Skip to main content
SpringerLink
Log in

Possibilistic rank-level fusion method for person re-identification

  • S.I. : Emerging trends in AI & ML
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The fusion of multiple classifiers may generate a more efficient classification than each of the individual ones. Possibility theory is particularly efficient in combining multiple information sources providing incomplete, imprecise, and conflicting knowledge. In this work, we focus on the enhancement of the person re-identification performance by combining multiple deep learning classifiers’ outputs trained on different body part streams. We propose a possibilistic rank-level late fusion method that allows us to deal with imprecision and uncertainty factors that may arise in the predictions of poor classifiers. The proposed fusion method takes place in the framework of possibility theory and combines the ranking identities generated by each classifier based on their possibility distributions. This fusion method can take advantage of the complementary information given by each classifier, even the weak ones. We demonstrate the effectiveness of our proposed fusion method by presenting experimental results on two benchmark datasets (Market-1501 and DukeMTMC-reID). The obtained results show consistent accuracy improvements in comparison with state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Gong S, Cristani M, Yan S, Loy CC (2014) Person re-identification. Springer, Berlin

    Book  Google Scholar 

  2. Cho Y-J, Yoon K-J (2016) Improving person re-identification via pose-aware multi-shot matching. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1354–1362

  3. Huang Y, Zha Z-J, Fu X, Zhang W (2019) Illumination-invariant person re-identification. In: ACM international conference on multimedia, pp 365–373

  4. Karanam S, Li Y, Radke RJ (2015) Person re-identification with discriminatively trained viewpoint invariant dictionaries. In: IEEE international conference on computer vision, pp 4516–4524

  5. Huang H, Li D, Zhang Z, Chen X, Huang K (2018) Adversarially occluded samples for person re-identification. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 5098–5107

  6. Tian M, Yi S, Li H, Li S, Zhang X, Shi J, Yan J, Wang X (2018) Eliminating background-bias for robust person re-identification. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 5794–5803

  7. Ghorbel M, Ammar S, Kessentini Y, Jmaiel M (2019) Improving person re-identification by background subtraction using two-stream convolutional networks. In: Karray F, Campilho A, Yu A (eds) Image analysis and recognition. Springer International Publishing, Cham, pp 345–356

    Chapter  Google Scholar 

  8. Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identification. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 152–159

  9. Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1249–1258

  10. Varior RR, Haloi M, Wang G (2016) Gated siamese convolutional neural network architecture for human re-identification. In: European conference on computer vision. Springer, pp 791–808

  11. Zhong Z, Zheng L, Cao D, Li S (2017) Re-ranking person re-identification with k-reciprocal encoding. In: IEEE international conference on computer vision and pattern recognition (CVPR). IEEE, pp 1318–1327

  12. Yu R, Zhou Z, Bai S, Bai X (2017) Divide and fuse: a re-ranking approach for person re-identification. In: The British machine vision conference (BMVC). BMVA Press, pp 135.1–135.13

  13. Mansouri N, Ammar S, Kessentini Y (2019) Improving person re-identification by combining siamese convolutional neural network and re-ranking process. In: IEEE international conference on advanced video and signal based surveillance (AVSS). IEEE, pp 1–8

  14. Mansouri N, Ammar S, Kessentini Y (2021) Re-ranking person re-identification using attributes learning. Neural Comput Appl 1–17

  15. Wang P, Qing C, Xu X, Cai B, Jin J, Ren J (2018) Local-global extraction unit for person re-identification. In: International conference on brain inspired cognitive systems, pp 402–411

  16. Li D, Chen X, Zhang Z, Huang K (2017) Learning deep context-aware features over body and latent parts for person re-identification. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 384–393

  17. Huang Z, Yu Z, Li Y, Wang Y, Lin S, Sun D, Zhong Y, Cao H, Gregersen H (2019) Contribution-based multi-stream feature distance fusion method with k-distribution re-ranking for person re-identification. IEEE Access 7:35631–35644

    Article  Google Scholar 

  18. Quan R, Dong X, Wu Y, Zhu L, Yang Y (2019) Auto-reid: searching for a part-aware convnet for person re-identification. In: IEEE international conference on computer vision, pp 3749–3758

  19. Yao H, Zhang S, Hong R, Zhang Y, Xu C, Tian Q (2019) Deep representation learning with part loss for person re-identification. IEEE Trans Image Process 28(6):2860–2871

    Article  MathSciNet  Google Scholar 

  20. Ghorbel M, Ammar S, Kessentini Y, Jmaiel M, Chaari A (2020) Fusing local and global features for person re-identification using multi-stream deep neural networks. In: Pattern recognition and artificial intelligence: 4th Mediterranean conference, MedPRAI 2020, Hammamet, Tunisia, December 20–22, 2020, proceedings 4. Springer International Publishing, pp 73–85. https://doi.org/10.1007/978-3-030-71804-6_6

