Attention-Based Convolutional Neural Network for Pavement Crack Detection
Achieving high detection accuracy of pavement cracks with complex textures under different lighting conditions is still challenging. In this context, an encoder-decoder network-based architecture named CrackResAttentionNet was proposed in this study, and the position attention module and channel att...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Advances in Materials Science and Engineering |
| Online Access: | http://dx.doi.org/10.1155/2021/5520515 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547612907012096 |
|---|---|
| author | Haifeng Wan Lei Gao Manman Su Qirun Sun Lei Huang |
| author_facet | Haifeng Wan Lei Gao Manman Su Qirun Sun Lei Huang |
| author_sort | Haifeng Wan |
| collection | DOAJ |
| description | Achieving high detection accuracy of pavement cracks with complex textures under different lighting conditions is still challenging. In this context, an encoder-decoder network-based architecture named CrackResAttentionNet was proposed in this study, and the position attention module and channel attention module were connected after each encoder to summarize remote contextual information. The experiment results demonstrated that, compared with other popular models (ENet, ExFuse, FCN, LinkNet, SegNet, and UNet), for the public dataset, CrackResAttentionNet with BCE loss function and PRelu activation function achieved the best performance in terms of precision (89.40), mean IoU (71.51), recall (81.09), and F1 (85.04). Meanwhile, for a self-developed dataset (Yantai dataset), CrackResAttentionNet with BCE loss function and PRelu activation function also had better performance in terms of precision (96.17), mean IoU (83.69), recall (93.44), and F1 (94.79). In particular, for the public dataset, the precision of BCE loss and PRelu activation function was improved by 3.21. For the Yantai dataset, the results indicated that the precision was improved by 0.99, the mean IoU was increased by 0.74, the recall was increased by 1.1, and the F1 for BCE loss and PRelu activation function was increased by 1.24. |
| format | Article |
| id | doaj-art-0090bdf552194145a3fb14eff763f5c9 |
| institution | Kabale University |
| issn | 1687-8434 1687-8442 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Materials Science and Engineering |
| spelling | doaj-art-0090bdf552194145a3fb14eff763f5c92025-02-03T06:43:48ZengWileyAdvances in Materials Science and Engineering1687-84341687-84422021-01-01202110.1155/2021/55205155520515Attention-Based Convolutional Neural Network for Pavement Crack DetectionHaifeng Wan0Lei Gao1Manman Su2Qirun Sun3Lei Huang4School of Civil Engineering, Yantai University, Yantai, Shandong 264005, ChinaCSIRO, Waite Campus, Urrbrae, SA 5064, AustraliaSchool of Civil Engineering, Yantai University, Yantai, Shandong 264005, ChinaSchool of Civil Engineering, Yantai University, Yantai, Shandong 264005, ChinaSchool of Civil Engineering, Yantai University, Yantai, Shandong 264005, ChinaAchieving high detection accuracy of pavement cracks with complex textures under different lighting conditions is still challenging. In this context, an encoder-decoder network-based architecture named CrackResAttentionNet was proposed in this study, and the position attention module and channel attention module were connected after each encoder to summarize remote contextual information. The experiment results demonstrated that, compared with other popular models (ENet, ExFuse, FCN, LinkNet, SegNet, and UNet), for the public dataset, CrackResAttentionNet with BCE loss function and PRelu activation function achieved the best performance in terms of precision (89.40), mean IoU (71.51), recall (81.09), and F1 (85.04). Meanwhile, for a self-developed dataset (Yantai dataset), CrackResAttentionNet with BCE loss function and PRelu activation function also had better performance in terms of precision (96.17), mean IoU (83.69), recall (93.44), and F1 (94.79). In particular, for the public dataset, the precision of BCE loss and PRelu activation function was improved by 3.21. For the Yantai dataset, the results indicated that the precision was improved by 0.99, the mean IoU was increased by 0.74, the recall was increased by 1.1, and the F1 for BCE loss and PRelu activation function was increased by 1.24.http://dx.doi.org/10.1155/2021/5520515 |
| spellingShingle | Haifeng Wan Lei Gao Manman Su Qirun Sun Lei Huang Attention-Based Convolutional Neural Network for Pavement Crack Detection Advances in Materials Science and Engineering |
| title | Attention-Based Convolutional Neural Network for Pavement Crack Detection |
| title_full | Attention-Based Convolutional Neural Network for Pavement Crack Detection |
| title_fullStr | Attention-Based Convolutional Neural Network for Pavement Crack Detection |
| title_full_unstemmed | Attention-Based Convolutional Neural Network for Pavement Crack Detection |
| title_short | Attention-Based Convolutional Neural Network for Pavement Crack Detection |
| title_sort | attention based convolutional neural network for pavement crack detection |
| url | http://dx.doi.org/10.1155/2021/5520515 |
| work_keys_str_mv | AT haifengwan attentionbasedconvolutionalneuralnetworkforpavementcrackdetection AT leigao attentionbasedconvolutionalneuralnetworkforpavementcrackdetection AT manmansu attentionbasedconvolutionalneuralnetworkforpavementcrackdetection AT qirunsun attentionbasedconvolutionalneuralnetworkforpavementcrackdetection AT leihuang attentionbasedconvolutionalneuralnetworkforpavementcrackdetection |