access icon free Training approach using the shallow model and hard triplet mining for person re-identification

© The Institution of Engineering and Technology
Received 19/03/2019, Accepted 16/09/2019, Revised 09/08/2019, Published 01/10/2019

Multi-target tracking in a non-overlapping camera network is an active research field, and one of the important problems in it is the person re-identification problem. In this study, the authors propose an approach to improve the performance of the backbone model in the person re-identification. Their approach focuses on training a fusion model with a shallow model and making hard triplets with relationship matrices quickly and efficiently. The proposed approach is simple, but it improves the performance of the backbone. In addition, the hard triplet mining in their process is much faster than the conventional approach. Experimental evaluation shows that the proposed approach can improve the performances of the backbone model. The proposed approach improves rank-1 and mean average precision (mAP) performance by more than 12.54 and 15.44%, respectively, over the backbone models in the Market1501 and DukeMTMC-reID dataset. The approach also achieves competitive performances compared with state-of-the-art approaches.

Inspec keywords: data mining; matrix algebra; sensor fusion; learning (artificial intelligence); image matching; target tracking; cameras; neural nets

Other keywords: nonoverlapping camera network; shallow model; mAP performance; rank-1 performance; multitarget tracking; person re-identification problem; relationship matrices; hard triplet mining; backbone model; Market1501 dataset; DukeMTMC-reID dataset; fusion model

Subjects: Neural computing techniques; Algebra; Image recognition; Data handling techniques; Algebra; Computer vision and image processing techniques; Image sensors; Sensor fusion

