Laser & Optoelectronics Progress, Volume. 58, Issue 2, 0215009(2021)
Rail Surface Damage Detection Method Based on Improved U-Net Convolutional Neural Network
Fig. 1. Detection flow chart of track damage image
Fig. 2. Sample images expanded by different operations. (a) Original images; (b) ground truth; (c) translation transformation; (d) rotation transformation; (e) scaling transformation
Fig. 3. Structure of improved U-Net convolution neural network
Fig. 4. Performance curves of proposed method in model training process
Fig. 5. ROC curve of proposed method
Fig. 6. Detection results of different methods
Fig. 7. Visualization results of different methods. (a) Defect images; (b) ground truth; (c) LN+DLBP; (d) MLC+PEME; (e) DWT; (f) CFE; (g) U-Net; (h) proposed method
Get Citation
Copy Citation Text
Bo Liang, Jun Lu, Yang Cao. Rail Surface Damage Detection Method Based on Improved U-Net Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0215009
Category: Machine Vision
Received: Jun. 5, 2020
Accepted: Aug. 3, 2020
Published Online: Jan. 11, 2021
The Author Email: Lu Jun (lujun@sust.edu.cn)