Fine-Grained Detection of Pavement Distress Based on Integrated Data Using Digital Twin
The automated detection of distress such as cracks or potholes is a key basis for assessing the condition of pavements and deciding on their maintenance. A fine-grained pavement distress-detection algorithm based on integrated data using a digital twin is proposed to solve the challenges of the insu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/7/4549 |
| _version_ | 1797608317883777024 |
|---|---|
| author | Weidong Wang Xinyue Xu Jun Peng Wenbo Hu Dingze Wu |
| author_facet | Weidong Wang Xinyue Xu Jun Peng Wenbo Hu Dingze Wu |
| author_sort | Weidong Wang |
| collection | DOAJ |
| description | The automated detection of distress such as cracks or potholes is a key basis for assessing the condition of pavements and deciding on their maintenance. A fine-grained pavement distress-detection algorithm based on integrated data using a digital twin is proposed to solve the challenges of the insufficiency of high-quality negative samples in specific scenarios An asphalt pavement background model is created based on UAV-captured images, and a lightweight physical engine is used to randomly render 5 types of distress and 3 specific scenarios to the background model, generating a digital twin model that can provide virtual distress data. The virtual data are combined with real data in different virtual-to-real ratios (0:1 to 5:1) to form an integrated dataset and used to fully train deep object detection networks for fine-grained detection. The results show that the YOLOv5 network with the virtual-to-real ratio of 3:1 achieves the best average precision for 5 types of distress (asphalt pavement MAP: 75.40%), with a 2-fold and 1.5-fold improvement compared to models developed without virtual data and with traditional data augmentation, respectively, and achieves over 40% recall in shadow, occlusion and blur. The proposed approach could provide a more reliable and refined automated method for pavement analysis in complex scenarios. |
| first_indexed | 2024-03-11T05:41:47Z |
| format | Article |
| id | doaj.art-4df6eb00577e4fd69e4900da0926175b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:41:47Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4df6eb00577e4fd69e4900da0926175b2023-11-17T16:21:55ZengMDPI AGApplied Sciences2076-34172023-04-01137454910.3390/app13074549Fine-Grained Detection of Pavement Distress Based on Integrated Data Using Digital TwinWeidong Wang0Xinyue Xu1Jun Peng2Wenbo Hu3Dingze Wu4School of Civil Engineering, Central South University, Changsha 410075, ChinaSchool of Civil Engineering, Central South University, Changsha 410075, ChinaSchool of Civil Engineering, Central South University, Changsha 410075, ChinaSchool of Civil Engineering, Central South University, Changsha 410075, ChinaSchool of Civil Engineering, Central South University, Changsha 410075, ChinaThe automated detection of distress such as cracks or potholes is a key basis for assessing the condition of pavements and deciding on their maintenance. A fine-grained pavement distress-detection algorithm based on integrated data using a digital twin is proposed to solve the challenges of the insufficiency of high-quality negative samples in specific scenarios An asphalt pavement background model is created based on UAV-captured images, and a lightweight physical engine is used to randomly render 5 types of distress and 3 specific scenarios to the background model, generating a digital twin model that can provide virtual distress data. The virtual data are combined with real data in different virtual-to-real ratios (0:1 to 5:1) to form an integrated dataset and used to fully train deep object detection networks for fine-grained detection. The results show that the YOLOv5 network with the virtual-to-real ratio of 3:1 achieves the best average precision for 5 types of distress (asphalt pavement MAP: 75.40%), with a 2-fold and 1.5-fold improvement compared to models developed without virtual data and with traditional data augmentation, respectively, and achieves over 40% recall in shadow, occlusion and blur. The proposed approach could provide a more reliable and refined automated method for pavement analysis in complex scenarios.https://www.mdpi.com/2076-3417/13/7/4549road engineeringpavement-distress detectiondigital twinintegrated dataphysical enginedeep-object detection network |
| spellingShingle | Weidong Wang Xinyue Xu Jun Peng Wenbo Hu Dingze Wu Fine-Grained Detection of Pavement Distress Based on Integrated Data Using Digital Twin Applied Sciences road engineering pavement-distress detection digital twin integrated data physical engine deep-object detection network |
| title | Fine-Grained Detection of Pavement Distress Based on Integrated Data Using Digital Twin |
| title_full | Fine-Grained Detection of Pavement Distress Based on Integrated Data Using Digital Twin |
| title_fullStr | Fine-Grained Detection of Pavement Distress Based on Integrated Data Using Digital Twin |
| title_full_unstemmed | Fine-Grained Detection of Pavement Distress Based on Integrated Data Using Digital Twin |
| title_short | Fine-Grained Detection of Pavement Distress Based on Integrated Data Using Digital Twin |
| title_sort | fine grained detection of pavement distress based on integrated data using digital twin |
| topic | road engineering pavement-distress detection digital twin integrated data physical engine deep-object detection network |
| url | https://www.mdpi.com/2076-3417/13/7/4549 |
| work_keys_str_mv | AT weidongwang finegraineddetectionofpavementdistressbasedonintegrateddatausingdigitaltwin AT xinyuexu finegraineddetectionofpavementdistressbasedonintegrateddatausingdigitaltwin AT junpeng finegraineddetectionofpavementdistressbasedonintegrateddatausingdigitaltwin AT wenbohu finegraineddetectionofpavementdistressbasedonintegrateddatausingdigitaltwin AT dingzewu finegraineddetectionofpavementdistressbasedonintegrateddatausingdigitaltwin |