Zhengyi Zhang, Jianwei Ding, Huiwen Wei, Xiaotong Xiao. Multi-Level Features Cascade for Person Re-Identification Based on Attention Mechanism[J]. Laser & Optoelectronics Progress, 2021, 58(22): 2215003
- Laser & Optoelectronics Progress
- Vol. 58, Issue 22, 2215003 (2021)
Fig. 1. Structure of the AMFC algorithm
Fig. 2. Structure of the MFC-Net
Fig. 3. Structure of the PCAM
Fig. 4. Structure of the CAM
Fig. 5. Visualization results of the area of interest of different algorithms. (a) Original image; (b) Baseline; (c) Baseline with MFC-Net; (d) AMFC
Fig. 6. Processing results of different algorithms on the occlusion and camera viewing angle changes. (a) Baseline; (b) Baseline with MFC-Net; (c) AMFC
Fig. 7. Processing results of different algorithms on the images of various illumination. (a) Baseline; (b) Baseline with MFC-Net; (c) AMFC
Fig. 8. Processing results of different algorithms on images with similarly dressed person. (a) Baseline; (b) Baseline with MFC-Net; (c) AMFC
| |||||||||||||||||||||||||||||||||||||||||
Table 1. Influence of MFC-Net on the performance of the algorithm unit: %
| |||||||||||||||||||||||||||||||||||||||||
Table 2. Influence of PCAM on algorithm performance unit: %
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 3. Detection performance of different algorithms unit: %
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20