Optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classification
Abstract In the task of pavement distress recognition and classification, the complexity of the pavement environment, the small proportion of distresses in images, significant variation in distress scales, and the influence of features such as vehicles and traffic signs in the data make distress fea...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-88251-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571760530161664 |
|---|---|
| author | Wenlin Wu Fenghua Zhu Zheng Li Xue Li Xiaowei Li Jinwen Wang |
| author_facet | Wenlin Wu Fenghua Zhu Zheng Li Xue Li Xiaowei Li Jinwen Wang |
| author_sort | Wenlin Wu |
| collection | DOAJ |
| description | Abstract In the task of pavement distress recognition and classification, the complexity of the pavement environment, the small proportion of distresses in images, significant variation in distress scales, and the influence of features such as vehicles and traffic signs in the data make distress feature extraction challenging. This paper proposes a spectrum focus transformer (SFT) layer, which processes the signal spectrum and focuses on important frequency components. Initially, by thoroughly analyzing the frequency domain characteristics of image data, frequency value distribution information is obtained to achieve fine-tuning of different frequency components. Subsequently, frequency information and images are learned and weighted in the frequency domain, thereby enhancing the capability to capture pavement distress regions. Experiments conducted on the road pavement distress dataset revealed through heatmap analysis that distress regions received increased attention, achieving an accuracy of 97.73%. This performance demonstrates a higher accuracy compared to other models. |
| format | Article |
| id | doaj-art-e5830a4fd8794ee28ac660d8ca2491da |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-e5830a4fd8794ee28ac660d8ca2491da2025-02-02T12:23:12ZengNature PortfolioScientific Reports2045-23222025-01-0115111110.1038/s41598-025-88251-6Optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classificationWenlin Wu0Fenghua Zhu1Zheng Li2Xue Li3Xiaowei Li4Jinwen Wang5School of Rail Transportation, Shandong Jiaotong UniversityInstitute of Automation, Chinese Academy of SciencesSchool of Rail Transportation, Shandong Jiaotong UniversitySchool of Rail Transportation, Shandong Jiaotong UniversitySchool of Rail Transportation, Shandong Jiaotong UniversitySchool of Rail Transportation, Shandong Jiaotong UniversityAbstract In the task of pavement distress recognition and classification, the complexity of the pavement environment, the small proportion of distresses in images, significant variation in distress scales, and the influence of features such as vehicles and traffic signs in the data make distress feature extraction challenging. This paper proposes a spectrum focus transformer (SFT) layer, which processes the signal spectrum and focuses on important frequency components. Initially, by thoroughly analyzing the frequency domain characteristics of image data, frequency value distribution information is obtained to achieve fine-tuning of different frequency components. Subsequently, frequency information and images are learned and weighted in the frequency domain, thereby enhancing the capability to capture pavement distress regions. Experiments conducted on the road pavement distress dataset revealed through heatmap analysis that distress regions received increased attention, achieving an accuracy of 97.73%. This performance demonstrates a higher accuracy compared to other models.https://doi.org/10.1038/s41598-025-88251-6 |
| spellingShingle | Wenlin Wu Fenghua Zhu Zheng Li Xue Li Xiaowei Li Jinwen Wang Optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classification Scientific Reports |
| title | Optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classification |
| title_full | Optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classification |
| title_fullStr | Optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classification |
| title_full_unstemmed | Optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classification |
| title_short | Optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classification |
| title_sort | optimized deep learning model with integrated spectrum focus transformer for pavement distress recognition and classification |
| url | https://doi.org/10.1038/s41598-025-88251-6 |
| work_keys_str_mv | AT wenlinwu optimizeddeeplearningmodelwithintegratedspectrumfocustransformerforpavementdistressrecognitionandclassification AT fenghuazhu optimizeddeeplearningmodelwithintegratedspectrumfocustransformerforpavementdistressrecognitionandclassification AT zhengli optimizeddeeplearningmodelwithintegratedspectrumfocustransformerforpavementdistressrecognitionandclassification AT xueli optimizeddeeplearningmodelwithintegratedspectrumfocustransformerforpavementdistressrecognitionandclassification AT xiaoweili optimizeddeeplearningmodelwithintegratedspectrumfocustransformerforpavementdistressrecognitionandclassification AT jinwenwang optimizeddeeplearningmodelwithintegratedspectrumfocustransformerforpavementdistressrecognitionandclassification |