Survey on person re-identification based on deep learning
- Author(s): Kejun Wang 1 ; Haolin Wang 1 ; Meichen Liu 1 ; Xianglei Xing 1 ; Tian Han 2
-
-
View affiliations
-
Affiliations:
1:
College of Automation, Harbin Engineering University , No. 145 Nantong Street, Nangang District, Harbin , People's Republic of China ;
2: Department of Statistics, University of California, Los Angeles , Los Angeles, CA 90095 , USA
-
Affiliations:
1:
College of Automation, Harbin Engineering University , No. 145 Nantong Street, Nangang District, Harbin , People's Republic of China ;
- Source:
Volume 3, Issue 4,
December
2018,
p.
219 – 227
DOI: 10.1049/trit.2018.1001 , Online ISSN 2468-2322
Person re-identification (Re-ID) is a fundamental subject in the field of the computer vision technologies. The traditional methods of person Re-ID have difficulty in solving the problems of person illumination, occlusion and attitude change under complex background. Meanwhile, the introduction of deep learning opens a new way of person Re-ID research and becomes a hot spot in this field. This study reviews the traditional methods of person Re-ID, then the authors focus on the related papers about different person Re-ID frameworks on the basis of deep learning, and discusses their advantages and disadvantages. Finally, they propose the direction of further research, especially the prospect of person Re-ID methods based on deep learning.
Inspec keywords: computer vision; image representation; image matching; feature extraction; learning (artificial intelligence)
Other keywords: metric-based method; occlusion; person Re-ID frameworks; person reidentification; person matching; computer vision technologies; deep learning; person representation; person Re-ID methods; attitude change; person Re-ID research; person illumination; feature-based method
Subjects: Knowledge engineering techniques; Computer vision and image processing techniques; Image recognition
References
-
-
1)
-
[5]. Liu, K., Ma, B., Zhang, W., et al: ‘A spatio-temporal appearance representation for video-based pedestrian Re-identification’. IEEE Int. Conf. on Computer Vision, Santiago, Chile, 2015, pp. 3810–3818.
-
-
2)
-
[60]. Fei-Fei, L., Fergus, R., Perona, P.: ‘One-shot learning of object categories’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (4), pp. 594–611 (doi: 10.1109/TPAMI.2006.79).
-
-
3)
-
[35]. Li, W., Zhu, X., Gong, S.: ‘Harmonious attention network for person re-identification’, arXiv:1802.08122v1, 2018.
-
-
4)
-
[18]. Geng, Y., Hu, H.-M., Zeng, G.: ‘A person re-identification algorithm by exploiting region-based feature salience’, J. Vis. Commun. Image Represent., 2015, 29, (C), pp. 89–102 (doi: 10.1016/j.jvcir.2015.02.001).
-
-
5)
-
[51]. Dai, J., Zhang, P., Lu, H., et al: ‘Video person re-identification by temporal residual learning’, arXiv:1802.07918, 2018.
-
-
6)
-
[11]. Chakraborty, A., Das, A., Roychowdhury, A.: ‘Network consistent data association’, IEEE Trans. Pattern Anal. Mach. Intell., 2016, 38, (9), pp. 1859–1871 (doi: 10.1109/TPAMI.2015.2491922).
-
-
7)
-
[40]. Su, C., Li, J., Zhang, S., et al: ‘Pose-driven deep convolutional model for person re-identification’. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 3980–3989.
-
-
8)
-
[54]. Ma, L., Jia, X., Sun, Q., et al: ‘Pose guided person image generation’, arXiv:1705.09368, 2017.
-
-
9)
-
[61]. Zheng, L., Zhang, H., Sun, S., et al: ‘Person re-identification in the wild’. IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2017, pp. 3346–3355.
-
-
10)
-
[34]. Liu, X., Zhao, H., Tian, M., et al: ‘Hydraplus-net: attentive deep features for pedestrian analysis’. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 350–359.
