Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features
Road pavement cracks automated detection is one of the key factors to evaluate the road distress quality, and it is a difficult issue for the construction of intelligent maintenance systems. However, pavement cracks automated detection has been a challenging task, including strong nonuniformity, com...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2020/6412562 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547618959392768 |
|---|---|
| author | Weidong Song Guohui Jia Hong Zhu Di Jia Lin Gao |
| author_facet | Weidong Song Guohui Jia Hong Zhu Di Jia Lin Gao |
| author_sort | Weidong Song |
| collection | DOAJ |
| description | Road pavement cracks automated detection is one of the key factors to evaluate the road distress quality, and it is a difficult issue for the construction of intelligent maintenance systems. However, pavement cracks automated detection has been a challenging task, including strong nonuniformity, complex topology, and strong noise-like problems in the crack images, and so on. To address these challenges, we propose the CrackSeg—an end-to-end trainable deep convolutional neural network for pavement crack detection, which is effective in achieving pixel-level, and automated detection via high-level features. In this work, we introduce a novel multiscale dilated convolutional module that can learn rich deep convolutional features, making the crack features acquired under a complex background more discriminant. Moreover, in the upsampling module process, the high spatial resolution features of the shallow network are fused to obtain more refined pixel-level pavement crack detection results. We train and evaluate the CrackSeg net on our CrackDataset, the experimental results prove that the CrackSeg achieves high performance with a precision of 98.00%, recall of 97.85%, F-score of 97.92%, and a mIoU of 73.53%. Compared with other state-of-the-art methods, the CrackSeg performs more efficiently, and robustly for automated pavement crack detection. |
| format | Article |
| id | doaj-art-1551acead79848898f8dda2761fab894 |
| institution | Kabale University |
| issn | 0197-6729 2042-3195 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-1551acead79848898f8dda2761fab8942025-02-03T06:43:50ZengWileyJournal of Advanced Transportation0197-67292042-31952020-01-01202010.1155/2020/64125626412562Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional FeaturesWeidong Song0Guohui Jia1Hong Zhu2Di Jia3Lin Gao4School of Geomatics, Liaoning Technical University, Fuxin 123000, ChinaSchool of Geomatics, Liaoning Technical University, Fuxin 123000, ChinaCollege of Ecology and Environment, Institute of Disaster Prevention, Beijing 101601, ChinaSchool of Electronic and Information Engineering, Liaoning Technical University, Huludao 125105, ChinaSchool of Geomatics, Liaoning Technical University, Fuxin 123000, ChinaRoad pavement cracks automated detection is one of the key factors to evaluate the road distress quality, and it is a difficult issue for the construction of intelligent maintenance systems. However, pavement cracks automated detection has been a challenging task, including strong nonuniformity, complex topology, and strong noise-like problems in the crack images, and so on. To address these challenges, we propose the CrackSeg—an end-to-end trainable deep convolutional neural network for pavement crack detection, which is effective in achieving pixel-level, and automated detection via high-level features. In this work, we introduce a novel multiscale dilated convolutional module that can learn rich deep convolutional features, making the crack features acquired under a complex background more discriminant. Moreover, in the upsampling module process, the high spatial resolution features of the shallow network are fused to obtain more refined pixel-level pavement crack detection results. We train and evaluate the CrackSeg net on our CrackDataset, the experimental results prove that the CrackSeg achieves high performance with a precision of 98.00%, recall of 97.85%, F-score of 97.92%, and a mIoU of 73.53%. Compared with other state-of-the-art methods, the CrackSeg performs more efficiently, and robustly for automated pavement crack detection.http://dx.doi.org/10.1155/2020/6412562 |
| spellingShingle | Weidong Song Guohui Jia Hong Zhu Di Jia Lin Gao Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features Journal of Advanced Transportation |
| title | Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features |
| title_full | Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features |
| title_fullStr | Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features |
| title_full_unstemmed | Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features |
| title_short | Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features |
| title_sort | automated pavement crack damage detection using deep multiscale convolutional features |
| url | http://dx.doi.org/10.1155/2020/6412562 |
| work_keys_str_mv | AT weidongsong automatedpavementcrackdamagedetectionusingdeepmultiscaleconvolutionalfeatures AT guohuijia automatedpavementcrackdamagedetectionusingdeepmultiscaleconvolutionalfeatures AT hongzhu automatedpavementcrackdamagedetectionusingdeepmultiscaleconvolutionalfeatures AT dijia automatedpavementcrackdamagedetectionusingdeepmultiscaleconvolutionalfeatures AT lingao automatedpavementcrackdamagedetectionusingdeepmultiscaleconvolutionalfeatures |