Dong Han, Gang Tang, Zhengkun Zhao. Surface Corrosion Detection of Quayside Crane Based on Improved MobileNetV2SSDLite[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1615006
- Laser & Optoelectronics Progress
- Vol. 58, Issue 16, 1615006 (2021)
Fig. 1. Structure of MobileNetV2SSDLite detection model
Fig. 2. Process of standard convolution and depth separable convolution. (a) Standard convolution; (b) depth separable convolution
Fig. 3. Different residuals. (a) Residual structure; (b) inverted residual structure
Fig. 4. Inverted residual block.(a) Stride is 1; (b) stride is 2
Fig. 5. Structure of improved network
Fig. 6. Images after data enhancement. (a) Original image; (b) color distortion; (c) random cropping; (d) horizontal flip; (e) random sampling
Fig. 7. Performance comparison of different models
Fig. 8. Number of network parameters and number of floating point operations
Fig. 9. Performance curves of various networks under different conditions. (a) Crack; (b) erosion; (c) overall
Fig. 10. Hard samples and easy sample. (a) Difficult sample 1; (b) simple sample; (c) difficult sample 2; (d) difficult sample 3
Fig. 11. Detection results of different networks. (a) image 1; (b) image 2; (c) image 3; (d) image 4
Fig. 12. Detection results of corrosion of quay bridge. (a) Banded corrosion; (b) pitting corrosion; (c) block corrosion
|
Table 1. Size of network priori box
|
Table 2. Parameters of basic network structure
|
Table 3. Parameters of network structure
|
Table 4. Performance comparison of different networks
|
Table 5. Impact of various methods on network performance
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