Kai Yang, Rui Li, Lin Luo, Liming Xie. Research on Train Key Components Detection Based on Improved RetinaNet[J]. Laser & Optoelectronics Progress, 2022, 59(12): 1215006
- Laser & Optoelectronics Progress
- Vol. 59, Issue 12, 1215006 (2022)
Fig. 1. RetinaNet network structure
Fig. 2. Bottleneck structure
Fig. 3. P6 and P7 layers structure
Fig. 4. RFB module
Fig. 5. PAN module
Fig. 6. Validation results of two networks on PASCAL VOC dataset. (a) mAP; (b) loss curves
Fig. 7. Detection results of RetinaNet
Fig. 8. Detection results of improved method
|
Table 1. Computing environment configuration
|
Table 2. Validation results on PASCAL VOC dataset (AP)
| |||||||||||||||||||||||||||||||||||||||
Table 3. Key component dataset
|
Table 4. Influence of different feature layers on detection effect
|
Table 5. AP comparison between proposed method and RetinaNet
|
Table 6. Comparison of detection speed and efficiency of different models
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