Re-identification enables the tracking of the person taken from different disjoint camera aspects either from online or retrospectively for recognition of his or her visual appearance. Here a new method is proposed for person re-identification, taking into consideration the pose of the person as the primary factor, with multiple features being extracted from significant portions. Then angle-based pose priority has applied for matching and identification more robust to viewpoint. Their proposed method helps to reduce the number of images which are redundant in the training phase as well as the number of matching process in the test phase. The strength of the proposed method is demonstrated on three different benchmark databases containing more than 1000 person-images under variations in illumination, viewpoint and occlusion. The experimental results show that the proposed approach provides a higher recognition rates for all the issues of identification process. Finally, the results prove the superiority of the proposed method over other re-identification methods both in terms of visual and quantitative comparisons.

References

1. 1)
  - 5. Poongothai, E., Suruliandi, A.: ‘Features analysis of person re-identification techniques’. Int. Conf. Computing Technologies and Intelligent Data Engineering, India, 2016.
2. 2)
  - 20. Cheng, D.S., Cristani, M., Stoppa, M., et al: ‘Custom pictorial structures for re-identification’, Int. British Machine Conf. Machine Vision, 2011, pp. 1–11.
3. 3)
  - 16. Kim, D.S., Kim, M., Kim, B.S., et al: ‘Histograms of local intensity differences for pedestrian classification in far-infrared images’, Electron. Lett., 2013, 49, (4), pp. 258–260.
4. 4)
  - 22. 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.
5. 5)
  - 4. Cheng, M.-H., Ho, M.-F., Huang, C.-L.: ‘Gait analysis for human identification through manifold learning and HMM’, Pattern Recognit., 2008, 41, (8), pp. 2541–2553.
6. 6)
  - 14. Liu, C., Gong, S., Loy, C.C., et al: ‘Evaluating feature importance for re-identification’, in Gong, S., Cristani, M., Yan, S., Loy, C.C. (Eds.) ‘Person re-identification’ (Springer Press, London, 2014), pp. 203–228.
7. 7)
  - 2. Mirmohamadsadeghi, L., Drygajlo, A.: ‘Palm vein recognition with local binary patterns and local derivative patterns’. Int. Conf. Biometrics, Washington, USA, 2011.
8. 8)
  - 17. Ye, M., Liang, C., Yu, Y., et al: ‘Person re-identification via ranking aggregation of similarity pulling and dissimilarity pushing’, IEEE Trans. Multimed., 2016, 18, (12), p. 2553.
9. 9)
  - 11. Ma, B., Su, Y., Jurie, F.: ‘Bicov: a novel image representation for person re-identification and face verification’. Int. Conf. Machine Vision, Guildford, UK, 2012.
10. 10)
  - 8. De, C.P., Felipe, R., Schwartz, W.R.: ‘CBRA: color-based ranking aggregation for person re-identification’. Int. Conf. Image Processing, QC, Canada, 2015.
11. 11)
  - 6. Eisenbach, M., Kolarow, A., Schenk, K., et al: ‘View invariant appearance-based person re-identification using fast online feature selection and score level fusion’. Int. Conf. Advanced Video and Signal-Based Surveillance, Beijing, China, 2012, pp. 184–190.
12. 12)
  - 3. Castro, F.M., Marín-Jiménez, M.J., Guil, N.: ‘Multimodal features fusion for gait, gender and shoes recognition’, Mach. Vis. Appl.', 2016, 27, (8), pp. 1213–1228.
13. 13)
  - 21. Satta, R., Fumera, G., Roli, F., et al: ‘A multiple component matching framework for person re-identification’. Int. Conf. Image Analysis and Processing, Berlin, Heidelberg, 2011, pp. 140–149.
14. 14)
  - 19. Mignon, A., Jurie, F.: ‘PCCA: a new approach for learning distances from sparse pairwise constraints’. Asian Conf. Computer Vision, South Korea, 2012.
15. 15)
  - 9. Tapaswi, M., Martin, B., et al: ‘‘Knock! Knock! Who is it?’ Probabilistic person identification in TV-series’. 2012 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), RI, USA, 2012.
16. 16)
  - 10. Kviatkovsky, I., Adam, A., Rivlin, E.: ‘Colour invariants for person re-identification’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (7), pp. 1622–1634.
17. 17)
  - 15. Slater, D., Healey, G.: ‘The illumination-invariant recognition of 3D objects using local color invariants’, IEEE Trans. Pattern Anal. Mach. Intell., 1996, 18, pp. 206–210.
18. 18)
  - 18. Cao, W., Han, H., Sun, X.K., et al: ‘Target re-identification based on adaptive incremental KISS measure learning’. Memetic Computing, 2016, pp. 1–8.
19. 19)
  - 7. Martinel, N., Micheloni, C., Foresti, GL.: ‘A pool of multiple person re-identification experts’, Pattern Recognit. Lett., 2016, 71, pp. 23–30.
20. 20)
  - 13. Pedagadi, S., Orwell, J., Velastin, S., et al: ‘Local Fisher discriminant analysis for pedestrian re-identification’. Int. Conf. Computer Vision and Pattern Recognition, OR, USA, 2013, pp. 3318–3325.
21. 21)
  - 12. Martinel, N., Micheloni, C.: ‘Person re-identification by modelling principal component analysis coefficients of image dissimilarities’, Electron. Lett., 2014, 50, (14), pp. 1000–1001.
22. 22)
  - 1. Guillaumin, M., Verbeek, J., Schmid, C.: ‘Is that you? Metric learning approaches for face identification’. 12th Int. Conf. Computer Vision, Kyoto, Japan, 2009, pp. 498–505.

Person re-identification based on pose angle estimation and multi-feature extraction

References

Related content