-
-
11)
-
[26]. Lecun, Y., Bottou, L., Bengio, Y., et al: ‘Gradient-based learning applied to document recognition’. Proc. of the IEEE, Oakland, 1998, pp. 2278–2324.
-
-
12)
-
[52]. Goodfellow, I.J., Pougetabadie, J., Mirza, M., et al: ‘Generative adversarial networks’, Adv. Neural. Inf. Process. Syst., 2014, 3, pp. 2672–2680.
-
-
13)
-
[49]. Liu, H., Feng, J., Qi, M., et al: ‘End-to-end comparative attention networks for person re-identification’, IEEE Trans. Image Process., 2017, PP, (99), pp. 1–1.
-
-
14)
-
[10]. Bak, S., Carr, P.: ‘One-shot metric learning for person re-identification’. IEEE Conf. on Computer Vision and Pattern Recognition, Hawaii, USA, 2017, pp. 1571–1580.
-
-
15)
-
[37]. Zheng, L., Huang, Y., Lu, H., et al: ‘Pose invariant embedding for deep person re-identification’, arXiv preprint arXiv:1701.07732, 2017.
-
-
16)
-
[13]. 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.
-
-
17)
-
[23]. Chen, J., Wang, Y., Qin, J., et al: ‘Fast person re-identification via cross-camera semantic binary transformation’. IEEE Conf. on Computer Vision and Pattern Recognition, Hawaii, USA, 2017, pp. 3873–3882.
-
-
18)
-
[29]. Li, S., Chen, L.: ‘Person re-identification based on locally deep matching’, Appl. Res. Comput., 2017, 34, (4), pp. 1235–1238. (In Chinese).
-
-
19)
-
[62]. Lin, J., Liang, L., Ren, L., et al: ‘Consistent-aware deep learning for person re-identification in a camera network’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Hawaii, USA, 2017, pp. 5771–5780.
-
-
20)
-
[7]. Li, D., Chen, X., Zhang, Z., et al: ‘Learning deep context-aware features over body and latent parts for person re-identification’. IEEE Conf. on Computer Vision and Pattern Recognition, Hawaii, USA, 2017, pp. 384–393.
-
-
21)
-
[42]. Ren, S., He, K., Girshick, R., et al: ‘Faster R-CNN: towards real-time object detection with region proposal networks’. Int. Conf. on Neural Information Processing Systems, Palais des Congrès de Montréal, 2015, pp. 91–99.
-
-
22)
-
[32]. Ahmed, E., Jones, M., Marks, T. K.: ‘An improved deep learning architecture for person re-identification’. The IEEE Conf. on Computer Vision and Pattern Recognition, Boston, Massachusetts, USA, 2015, pp. 3908–3916.
-
-
23)
-
[48]. Wu, L., Shen, C., Hengel, A.: ‘Deep recurrent convolutional networks for video-based person re-identification: an end-to-end approach’, arXiv preprint arXiv:1606.01609, 2016.
-
-
24)
-
[55]. Quan, T.M., Hilderbrand, D.G.C., Jeong, W. K.: ‘Fusionnet: a deep fully residual convolutional neural network for image segmentation in connectomics’, arXiv:1612.05360, 2016.
-
-
25)
-
[21]. Yu, H.X., Wu, A., Zheng, W. S.: ‘Cross-view asymmetric metric learning for unsupervised person re-identification’, arXiv preprint arXiv:1708.08062, 2017, pp. 994–1002.
-
-
26)
-
[25]. Yi, D., Lei, Z., Liao, S., et al: ‘Deep metric learning for person re-identification’. Int. Conf. on Pattern Recognition, Columbus, OH, USA, 2014, pp. 34–39.
-
-
27)
-
[8]. Zheng, L., Shen, L., Tian, L., et al: ‘Scalable person re-identification: a benchmark’. IEEE Int. Conf. on Computer Vision, Santiago, Chile, 2016, pp. 1116–1124.
