Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture
Automatic crack detection from images is an important task that is adopted to ensure road safety and durability for Portland cement concrete (PCC) and asphalt concrete (AC) pavement. Pavement failure depends on a number of causes including water intrusion, stress from heavy loads, and all the climat...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/13/13/2960 |
| _version_ | 1797563535661727744 |
|---|---|
| author | Zhun Fan Chong Li Ying Chen Jiahong Wei Giuseppe Loprencipe Xiaopeng Chen Paola Di Mascio |
| author_facet | Zhun Fan Chong Li Ying Chen Jiahong Wei Giuseppe Loprencipe Xiaopeng Chen Paola Di Mascio |
| author_sort | Zhun Fan |
| collection | DOAJ |
| description | Automatic crack detection from images is an important task that is adopted to ensure road safety and durability for Portland cement concrete (PCC) and asphalt concrete (AC) pavement. Pavement failure depends on a number of causes including water intrusion, stress from heavy loads, and all the climate effects. Generally, cracks are the first distress that arises on road surfaces and proper monitoring and maintenance to prevent cracks from spreading or forming is important. Conventional algorithms to identify cracks on road pavements are extremely time-consuming and high cost. Many cracks show complicated topological structures, oil stains, poor continuity, and low contrast, which are difficult for defining crack features. Therefore, the automated crack detection algorithm is a key tool to improve the results. Inspired by the development of deep learning in computer vision and object detection, the proposed algorithm considers an encoder-decoder architecture with hierarchical feature learning and dilated convolution, named U-Hierarchical Dilated Network (U-HDN), to perform crack detection in an end-to-end method. Crack characteristics with multiple context information are automatically able to learn and perform end-to-end crack detection. Then, a multi-dilation module embedded in an encoder-decoder architecture is proposed. The crack features of multiple context sizes can be integrated into the multi-dilation module by dilation convolution with different dilatation rates, which can obtain much more cracks information. Finally, the hierarchical feature learning module is designed to obtain a multi-scale features from the high to low- level convolutional layers, which are integrated to predict pixel-wise crack detection. Some experiments on public crack databases using 118 images were performed and the results were compared with those obtained with other methods on the same images. The results show that the proposed U-HDN method achieves high performance because it can extract and fuse different context sizes and different levels of feature maps than other algorithms. |
| first_indexed | 2024-03-10T18:44:02Z |
| format | Article |
| id | doaj.art-ea6225061c184ce5bc78dcee7d4b1d9e |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-10T18:44:02Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-ea6225061c184ce5bc78dcee7d4b1d9e2023-11-20T05:39:46ZengMDPI AGMaterials1996-19442020-07-011313296010.3390/ma13132960Automatic Crack Detection on Road Pavements Using Encoder-Decoder ArchitectureZhun Fan0Chong Li1Ying Chen2Jiahong Wei3Giuseppe Loprencipe4Xiaopeng Chen5Paola Di Mascio6Key Lab of Digital Signal and Image Processing of Guangdong Province, Department of Electronic and information Engineering, College of Engineering, Shantou University, Shan’tou 515063, ChinaKey Lab of Digital Signal and Image Processing of Guangdong Province, Department of Electronic and information Engineering, College of Engineering, Shantou University, Shan’tou 515063, ChinaKey Lab of Digital Signal and Image Processing of Guangdong Province, Department of Electronic and information Engineering, College of Engineering, Shantou University, Shan’tou 515063, ChinaKey Lab of Digital Signal and Image Processing of Guangdong Province, Department of Electronic and information Engineering, College of Engineering, Shantou University, Shan’tou 515063, ChinaDepartment of Civil, Constructional and Environmental Engineering, Sapienza University of Rome, 00184 Rome, ItalyDepartment of Industrial Engineering, Pusan National University, Busan 609735, KoreaDepartment of Civil, Constructional and Environmental Engineering, Sapienza University of Rome, 00184 Rome, ItalyAutomatic crack detection from images is an important task that is adopted to ensure road safety and durability for Portland cement concrete (PCC) and asphalt concrete (AC) pavement. Pavement failure depends on a number of causes including water intrusion, stress from heavy loads, and all the climate effects. Generally, cracks are the first distress that arises on road surfaces and proper monitoring and maintenance to prevent cracks from spreading or forming is important. Conventional algorithms to identify cracks on road pavements are extremely time-consuming and high cost. Many cracks show complicated topological structures, oil stains, poor continuity, and low contrast, which are difficult for defining crack features. Therefore, the automated crack detection algorithm is a key tool to improve the results. Inspired by the development of deep learning in computer vision and object detection, the proposed algorithm considers an encoder-decoder architecture with hierarchical feature learning and dilated convolution, named U-Hierarchical Dilated Network (U-HDN), to perform crack detection in an end-to-end method. Crack characteristics with multiple context information are automatically able to learn and perform end-to-end crack detection. Then, a multi-dilation module embedded in an encoder-decoder architecture is proposed. The crack features of multiple context sizes can be integrated into the multi-dilation module by dilation convolution with different dilatation rates, which can obtain much more cracks information. Finally, the hierarchical feature learning module is designed to obtain a multi-scale features from the high to low- level convolutional layers, which are integrated to predict pixel-wise crack detection. Some experiments on public crack databases using 118 images were performed and the results were compared with those obtained with other methods on the same images. The results show that the proposed U-HDN method achieves high performance because it can extract and fuse different context sizes and different levels of feature maps than other algorithms.https://www.mdpi.com/1996-1944/13/13/2960pavement crackingautomatic crack detectionencoder-decoderdeep learningU-nethierarchical feature |
| spellingShingle | Zhun Fan Chong Li Ying Chen Jiahong Wei Giuseppe Loprencipe Xiaopeng Chen Paola Di Mascio Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture Materials pavement cracking automatic crack detection encoder-decoder deep learning U-net hierarchical feature |
| title | Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture |
| title_full | Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture |
| title_fullStr | Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture |
| title_full_unstemmed | Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture |
| title_short | Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture |
| title_sort | automatic crack detection on road pavements using encoder decoder architecture |
| topic | pavement cracking automatic crack detection encoder-decoder deep learning U-net hierarchical feature |
| url | https://www.mdpi.com/1996-1944/13/13/2960 |
| work_keys_str_mv | AT zhunfan automaticcrackdetectiononroadpavementsusingencoderdecoderarchitecture AT chongli automaticcrackdetectiononroadpavementsusingencoderdecoderarchitecture AT yingchen automaticcrackdetectiononroadpavementsusingencoderdecoderarchitecture AT jiahongwei automaticcrackdetectiononroadpavementsusingencoderdecoderarchitecture AT giuseppeloprencipe automaticcrackdetectiononroadpavementsusingencoderdecoderarchitecture AT xiaopengchen automaticcrackdetectiononroadpavementsusingencoderdecoderarchitecture AT paoladimascio automaticcrackdetectiononroadpavementsusingencoderdecoderarchitecture |