  21. Atrey PK, Hossain MA, El Saddik A, Kankanhalli MS (2010) Multimodal fusion for multimedia analysis: a survey. Multimed Syst 16(6):345–379. https://doi.org/10.1007/s00530-010-0182-0

    Article  Google Scholar 

  22. Kittler J (1998) Combining classifiers: a theoretical framework. Pattern Anal Appl 1(1):18–27

    Article  Google Scholar 

  23. Ben Slima I, Ammar S, Ghorbel M, Kessentini Y (2020) Possibilistic classifier combination for person re-identification. In: Pattern recognition and artificial intelligence: 4th Mediterranean conference, MedPRAI 2020, Hammamet, Tunisia, December 20–22, 2020, proceedings 4. Springer International Publishing, pp 98–111. https://doi.org/10.1007/978-3-030-71804-6_8

    Chapter  Google Scholar 

  24. Zadeh LA (1978) Fuzzy sets as a basis for a theory of possibility. Fuzzy Sets Syst 1(1):3–28

    Article  MathSciNet  Google Scholar 

  25. Ho T, Hull J, Srihari S (1994) Decision combination in multiple classifier systems. IEEE Trans Pattern Anal Mach Intell 16:66–75

    Article  Google Scholar 

  26. Tian Y, Mi X, Cui H, Zhang P, Kang B (2021) Using z-number to measure the reliability of new information fusion method and its application in pattern recognition. Appl Soft Comput 111:107658

    Article  Google Scholar 

  27. Asad M, Yang J, He J, Shamsolmoali P, He X (2021) Multi-frame feature-fusion-based model for violence detection. Vis Comput 37(6):1415–1431

    Article  Google Scholar 

  28. Ben Slima I, Borgi A (2018) Features’ associations in fuzzy ensemble classifiers. In: International conference on database and expert systems applications. Springer, pp 369–377

    Chapter  Google Scholar 

  29. Ben Slima I, Borgi A (2018) Supervised methods for regrouping attributes in fuzzy rule-based classification systems. Appl Intell 48(12):4577–4593

    Article  Google Scholar 

  30. Wei-bin L, Zhi-yuan Z, Wei-wei X (2017) Feature fusion methods in pattern classification. J Beijing Univ Posts Telecommun 40(4):1

    Google Scholar 

  31. Moreno-Seco F, Inesta JM, De León PJP, Micó L (2006) Comparison of classifier fusion methods for classification in pattern recognition tasks. In: Joint IAPR international workshops on statistical techniques in pattern recognition (SPR) and structural and syntactic pattern recognition (SSPR). Springer, pp 705–713

  32. Maltoni D, Maio D, Jain AK, Prabhakar S (2009) Biometric fusion. Handb Fingerpr Recognit. https://doi.org/10.1007/978-1-84882-254-2_7

    Article  Google Scholar 

  33. Modak SKS, Jha VK (2019) Multibiometric fusion strategy and its applications: a review. Inf Fusion 49:174–204. https://doi.org/10.1016/j.inffus.2018.11.018

    Article  Google Scholar 

  34. Kumar A (2009) Fusion, rank-level. Springer US, Boston, pp 607–611. https://doi.org/10.1007/978-0-387-73003-5_159

  35. Abaza A, Ross A (2009) Quality based rank-level fusion in multibiometric systems. In: 2009 IEEE 3rd international conference on biometrics: theory, applications, and systems. IEEE, pp 1–6

  36. Pala F, Satta R, Fumera G, Roli F (2015) Multimodal person reidentification using rgb-d cameras. IEEE Trans Circuits Syst Video Technol 26(4):788–799

    Article  Google Scholar 

  37. Liu C, Gong S, Loy CC, Lin X (2014) Evaluating feature importance for re-identification. Springer, London, pp 203–228. https://doi.org/10.1007/978-1-4471-6296-4_10

    Book  Google Scholar 

  38. Gao M, Ai H, Bai B (2016) A feature fusion strategy for person re-identification. In: 2016 IEEE international conference on image processing (ICIP). IEEE, pp 4274–4278

  39. Johnson J, Yasugi S, Sugino Y, Pranata S, Shen S (2018) Person re-identification with fusion of hand-crafted and deep pose-based body region features. arXiv preprint arXiv:1803.10630

  40. Bhuiyan A, Liu Y, Siva P, Javan M, Ayed IB, Granger E (2020) Pose guided gated fusion for person re-identification. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 2675–2684

