Laser & Optoelectronics Progress, Volume. 59, Issue 22, 2215003(2022)
Defect Detection of Wheel Set Tread Based on Improved YOLOv5
Fig. 1. YOLOv5 model structure
Fig. 2. Structure of convolution attention mechanism
Fig. 3. Structure diagram of improved YOLOv5
Fig. 4. Tread defect type. (a) Normal; (b) scratch; (c) laceration injury; (d) peel
Fig. 5. Loss variation curve
Fig. 6. Comparison of detection results between YOLOv5 and improved YOLOv5. (a) (c) (e) Detection results of YOLOv5; (b) (d) (f) detection results of the improved YOLOv5
Fig. 7. Comparison of inclusion detection results. (a) Scratch; (b) including scratch; (c) confluent scratch
|
|
|
|
Get Citation
Copy Citation Text
Yaoze Sun, Junwei Gao. Defect Detection of Wheel Set Tread Based on Improved YOLOv5[J]. Laser & Optoelectronics Progress, 2022, 59(22): 2215003
Category: Machine Vision
Received: Dec. 15, 2021
Accepted: Jan. 11, 2022
Published Online: Oct. 13, 2022
The Author Email: Sun Yaoze (486695900@qq.com)