A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Road damage detection using super-resolution and semi-supervised learning with generative adversarial network
Abstract Road maintenance technology is required to maintain favorable driving conditions and prevent accidents. In particular, a sensor technology is required for detecting road damage. In this study, we developed a new sensor technology that can detect road damage using a deep learning-based image processing algorithm. The proposed technology includes a super-resolution and semi-supervised learning method based on a generative adversarial network. The former improves the quality of the road image to make the damaged area clearly visible. The latter enhances the detection performance using 5327 road images and 1327 label images. These two methods were applied to four lightweight segmentation neural networks. For 400 road images, the average recognition performance was 81.540% and 79.228% in terms of the mean intersection over union and F1-score, respectively. Consequently, the proposed training method improves the road damage detection algorithm and can be used for efficient road management in the future.
Graphical abstract Display Omitted
Highlights Enlarged Road damage image by super-resolution method for quality enhancement Training method using super-resolution and semi-supervised learning with GAN Lightweight road damage detection algorithm with high recognition performance Multiple road damage detection with 81.540% m-IoU and 79.228% F1 on average
Road damage detection using super-resolution and semi-supervised learning with generative adversarial network
Abstract Road maintenance technology is required to maintain favorable driving conditions and prevent accidents. In particular, a sensor technology is required for detecting road damage. In this study, we developed a new sensor technology that can detect road damage using a deep learning-based image processing algorithm. The proposed technology includes a super-resolution and semi-supervised learning method based on a generative adversarial network. The former improves the quality of the road image to make the damaged area clearly visible. The latter enhances the detection performance using 5327 road images and 1327 label images. These two methods were applied to four lightweight segmentation neural networks. For 400 road images, the average recognition performance was 81.540% and 79.228% in terms of the mean intersection over union and F1-score, respectively. Consequently, the proposed training method improves the road damage detection algorithm and can be used for efficient road management in the future.
Graphical abstract Display Omitted
Highlights Enlarged Road damage image by super-resolution method for quality enhancement Training method using super-resolution and semi-supervised learning with GAN Lightweight road damage detection algorithm with high recognition performance Multiple road damage detection with 81.540% m-IoU and 79.228% F1 on average
Road damage detection using super-resolution and semi-supervised learning with generative adversarial network
Shim, Seungbo (author) / Kim, Jin (author) / Lee, Seong-Won (author) / Cho, Gye-Chun (author)
2022-01-06
Article (Journal)
Electronic Resource
English
Generative adversarial network for road damage detection
| Wiley | 2021
| Wiley | 2022