  41. Zhang Y, Gu X, Tang J, Cheng K, Tan S (2019) Part-based attribute-aware network for person re-identification. IEEE Access 7:53585–53595

    Article  Google Scholar 

  42. Eisenbach M, Kolarow A, Vorndran A, Niebling J, Gross H (2015) Evaluation of multi feature fusion at score-level for appearance-based person re-identification. In: 2015 international joint conference on neural networks (IJCNN), pp 1–8. https://doi.org/10.1109/IJCNN.2015.7280360

  43. Lejbølle A, Nasrollahi K, Moeslund T (2018) Enhancing person re-identification by late fusion of low-, mid-, and high-level features. IET Biom 7(2):125–135. https://doi.org/10.1049/iet-bmt.2016.0200

    Article  Google Scholar 

  44. Lejbølle A, Nasrollahi K, Moeslund T (2017) Late fusion in part-based person re-identification, pp 385–393. https://doi.org/10.1145/3055635.3056640

  45. Zheng L, Wang S, Tian L, Fei He, Liu Z, Tian Q (2015) Query-adaptive late fusion for image search and person re-identification. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 1741–1750. https://doi.org/10.1109/CVPR.2015.7298783

  46. Nguyen T-B, Le T-L, Ngoc NP (2019) Fusion schemes for image-to-video person re-identification. J Inform Telecommun 3(1):74–94. https://doi.org/10.1080/24751839.2018.1531233

    Article  Google Scholar 

  47. Nguyen T, Nguyen T-N, Hong Quan N, Le T, Phamthanh T (2020) How feature fusion can help to improve multi-shot person re-identification performance? In: The international conference on multimedia analysis and pattern recognition (MAPR), pp 1–6. https://doi.org/10.1109/MAPR49794.2020.9237782

  48. Dubois D, Foulloy L, Mauris G, Prade H (2004) Probability-possibility transformations, triangular fuzzy sets, and probabilistic inequalities. Reliab Comput 10(4):273–297

    Article  MathSciNet  Google Scholar 

  49. Bouchon-Meunier B, Dubois D, Godo L, Prade H (1999) Fuzzy sets and possibility theory in approximate and plausible reasoning. In: Fuzzy sets in approximate reasoning and information systems. Springer, pp 15–190

  50. Dubois D, Nguyen HT, Prade H (2000) Possibility theory, probability and fuzzy sets misunderstandings, bridges and gaps. In: Fundamentals of fuzzy sets. Springer, pp 343–438

  51. Bounhas M, Mellouli K, Prade H, Serrurier M (2013) Possibilistic classifiers for numerical data. Soft Comput 17(5):733–751

    Article  Google Scholar 

  52. Baati K, Hamdani TM, Alimi AM, Abraham A (2019) A new possibilistic classifier for mixed categorical and numerical data based on a bi-module possibilistic estimation and the generalized minimum-based algorithm. Intell Fuzzy Syst 36(4):3513–3523. https://doi.org/10.3233/JIFS-181383

    Article  Google Scholar 

  53. Bouhamed SA, Kallel IK, Yager RR, Bossé E, Solaiman B (2020) An intelligent quality-based approach to fusing multi-source possibilistic information. Inform Fusion 55:68–90. https://doi.org/10.1016/j.inffus.2019.08.003

    Article  Google Scholar 

  54. Albardan M, Klein J, Colot O (2020) SPOCC: scalable possibilistic classifier combination—toward robust aggregation of classifiers. Expert Syst Appl 150:113332. https://doi.org/10.1016/j.eswa.2020.113332

    Article  Google Scholar 

  55. Giannakopoulos T, Pikrakis A (2014) Chapter 5—audio classification. In: Introduction to audio analysis. Academic Press, pp 107–151

  56. Meyer-Baese A, Schmid V (2014) Chapter 7—foundations of neural networks. In: Pattern recognition and signal analysis in medical imaging, 2nd edn. Academic Press, pp 197–243

  57. Dubois D, Prade H (1982) On several representations of an uncertain body of evidence. Fuzzy Inform Decis Process 167–181

  58. Shafer G (1976) A mathematical theory of evidence, vol 42. Princeton University Press, Princeton

    Book  Google Scholar 

  59. Anderson R, Koh YS, Dobbie G (2016) CPF: concept profiling framework for recurring drifts in data streams. In: Kang BH, Bai Q (eds) AI 2016: advances in artificial intelligence. Springer International Publishing, Berlin, pp 203–214

    Chapter  Google Scholar 

  60. Mercier D, Quost B, Denœux T (2008) Refined modeling of sensor reliability in the belief function framework using contextual discounting. Inform Fusion 9(2):246–258

