Minyu Song, Lirong Chen, Jian'an Liang, Jinpeng Li, Zhenzhen Niu, Zhen Wang, Lili Bai. Real-Time Optical Fiber End Surface Defects Detection Model Based on Lightweight Improved Network[J]. Laser & Optoelectronics Progress, 2022, 59(24): 2415006
- Laser & Optoelectronics Progress
- Vol. 59, Issue 24, 2415006 (2022)
Fig. 1. Diagram of fiber end surface defects
Fig. 2. General structure of YOLOv5s
Fig. 3. Diagram of YOLOv5s substructure
Fig. 4. Basic unit of shuffleNetV2
Fig. 5. ShuffleNetV2 unit down sampled in space
Fig. 6. Structure diagram of convolutional block attention module (CBAM)
Fig. 7. Structure diagram of channel attention module
Fig. 8. Structure diagram of spatial attention module
Fig. 9. Structure diagram of YOLOv5_CS
Fig. 10. Comparison of mAP changes during training
Fig. 11. Contrast diagram of training loss function
Fig. 12. P-R graph
Fig. 13. Detection results comparison of YOLOv5_CS model and YOLOv5s model. (a), (c) YOLOv5s detection results; (b), (d) YOLOv5_CS ditection results
Fig. 14. Detection results comparison of YOLOv5_CS model and YOLOv5s model. (a), (c) YOLOv5s detection results; (b), (d) YOLOv5_CS detection results
|
Table 1. Comparison of detection results of five models
|
Table 2. Complexity comparison of five models
|
Table 3. Comparison of detection speed of different graphics cards
|
Table 4. Comparison of average precision of three types of defects
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