References

    1. 1)
      • 10. Zhao, R., Ouyang, W., Wang, X.: ‘Person re-identification by salience matching’. Proc. IEEE Int. Conf. on Computer Vision, Sydney, Australia, 2013, pp. 2528–2535.
    2. 2)
      • 23. Li, W., Zhu, X., Gong, S.: ‘Person re-identification by deep joint learning of multi-loss classification’, arXiv preprint arXiv:1705.04724, 2017.
    3. 3)
      • 15. Zheng, Z., Zheng, L., Yang, Y.: ‘A discriminatively learned CNN embedding for person reidentification’, ACM Trans. Multimed. Comput. Commun. Appl., 2018, 14, (1), p. 13.
    4. 4)
      • 44. Barbosa, I.B., Cristani, M., Caputo, B., et al: ‘Looking beyond appearances: synthetic training data for deep CNNs in re-identification’, Comput. Vis. Image Underst., 2018, 167, pp. 50–62.
    5. 5)
      • 13. Wei, L., Shah, S.K.: ‘Person re-identification with spatial appearance group feature’. 2016 IEEE Symp. on Technologies for Homeland Security (HST), Waltham, USA, 2016, pp. 1–6.
    6. 6)
      • 45. Liu, Y., Sheng, H., Zheng, Y., et al: ‘GDMN: group decision-making network for person re-identification’, IEEE Access, 2018, 6, pp. 64169–64181.
    7. 7)
      • 38. Kingma, D.P., Ba, J.: ‘Adam: a method for stochastic optimization’, arXiv preprint arXiv:1412.6980, 2014.
    8. 8)
      • 37. Glorot, X., Bengio, Y.: ‘Understanding the difficulty of training deep feedforward neural networks’. Proc. 13th Int. Conf. on Artificial Intelligence and Statistics, Amsterdam, Netherlands, 2010, pp. 249–256.
    9. 9)
      • 43. Lin, J., Ren, L., Lu, J., et al: ‘Consistent-aware deep learning for person re-identification in a camera network’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017, vol. 6.
    10. 10)
      • 24. Wu, S., Zhong, S., Liu, Y.: ‘Deep residual learning for image steganalysis’, Multimedia Tools Appl., 2018, 77, (9), pp. 10437–10453.
    11. 11)
      • 31. Hermans, A., Beyer, L., Leibe, B.: ‘In defense of the triplet loss for person re-identification’, arXiv preprint arXiv:1703.07737, 2017.
    12. 12)
      • 17. Chen, W., Chen, X., Zhang, J., et al: ‘Beyond triplet loss: a deep quadruplet network for person re-identification’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 2017, vol. 2.
    13. 13)
      • 36. Ristani, E., Solera, F., Zou, R., et al: ‘Performance measures and a data set for multi-target, multi-camera tracking’. European Conf. on Computer Vision workshop on Benchmarking Multi-Target Tracking, 2016.
    14. 14)
      • 28. Zhong, Z., Zheng, L., Cao, D., et al: ‘Re-ranking person re-identification with k-reciprocal encoding’. 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 2017, pp. 3652–3661.
    15. 15)
      • 6. Gordo, A., Almazan, J., Revaud, J., et al: ‘End-to-end learning of deep visual representations for image retrieval’, Int. J. Comput. Vis., 2017, 124, (2), pp. 237–254.
    16. 16)
      • 48. Tian, M., Yi, S., Li, H., et al: ‘Eliminating background-bias for robust person re-identification’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018, pp. 5794–5803.
    17. 17)
      • 9. 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), Rhode Island, USA, 2012, pp. 2288–2295.
    18. 18)
      • 42. Oh, S.H., Han, S.-W., Choi, B.-S., et al: ‘Deep feature learning for person re-identification in a large-scale crowdsourced environment’, J. Supercomput., 2018, 74, (12), pp. 6753–6765.
    19. 19)
      • 53. Jiao, F., Bhanu, B.: ‘Deepagent: an algorithm integration approach for person re-identification’. 2018 25th IEEE Int. Conf. on Image Processing (ICIP), Athens, Greece, 2018, pp. 853–857.
    20. 20)
      • 40. Zhou, S., Wang, J., Wang, J., et al: ‘Point to set similarity based deep feature learning for person reidentification’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 2017, vol. 6.
    21. 21)
      • 39. Ustinova, E., Ganin, Y., Lempitsky, V.: ‘Multi-region bilinear convolutional neural networks for person re-identification’. 2017 14th IEEE Int. Conf. on Advanced Video and Signal Based Surveillance (AVSS), Lecce, Italy, 2017, pp. 1–6.
    22. 22)
      • 8. Yu, Q., Chang, X., Song, Y.Z., et al: ‘The devil is in the middle: exploiting mid-level representations for cross-domain instance matching’, arXiv preprint arXiv:1711.08106, 2017.
    23. 23)
      • 50. Liu, Y., Zhang, Y., Chi, J.: ‘Bag of local features for person re-identification on large-scale datasets’, J. Electron. Imaging, 2018, 27, (5), p. 053041.
    24. 24)
      • 5. Lin, D.T., Huang, K.Y.: ‘Collaborative pedestrian tracking and data fusion with multiple cameras’, IEEE Trans. Inf. Forensics Sec., 2011, 6, (4), pp. 1432–1444.
    25. 25)
      • 33. Felzenszwalb, P.F., Girshick, R.B., McAllester, D., et al: ‘Object detection with discriminatively trained part-based models’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (9), pp. 1627–1645.
    26. 26)
      • 21. Li, W., Zhao, R., Xiao, T., et al: ‘Deepreid: deep filter pairing neural network for person re-identification’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Ohio, USA, 2014, pp. 152–159.
    27. 27)
      • 18. Ahmed, E., Jones, M., Marks, T.K.: ‘An improved deep learning architecture for person re-identification’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Boston, USA, 2015, pp. 3908–3916.
    28. 28)
