Laser & Optoelectronics Progress, Volume. 60, Issue 22, 2215005(2023)
Gear Surface Defect Detection Method Based on Improved YOLOx Network
Fig. 1. The main structure of the YOLOx algorithm
Fig. 2. Structure diagram of CSP_X
Fig. 3. Structure of decoupled head
Fig. 4. Schematic diagram of the structure of classic ASFF
Fig. 5. Revised structural diagram
Fig. 6. Schematic diagram of SE-Layer
Fig. 7. Flowchart of the SE-Layer
Fig. 8. Schematic diagram of ECA
Fig. 9. Structure of improved YOLOx
Fig. 10. Change curves of loss function value during original YOLOx training
Fig. 11. Change curves of the loss function value during the training of the improved YOLOx
Fig. 12. Comparison of the mAP@0.5 curves by the improved and original YOLOx network
Fig. 13. Comparison of the metallic gear defect detection results by the original and improved YOLOx networks. (a) Original YOLOx;(b) improved YOLOx
Fig. 14. Detection site of gear surface defects. (a) The first detection station; (b) the second detection station
|
|
|
Get Citation
Copy Citation Text
Shuwen Zhang, Zhenyu Zhong, Dahu Zhu. Gear Surface Defect Detection Method Based on Improved YOLOx Network[J]. Laser & Optoelectronics Progress, 2023, 60(22): 2215005
Category: Machine Vision
Received: Jan. 9, 2023
Accepted: Mar. 6, 2023
Published Online: Nov. 16, 2023
The Author Email: Zhu Dahu (dhzhu@whut.edu.cn)