A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Underwater crack pixel-wise identification and quantification for dams via lightweight semantic segmentation and transfer learning
Abstract Remotely operated vehicles (ROVs) with cameras provide a solution for dam underwater information acquisition, but problems like massive high-dimensional data processing and effective damage-related information extraction also occur. This paper thereby proposes a real-time pixel-level dam underwater crack automatic segmentation and quantification framework using lightweight semantic segmentation network LinkNet and two-stage hybrid transfer learning(TL). With the combination of in-domain and cross-domain TL, the modeling cost and computational burden can be significantly reduced by transferring knowledge learned in relevant domains to the target domain. The proposed method shows strong identification capability in complicated underwater scenarios(motion blur, uneven illumination, and obstacle blocking), achieving performance with 0.8924 mIOU, 0.9444 precision, 0.9151 recall, and 0.9295 F1-score in the test set. Combined with infrared laser-assisted ranging systems, the geometric features and physical sizes of cracks are quantified using the proposed method. Finally, a visual GUI software with both offline and online detection patterns is developed to perform real-time detection in practice.
Highlights The two-stage hybrid TL strategy can significantly reduce the high-quality labeled data dependence for the detection model The proposed dam underwater crack segmentation method achieves good detection accuracy in terms of 0.8924 mIOU, 0.9444 precision, 0.9151 recall, and 0.9295 F1-score. The model robustness has been validated in underwater inspection scenarios, including motion blur, uneven illumination, and obstacle blocking.
Underwater crack pixel-wise identification and quantification for dams via lightweight semantic segmentation and transfer learning
Abstract Remotely operated vehicles (ROVs) with cameras provide a solution for dam underwater information acquisition, but problems like massive high-dimensional data processing and effective damage-related information extraction also occur. This paper thereby proposes a real-time pixel-level dam underwater crack automatic segmentation and quantification framework using lightweight semantic segmentation network LinkNet and two-stage hybrid transfer learning(TL). With the combination of in-domain and cross-domain TL, the modeling cost and computational burden can be significantly reduced by transferring knowledge learned in relevant domains to the target domain. The proposed method shows strong identification capability in complicated underwater scenarios(motion blur, uneven illumination, and obstacle blocking), achieving performance with 0.8924 mIOU, 0.9444 precision, 0.9151 recall, and 0.9295 F1-score in the test set. Combined with infrared laser-assisted ranging systems, the geometric features and physical sizes of cracks are quantified using the proposed method. Finally, a visual GUI software with both offline and online detection patterns is developed to perform real-time detection in practice.
Highlights The two-stage hybrid TL strategy can significantly reduce the high-quality labeled data dependence for the detection model The proposed dam underwater crack segmentation method achieves good detection accuracy in terms of 0.8924 mIOU, 0.9444 precision, 0.9151 recall, and 0.9295 F1-score. The model robustness has been validated in underwater inspection scenarios, including motion blur, uneven illumination, and obstacle blocking.
Underwater crack pixel-wise identification and quantification for dams via lightweight semantic segmentation and transfer learning
Li, Yangtao (author) / Bao, Tengfei (author) / Huang, Xianjun (author) / Chen, Hao (author) / Xu, Bo (author) / Shu, Xiaosong (author) / Zhou, Yuhang (author) / Cao, Qingbo (author) / Tu, Jiuzhou (author) / Wang, Ruijie (author)
2022-09-27
Article (Journal)
Electronic Resource
English
Pixel-wise crack defect segmentation with dual-encoder fusion network
| Elsevier | 2024
Pixel-wise crack defect segmentation with dual-encoder fusion network
| Elsevier | 2024