      • 51. Liao, S., Hu, Y., Zhu, X., et al: ‘Person re-identification by local maximal occurrence representation and metric learning’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Boston, USA, 2015, pp. 2197–2206.
    29. 29)
      • 30. Harwood, B., Vijay Kumar Carneiro, B.G.G., et al: ‘Smart mining for deep metric learning’, Space, 2017, 9, (13), p. 22.
    30. 30)
      • 12. Corvee, E., Bremond, F., Thonnat, M., et al: ‘Person re-identification using spatial covariance regions of human body parts’. 2010 Seventh IEEE Int. Conf. on Advanced Video and Signal Based Surveillance (AVSS), Boston, USA, 2010, pp. 435–440.
    31. 31)
      • 11. 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.
    32. 32)
      • 26. Zheng, Z., Zheng, L., Yang, Y.: ‘Pedestrian alignment network for large-scale person re-identification’, arXiv preprint arXiv:1707.00408, 2017.
    33. 33)
      • 32. Schroff, F., Kalenichenko, D., Philbin, J.: ‘FaceNet: a unified embedding for face recognition and clustering’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Boston, USA, 2015, pp. 815–823.
    34. 34)
      • 16. Cheng, D., Gong, Y., Zhou, S., et al: ‘Person re-identification by multi-channel parts-based CNN with improved triplet loss function’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016, pp. 1335–1344.
    35. 35)
      • 3. 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, USA, 2010, pp. 2360–2367.
    36. 36)
      • 27. Nguyen, N.B., Nguyen, V.H., Ngo, T.D., et al: ‘Person reidentification with mutual re-ranking’, Vietnam J. Comput. Sci., 2017, 4, (4), pp. 233–244.
    37. 37)
      • 4. Bredereck, M., Jiang, X., Körner, M., et al: ‘Data association for multiobject tracking-by-detection in multi-camera networks’. 2012 Sixth Int. Conf. on Distributed Smart Cameras (ICDSC), Hong Kong, 2012, pp. 1–6.
    38. 38)
      • 22. Su, C., Li, J., Zhang, S., et al: ‘Pose-driven deep convolutional model for person re-identification’. 2017 IEEE Int. Conf. on Computer Vision (ICCV), Venice, Italy, 2017, pp. 3980–3989.
    39. 39)
      • 29. Zhong, Z., Zheng, L., Kang, G., et al: ‘Random erasing data augmentation’, arXiv preprint arXiv:1708.04896, 2017.
    40. 40)
      • 7. Yu, Q., Liu, F., Song, Y.Z., et al: ‘Sketch me that shoe’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016, pp. 799–807.
    41. 41)
      • 47. Liu, J., Ni, B., Yan, Y., et al: ‘Pose transferrable person re-identification’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018, pp. 4099–4108.
    42. 42)
      • 46. Zhao, H., Tian, M., Sun, S., et al: ‘Spindle net: person re-identification with human body region guided feature decomposition and fusion’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Honolulu, Hawaii, 2017, pp. 1077–1085.
    43. 43)
      • 2. Lin, D.T., Wu, K.Y.: ‘Wide area object tracking using multiple cameras with mixed configuration of over-lapping and non-overlapping FOV’, Int. J. Multimed. Ubiquit. Eng., 2016, 11, (3), pp. 239–248.
    44. 44)
      • 25. Deng, J., Dong, W., Socher, R., et al: ‘ImageNet: a large-scale hierarchical image database’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Miami, USA, 2009, pp. 248–255.
    45. 45)
      • 52. Zheng, L., Yang, Y., Hauptmann, A.G.: ‘Person re-identification: past, present and future’, arXiv preprint arXiv:1610.02984, 2016.
    46. 46)
      • 41. Chen, Y.-C., Zhu, X., Zheng, W.-S., et al: ‘Person re-identification by camera correlation aware feature augmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2018, 40, (2), pp. 392–408.
    47. 47)
      • 20. Varior, R.R., Shuai, B., Lu, J., et al: ‘A Siamese long short-term memory architecture for human re-identification’. European Conf. on Computer Vision, 2016, pp. 135–153.
    48. 48)
      • 19. Yi, D., Lei, Z., Liao, S., et al: ‘Deep metric learning for person reidentification’. 2014 22nd Int. Conf. on Pattern Recognition (ICPR), Stockholm, Sweden, 2014, pp. 34–39.
    49. 49)
      • 14. Zhou, J., Yu, P., Tang, W., et al: ‘Efficient online local metric adaptation via negative samples for person reidentification’. IEEE Int. Conf. on Computer Vision (ICCV), Venice, Italy, 2017, vol. 2, p. 7.
    50. 50)
      • 35. Zheng, Z., Zheng, L., Yang, Y.: ‘Unlabeled samples generated by GAN improve the person re-identification baseline in vitro’, arXiv preprint arXiv:1701.07717, 2017, vol. 3.
    51. 51)
      • 34. Zheng, L., Shen, L., Tian, L., et al: ‘Scalable person reidentification: a benchmark’. Proc. IEEE Int. Conf. on Computer Vision, Santiago, Chile, 2015, pp. 1116–1124.
    52. 52)
      • 1. Chen, K.W., Lai, C.C., Lee, P.J., et al: ‘Adaptive learning for target tracking and true linking discovering across multiple non-overlapping cameras’, IEEE Trans. Multimed., 2011, 13, (4), pp. 625–638.
    53. 53)
      • 54. Xiao, T., Li, S., Wang, B., et al: ‘Joint detection and identification feature learning for person search’. 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 2017, pp. 3376–3385.
    54. 54)
      • 49. Lin, Y., Zheng, Z., Zhang, H., et al: ‘Bayesian query expansion for multi-camera person re-identification’, Pattern Recognit. Lett., 2018, 15, pp. 1–9.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2019.0334
Loading

Related content

content/journals/10.1049/iet-ipr.2019.0334
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading