The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph Network
Crack is a common concrete pavement distress that will deteriorate into severe problems without timely repair, which means the automated detection of pavement crack is essential for pavement maintenance. However, automatic crack detection and segmentation remain challenging due to the complex paveme...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2022/2238095 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832554976131416064 |
|---|---|
| author | Jiang Chen Ye Yuan Hong Lang Shuo Ding Jian John Lu |
| author_facet | Jiang Chen Ye Yuan Hong Lang Shuo Ding Jian John Lu |
| author_sort | Jiang Chen |
| collection | DOAJ |
| description | Crack is a common concrete pavement distress that will deteriorate into severe problems without timely repair, which means the automated detection of pavement crack is essential for pavement maintenance. However, automatic crack detection and segmentation remain challenging due to the complex pavement condition. Recent research on pavement crack detection based on deep learning has laid a good foundation for automated crack segmentation, but there can still be improvements. This paper proposes an automatic concrete pavement crack segmentation framework with enhanced graph network branch. First, the nodes of the graph and nodes’ attributions are generated based on the image dividing. The edges of the graph are determined based on Gaussian distribution. Then, the graph from the image is input into the graph branch. The graph feature map of the graph branch output is fused with the image feature map of the encoder and then enters the decoder to recover the image resolution to obtain the crack segmentation result. Finally, the method is tested on a self-built 3D concrete pavement crack dataset. The proposed method achieves the highest F1 and IoU (Intersection over Union) in the comparison experiments. And the graph branch addition improves 0.08 on F1 and 0.06 on IoU compared with U-Net. |
| format | Article |
| id | doaj-art-cc18e203997b408797f521eb5fcaf378 |
| institution | Kabale University |
| issn | 2042-3195 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-cc18e203997b408797f521eb5fcaf3782025-02-03T05:49:59ZengWileyJournal of Advanced Transportation2042-31952022-01-01202210.1155/2022/2238095The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph NetworkJiang Chen0Ye Yuan1Hong Lang2Shuo Ding3Jian John Lu4The Key Laboratory of Road and Traffic Engineering of the Ministry of EducationThe Key Laboratory of Road and Traffic Engineering of the Ministry of EducationThe Key Laboratory of Road and Traffic Engineering of the Ministry of EducationThe Key Laboratory of Road and Traffic Engineering of the Ministry of EducationThe Key Laboratory of Road and Traffic Engineering of the Ministry of EducationCrack is a common concrete pavement distress that will deteriorate into severe problems without timely repair, which means the automated detection of pavement crack is essential for pavement maintenance. However, automatic crack detection and segmentation remain challenging due to the complex pavement condition. Recent research on pavement crack detection based on deep learning has laid a good foundation for automated crack segmentation, but there can still be improvements. This paper proposes an automatic concrete pavement crack segmentation framework with enhanced graph network branch. First, the nodes of the graph and nodes’ attributions are generated based on the image dividing. The edges of the graph are determined based on Gaussian distribution. Then, the graph from the image is input into the graph branch. The graph feature map of the graph branch output is fused with the image feature map of the encoder and then enters the decoder to recover the image resolution to obtain the crack segmentation result. Finally, the method is tested on a self-built 3D concrete pavement crack dataset. The proposed method achieves the highest F1 and IoU (Intersection over Union) in the comparison experiments. And the graph branch addition improves 0.08 on F1 and 0.06 on IoU compared with U-Net.http://dx.doi.org/10.1155/2022/2238095 |
| spellingShingle | Jiang Chen Ye Yuan Hong Lang Shuo Ding Jian John Lu The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph Network Journal of Advanced Transportation |
| title | The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph Network |
| title_full | The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph Network |
| title_fullStr | The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph Network |
| title_full_unstemmed | The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph Network |
| title_short | The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph Network |
| title_sort | improvement of automated crack segmentation on concrete pavement with graph network |
| url | http://dx.doi.org/10.1155/2022/2238095 |
| work_keys_str_mv | AT jiangchen theimprovementofautomatedcracksegmentationonconcretepavementwithgraphnetwork AT yeyuan theimprovementofautomatedcracksegmentationonconcretepavementwithgraphnetwork AT honglang theimprovementofautomatedcracksegmentationonconcretepavementwithgraphnetwork AT shuoding theimprovementofautomatedcracksegmentationonconcretepavementwithgraphnetwork AT jianjohnlu theimprovementofautomatedcracksegmentationonconcretepavementwithgraphnetwork AT jiangchen improvementofautomatedcracksegmentationonconcretepavementwithgraphnetwork AT yeyuan improvementofautomatedcracksegmentationonconcretepavementwithgraphnetwork AT honglang improvementofautomatedcracksegmentationonconcretepavementwithgraphnetwork AT shuoding improvementofautomatedcracksegmentationonconcretepavementwithgraphnetwork AT jianjohnlu improvementofautomatedcracksegmentationonconcretepavementwithgraphnetwork |