    Article  Google Scholar 

  61. Dubois D, Prade H (1988) Possibility theory? An approach to computerized processing of uncertainty, 1st edn. Springer, Berlin

    MATH  Google Scholar 

  62. Dubois D, Prade H (1988) Representation and combination of uncertainty with belief functions and possibility measures. Comput Intell 4(3):244–264

    Article  Google Scholar 

  63. Dubois D, Prade H (1985) A review of fuzzy set aggregation connectives. Inf Sci 36(1–2):85–121

    Article  MathSciNet  Google Scholar 

  64. Beliakov G (2005) Fitting triangular norms to empirical data. In: Klement EP, Mesiar R (eds) Logical, algebraic, analytic and probabilistic aspects of triangular norms. Elsevier, Amsterdam, pp 261–272. https://doi.org/10.1016/B978-044451814-9/50009-4

    Chapter  MATH  Google Scholar 

  65. Yager R, Gupta M, Kandel A, Bandler W, Kiszka J (1985) Forms of multi-criteria decision functions and preference information types. In: Approximate reasoning in expert systems, pp 167–177

  66. Farahbod F, Eftekhari M (2012) Comparison of different t-norm operators in classification problems. Fuzzy Log Syst 2(3)

  67. Deschrijver G, Cornelis C, Kerre EE (2004) On the representation of intuitionistic fuzzy t-norms and t-conorms. IEEE Trans Fuzzy Syst 12(1):45–61

    Article  Google Scholar 

  68. Klement EP, Mesiar R, Pap E (2005) Triangular norms: basic notions and properties. In: Logical, algebraic, analytic and probabilistic aspects of triangular norms. Elsevier, pp 17–60

  69. Yager RR, Kacprzyk J (2012) The ordered weighted averaging operators: theory and applications. Springer Science & Business Media, Berlin

    Google Scholar 

  70. Yager RR (1988) On ordered weighted averaging aggregation operators in multicriteria decision making. IEEE Trans Syst Man Cybern 18(1):183–190

    Article  Google Scholar 

  71. Yager RR (1992) Decision making under Dempster–Shafer uncertainties. Int J Gen Syst 20(3):233–245

    Article  Google Scholar 

  72. Yager RR, Filev DP (1999) Induced ordered weighted averaging operators. IEEE Trans Syst Man Cybern Part B Cybern 29(2):141–150

    Article  Google Scholar 

  73. Xu Z (2005) An overview of methods for determining OWA weights. Int J Intell Syst 20(8):843–865

    Article  Google Scholar 

  74. Klinker F (2011) Exponential moving average versus moving exponential average. Math Semesterber 58:97–107. https://doi.org/10.1007/s00591-010-0080-8

    Article  MathSciNet  MATH  Google Scholar 

  75. 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 vision, pp 1116–1124

  76. Zheng Z, Zheng L, Yang Y (2017) Unlabeled samples generated by Gan improve the person re-identification baseline in vitro. In: Proceedings of the IEEE international conference on computer vision

  77. Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: European conference on computer vision workshop on benchmarking multi-target tracking

  78. Zheng Z, Zheng L, Yang Y (2017) A discriminatively learned CNN embedding for person reidentification. ACM Trans Multimed Comput Commun Appl TOMM 14(1):1–20

    Google Scholar 

  79. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778

  80. Fraenkel J, Grofman B (2014) The Borda count and its real-world alternatives: comparing scoring rules in Nauru and Slovenia. Aust J Polit Sci 49(2):186–205. https://doi.org/10.1080/10361146.2014.900530

    Article  Google Scholar 

  81. Mercier D, Elouedi Z, Lefevre E (2010) Sur l’affaiblissement d’une fonction de croyance par une matrice de confusion. Rencontres Francophones sur la Logique Floue et Ses Applications, pp 277–283

Download references

Acknowledgements

We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.

Author information

Authors and Affiliations

  1. Digital Research Center of Sfax, 3021, Sfax, Tunisia

    Ilef Ben Slima, Sourour Ammar & Mahmoud Ghorbel

  2. SM@RTS: Laboratory of Signals, systeMs, aRtificial Intelligence and neTworkS, Sfax, Tunisia

    Ilef Ben Slima & Sourour Ammar

  3. ReDCAD Laboratory, Sfax University, Sfax, Tunisia

    Mahmoud Ghorbel

Authors
  1. Ilef Ben Slima
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sourour Ammar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mahmoud Ghorbel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ilef Ben Slima.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ben Slima, I., Ammar, S. & Ghorbel, M. Possibilistic rank-level fusion method for person re-identification. Neural Comput & Applic 34, 14151–14168 (2022). https://doi.org/10.1007/s00521-021-06502-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06502-9

Keywords

Search

Navigation