-
-
28)
-
[1]. Bedagkar-Gala, A., Shah, S. K.: ‘A survey of approaches and trends in person re-identification’, Image Vis. Comput., 2014, 32, (4), pp. 270–286 (doi: 10.1016/j.imavis.2014.02.001).
-
-
29)
-
[56]. Yin, Z., Zheng, W.S., Wu, A., et al: ‘Adversarial attribute-image person re-identification’, arXiv:1712.01493, 2017.
-
-
30)
-
[16]. Chen, L., Chen, H., Li, S., et al: ‘Person Re-identification by color distribution fields’, J. Chi. Comput. Syst., 2017, 38, (6), pp. 1404–1408 (in Chinese).
-
-
31)
-
[6]. Zheng, W. S., Gong, S., Xiang, T.: ‘Associating groups of people’. British Machine Vision Conf., BMVC 2009, Proc. DBLP, 2009, London, UK, 7–10 September 2009.
-
-
32)
-
[47]. Mclaughlin, N., Rincon, J.M.D., Miller, P.: ‘Recurrent convolutional network for video-based person re-identification’. IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 1325–1334.
-
-
33)
-
[9]. Jose, C., Fleuret, F.: ‘Scalable metric learning via weighted approximate rank component analysis’. European Conf. on Computer Vision, Amsterdam, The Netherlands, 2016, pp. 875–890.
-
-
34)
-
[4]. You, J., Wu, A., Li, X., et al: ‘Top-push video-based person re-identification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 1345–1353.
-
-
35)
-
[50]. Xu, S., Cheng, Y., Gu, K., et al: ‘Jointly attentive spatial-temporal pooling networks for video-based person re-identification’. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 4743–4752.
-
-
36)
-
[45]. Liao, W., Yang, M.Y., Zhan, N., et al: ‘Triplet-based deep similarity learning for person re-identification’, 2018.
-
-
37)
-
[39]. He, K., Zhang, X., Ren, S., et al: ‘Deep residual learning for image recognition’. Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 770–778.
-
-
38)
-
[24]. Li, W., Zhao, R., Xiao, T., et al: ‘DeepReID: deep filter pairing neural network for person re-identification’. Comput. Vis. Pattern Recognit., 2014, pp. 152–159.
-
-
39)
-
[36]. Jaderberg, M., Simonyan, K., Zisserman, A.: ‘Spatial transformer networks’. Adv. Neural. Inf. Process. Syst., Istanbul, Turkey, 2015, pp. 2017–2025.
-
-
40)
-
[3]. Liu, H., Jie, Z., Jayashree, K., et al: ‘Video-based person Re-identification with accumulative motion context’, IEEE Trans. Circuits Syst. Video Technol., 2017, PP, (99), pp. 1–1.
-
-
41)
-
20. Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’, Int. J. Comput. Vis., 2004, 60, pp. 91–110 (doi: 10.1023/B:VISI.0000029664.99615.94).
-
-
42)
-
[46]. Kuhn, G., Watrous, R.L., Ladendorf, B.: ‘Connected recognition with a recurrent network’, Speech Commun., 1990, 9, (1), pp. 41–48 (doi: 10.1016/0167-6393(90)90044-A).
-
-
43)
-
[27]. Li, W., Zhao, R., Xiao, T., et al: ‘Deepreid: deep filter pairing neural network for person re-identification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 152–159.
-
-
44)
-
[30]. Felzenszwalb, P.F., Girshick, R.B., Mcallester, D., et al: ‘Object detection with discriminatively trained part-based models’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 47, (2), pp. 6–7.
-
-
45)
-
[19]. Layne, R., Hospedales, T.M., Gong, S., et al: ‘Person re-identification by attributes’, BMVC, London, UK, 2012, vol. 2, (3), p. 8.
