.: ‘Sparse re-id: block sparsity for person reidentification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition Workshops, Boston, MA, USA, 2015, pp. 33–40.
18. 18)
  - 37. Li, Z., Chang, S., Liang, F., et al: ‘Learning locally-adaptive decision functions for person verification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Portland, OR, USA, 2013, pp. 3610–3617.
19. 19)
  - 12. Yang, M., Zhu, P., Van Gool, L., et al: ‘Face recognition based on regularized nearest points between image sets’. 2013 10th IEEE Int. Conf. and Workshops on Automatic Face and Gesture Recognition (FG), Shanghai, China, 2013, pp. 1–7.
20. 20)
  - 33. Klaser, A., Marszałek, M., Schmid, C.: ‘A spatio-temporal descriptor based on 3D-gradients’. BMVC 2008-19th British Machine Vision Conf., Newcastle, UK, 2008, pp. 1–10.
21. 21)
  - 16. Zhao, R., Ouyang, W., Wang, X.: ‘Unsupervised salience learning for person re-identification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Portland, OR, USA, 2013, pp. 3586–3593.
22. 22)
  - 28. Wu, Y., Minoh, M., Mukunoki, M.: ‘Collaboratively regularized nearest points for set based recognition’. Proc. of the British Machine Vision Conf. (BMVC), Bristol, UK, 2013, vol. 2, no. 3, p. 5.
23. 23)
  - 34. Liao, S., Hu, Y., Zhu, X., et al: ‘Person re-identification by local maximal occurrence representation and metric learning’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Boston, MA, USA, 2015, pp. 2197–2206.
24. 24)
  - 13. Gray, D., Tao, H.: ‘Viewpoint invariant pedestrian recognition with an ensemble of localized features’. European Conf. on Computer Vision, Marseille, France, 2008, pp. 262–275.
25. 25)
  - 4. Ye, M., Wang, Z., Lan, X., et al: ‘Visible thermal person re-identification via dual-constrained top-ranking’. Int. Joint Conf. on Artificial Intelligence, Brisbane, Australia, 2018, pp. 1092–1099.
26. 26)
  - 18. Koestinger, M., Hirzer, M., Wohlhart, P., et al: ‘Large scale metric learning from equivalence constraints’. 2012 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, 2012, pp. 2288–2295.
27. 27)
  - 27. Wu, Y., Mukunoki, M., Minoh, M.: ‘Locality-constrained collaborative sparse approximation for multiple-shot person re-identification’. Asian Conf. on Pattern Recognition (ACPR), Naha, Japan, 2013, pp. 140–144.
28. 28)
  - 41. McLaughlin, N., Martinez del Rincon, J., Miller, P.: ‘Recurrent convolutional network for video-based person re-identification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 1325–1334.
29. 29)
  - 8. Wang, T., Gong, S., Zhu, X., et al: ‘Person re-identification by video ranking’. European Conf. on Computer Vision, Zurich, Switzerland, 2014, pp. 688–703.
30. 30)
  - 23. Lin, Z., Jiang, Z., Davis, L.S.: ‘Recognizing actions by shape-motion prototype trees’. 2009 IEEE 12th Int. Conf. on Computer Vision, Kyoto, Japan, 2009, pp. 444–451.
31. 31)
  - 40. Chung, D., Tahboub, K., Delp, E.J.: ‘A two stream Siamese convolutional neural network for person re-identification’. The IEEE Int. Conf. on Computer Vision (ICCV), Venice, Italy, 2017.
32. 32)
  - 1. Farenzena, M., Bazzani, L., Perina, A., et al: ‘Person reidentification by symmetry-driven accumulation of local features’. 2010 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, 2010, pp. 2360–2367.
33. 33)
  - 11. You, J., Wu, A., Li, X., et al: ‘Top-push video-based person reidentification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 1345–1353.
34. 34)
  - 15. Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’, Int. J. Comput. Vis., 2004, 60, (2), pp. 91–110.
35. 35)
  - 32. Zheng, L., Bie, Z., Sun, Y., et al: ‘Mars: a video benchmark for large-scale person re-identification’. European Conf. on Computer Vision, Amsterdam, Netherlands, 2016, pp. 868–884.
36. 36)
  - 2. Gou, M., Karanam, S., Liu, W., et al: ‘DukeMTMC4ReID: a large-scale multi-camera person re-identification dataset’. Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 2017, pp. 1425–1434.
37. 37)
  - 25. Li, Y., Wu, Z., Radke, R.J.: ‘Multi-shot re-identification with random-projection- based random forests’. 2015 IEEE Winter Conf. on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2015, pp. 373–380.
38. 38)
  - 3. Ye, M., Lan, X., Li, J., et al: ‘Hierarchical discriminative learning for visible thermal person re-identification’, 2018.
39. 39)
  - 6. Zhao, R., Ouyang, W., Wang, X.: ‘Learning mid-level filters for person reidentification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, Ohio, USA, 2014, pp. 144–151.
40. 40)
  - 5. Zheng, W.-S., Li, X., Xiang, T., et al: ‘Partial person reidentification’. Proc. of the IEEE Int. Conf. on Computer Vision, Santiago, Chile, 2015, pp. 4678–4686.
41. 41)
  - 26. Wu, Y., Minoh, M., Mukunoki, M., et al: ‘Collaborative sparse approximation for multiple-shot across-camera person re-identification’. 2012 IEEE Ninth Int. Conf. on Advanced Video and Signal-Based Surveillance (AVSS), Beijing, China, 2012, pp. 209–214.
42. 42)
  - 38. Engel, C., Baumgartner, P., Holzmann, M., et al: ‘Person re-identification by support vector ranking’. British Machine Vision Conf., BMVC 2010, Aberystwyth, UK, 31 August–3 September 2010, pp. 1–11.

Video-based person re-identification based on regularised hull distance learning

References

Related content