Possibilistic rank-level fusion method for person re-identification

被引:1
作者
Ben Slima, Ilef [1 ,2 ]
Ammar, Sourour [1 ,2 ]
Ghorbel, Mahmoud [1 ,3 ]
机构
[1] Digital Res Ctr Sfax, Sfax 3021, Tunisia
[2] SM RTS Lab Signals Syst aRtificial Intelligence &, Sfax, Tunisia
[3] Sfax Univ, ReDCAD Lab, Sfax, Tunisia
关键词
Classifier fusion; Rank-level fusion; Possibility theory; Deep learning; CNN; Person re-identification; AGGREGATION; CLASSIFICATION; COMBINATION; NETWORK; SET;
D O I
10.1007/s00521-021-06502-9
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:14151 / 14168
页数:18
相关论文
共 81 条
[51]  
Mansouri N., 2019, P 16 IEEE INT C ADV, P1
[52]  
Mercier D, 2010, RENCONTRES FRANCOPHO, P277
[53]   Refined modeling of sensor reliability in the belief function framework using contextual discounting [J].
Mercier, David ;
Quost, Benjamin ;
Denoeux, Thierry .
INFORMATION FUSION, 2008, 9 (02) :246-258
[54]   Multibiometric fusion strategy and its applications: A review [J].
Modak, Sandip Kumar Singh ;
Jha, Vijay Kumar .
INFORMATION FUSION, 2019, 49 :174-204
[55]  
Moreno-Seco F, 2006, LECT NOTES COMPUT SC, V4109, P705
[56]  
Nguyen T, 2020, INT C MULT AN PATT R, P1, DOI [10.1109/MAPR49794.2020.9237782, DOI 10.1109/MAPR49794.2020.9237782]
[57]   Multimodal Person Reidentification Using RGB-D Cameras [J].
Pala, Federico ;
Satta, Riccardo ;
Fumera, Giorgio ;
Roli, Fabio .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2016, 26 (04) :788-799
[58]   Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-Identification [J].
Quan, Ruijie ;
Dong, Xuanyi ;
Wu, Yu ;
Zhu, Linchao ;
Yang, Yi .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :3749-3758
[59]   Performance Measures and a Data Set for Multi-target, Multi-camera Tracking [J].
Ristani, Ergys ;
Solera, Francesco ;
Zou, Roger ;
Cucchiara, Rita ;
Tomasi, Carlo .
COMPUTER VISION - ECCV 2016 WORKSHOPS, PT II, 2016, 9914 :17-35
[60]  
Shafer G., 1976, A mathematical theory of evidence, DOI [10.1515/9780691214696, DOI 10.1515/9780691214696]