-
-
46)
-
[15]. Paisitkriangkrai, S., Shen, C., van den Hengel, A.: ‘Learning to rank in person re-identification with metric ensembles’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Boston, Massachusetts, USA, 2015, pp. 1846–1855.
-
-
47)
-
[53]. Zheng, Z., Zheng, L., Yang, Y.: ‘Unlabeled samples generated by GAN improve the person re-identification baseline in vitro’. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 3774–3782.
-
-
48)
-
[20]. Weinberger, K.Q., Saul, L. K.: ‘Distance metric learning for large margin nearest neighbor classification’. JMLR.org, 2009, 10, (1), pp. 207–244.
-
-
49)
-
[58]. Sun, Y., Zheng, L., Deng, W., et al: ‘SVDNet for pedestrian retrieval’. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 3820–3828.
-
-
50)
-
[17]. Yang, M., Wan, W., Hou, L., et al: ‘Person re-identification using human salience based on multi-feature fusion’. Int. Conf. on Smart and Sustainable City and Big Data, Shanghai, China, 2016, pp. 1–5.
-
-
51)
-
[31]. Varior, R.R., Haloi, M., Wang, G.: ‘Gated Siamese convolutional neural network architecture for human re-identification’. European Conf. on Computer Vision, Amsterdam, The Netherlands, 2016, pp. 791–808.
-
-
52)
-
5. Hinton, G.E., Salakhutdinov, R.R.: ‘Reducing the dimensionality of data with neural networks’, Science, 2006, 313, (5786), pp. 504–507 (doi: 10.1126/science.1127647).
-
-
53)
-
[28]. Cheng, D., Gong, Y., Zhou, S., et al: ‘Person re-identification by multi-channel parts-based CNN with improved triplet loss function’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 1335–1344.
-
-
54)
-
[57]. Yan, Y., Ni, B., Song, Z., et al: ‘Person re-identification via recurrent feature aggregation’. European Conf. on Computer Vision, 2016, pp. 701–716.
-
-
55)
-
[33]. Qian, X., Fu, Y., Jiang, Y.G., et al: ‘Multi-scale deep learning architectures for person re-identification’. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 5409–5418.
-
-
56)
-
[59]. Revaud, J., Weinzaepfel, P., Harchaoui, Z., et al: ‘Epicflow: edge-preserving interpolation of correspondences for optical flow’. Computer Vision and Pattern Recognition, Boston, Massachusetts, USA, 2015, pp. 1164–1172.
-
-
57)
-
[12]. Liao, S., Hu, Y., Zhu, X., et al: ‘Person re-identification by local maximal occurrence representation and metric learning’, Computer Vision and Pattern Recognition, Boston, Massachusetts, USA, 2015, pp. 2197–2206.
-
-
58)
-
[43]. Xiao, T., Li, H., Ouyang, W., et al: ‘Learning deep feature representations with domain guided dropout for person re-identification’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 1249–1258.
-
-
59)
-
[22]. Zhong, Z., Zheng, L., Cao, D., et al: ‘Re-ranking person re-identification with k-reciprocal encoding’, The IEEE Conf. on Computer Vision and Pattern Recognition, Hawaii, USA, 2017, pp. 318–1327.
-
-
60)
-
[44]. Su, C., Zhang, S., Xing, J., et al: ‘Deep attributes driven multi-camera person re-identification’. European Conf. on Computer Vision, Amsterdam, The Netherlands, 2016, pp. 475–491.
-
-
61)
-
[41]. Zhao, H., Tian, M., Sun, S., et al: ‘Spindle net: person re-identification with human body region guided feature decomposition and fusion’. Computer Vision and Pattern Recognition, Hawaii, USA, 2017, pp. 1077–1085.
-
-
62)
-
[38]. Dong, S.C., Cristani, M., Stoppa, M., et al: ‘Custom pictorial structures for re-identification’. British Machine Vision Conf., Dundee, UK, 2011, pp. 68.1–68.11.
-
-
1)