Real-time detection of road surface friction coefficient: A new framework integrating diffusion model and Transformer in Transformer algorithms
The real-time road surface friction coefficient (RSFC) is a critical parameter for evaluating skid resistance and making safe driving decisions in driver assistance systems and autonomous vehicles, especially under adverse weather conditions. RSFC estimation depends on the interaction between the ro...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824014170 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206943058231296 |
|---|---|
| author | Zhangcun Yan Lishengsa Yue Wang Luo Jian Sun |
| author_facet | Zhangcun Yan Lishengsa Yue Wang Luo Jian Sun |
| author_sort | Zhangcun Yan |
| collection | DOAJ |
| description | The real-time road surface friction coefficient (RSFC) is a critical parameter for evaluating skid resistance and making safe driving decisions in driver assistance systems and autonomous vehicles, especially under adverse weather conditions. RSFC estimation depends on the interaction between the road surface and tires. However, accurate estimation is challenging due to varying road environments and sensor errors that can cause significant distortions. To obtain high-accuracy RSFC, this study proposes a novel real-time RSFC detection method that integrates a diffusion model with the Transformer-in-Transformer(TNT) model to detect RSFC from vehicle video pictures. The method consists of three steps. First, we created labeled friction coefficient image datasets representing asphalt concrete surfaces under four moisture conditions. Second, we used a diffusion model to enhance the dataset, increasing sample diversity. Finally, we trained a TNT model on the extended dataset to recognize friction coefficients. The approach was tested across various datasets and compared to four state-of-the-art (SOTA) methods. The results show that the proposed method significantly improves accuracy, achieving a 22.89% increase compared to the unenhanced dataset and a 5.59% improvement over SOTA methods. The primary contribution of this study is the integration of generative artificial intelligence and computer vision algorithms to enhance RSFC recognition accuracy. Furthermore, the recognition method meets the real-time performance requirements, processing frames in just two milliseconds. This method can be an effective tool for perceiving road surface environmental parameters and holds significant value in improving driving safety under adverse weather conditions. |
| format | Article |
| id | doaj-art-541a1b44a4af4edc9e54be8aff28162c |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-541a1b44a4af4edc9e54be8aff28162c2025-02-07T04:46:59ZengElsevierAlexandria Engineering Journal1110-01682025-02-01113620632Real-time detection of road surface friction coefficient: A new framework integrating diffusion model and Transformer in Transformer algorithmsZhangcun Yan0Lishengsa Yue1Wang Luo2Jian Sun3Key Laboratory of Road and Traffic Engineering of Ministry of Education & School of Transportation Engineering, Tongji University. No. 4800 Cao’an Road, Shanghai, 201804, ChinaKey Laboratory of Road and Traffic Engineering of Ministry of Education & School of Transportation Engineering, Tongji University. No. 4800 Cao’an Road, Shanghai, 201804, China; Corresponding author.Smart Transportation Key Laboratory of Hunan Province, School of Traffic and Transportation Engineering, Central South University, Changsha 410075, ChinaKey Laboratory of Road and Traffic Engineering of Ministry of Education & School of Transportation Engineering, Tongji University. No. 4800 Cao’an Road, Shanghai, 201804, ChinaThe real-time road surface friction coefficient (RSFC) is a critical parameter for evaluating skid resistance and making safe driving decisions in driver assistance systems and autonomous vehicles, especially under adverse weather conditions. RSFC estimation depends on the interaction between the road surface and tires. However, accurate estimation is challenging due to varying road environments and sensor errors that can cause significant distortions. To obtain high-accuracy RSFC, this study proposes a novel real-time RSFC detection method that integrates a diffusion model with the Transformer-in-Transformer(TNT) model to detect RSFC from vehicle video pictures. The method consists of three steps. First, we created labeled friction coefficient image datasets representing asphalt concrete surfaces under four moisture conditions. Second, we used a diffusion model to enhance the dataset, increasing sample diversity. Finally, we trained a TNT model on the extended dataset to recognize friction coefficients. The approach was tested across various datasets and compared to four state-of-the-art (SOTA) methods. The results show that the proposed method significantly improves accuracy, achieving a 22.89% increase compared to the unenhanced dataset and a 5.59% improvement over SOTA methods. The primary contribution of this study is the integration of generative artificial intelligence and computer vision algorithms to enhance RSFC recognition accuracy. Furthermore, the recognition method meets the real-time performance requirements, processing frames in just two milliseconds. This method can be an effective tool for perceiving road surface environmental parameters and holds significant value in improving driving safety under adverse weather conditions.http://www.sciencedirect.com/science/article/pii/S1110016824014170Road engineeringRoad surface friction coefficient detectionImage classificationData augmentationDiffusion modelTransform in transform |
| spellingShingle | Zhangcun Yan Lishengsa Yue Wang Luo Jian Sun Real-time detection of road surface friction coefficient: A new framework integrating diffusion model and Transformer in Transformer algorithms Alexandria Engineering Journal Road engineering Road surface friction coefficient detection Image classification Data augmentation Diffusion model Transform in transform |
| title | Real-time detection of road surface friction coefficient: A new framework integrating diffusion model and Transformer in Transformer algorithms |
| title_full | Real-time detection of road surface friction coefficient: A new framework integrating diffusion model and Transformer in Transformer algorithms |
| title_fullStr | Real-time detection of road surface friction coefficient: A new framework integrating diffusion model and Transformer in Transformer algorithms |
| title_full_unstemmed | Real-time detection of road surface friction coefficient: A new framework integrating diffusion model and Transformer in Transformer algorithms |
| title_short | Real-time detection of road surface friction coefficient: A new framework integrating diffusion model and Transformer in Transformer algorithms |
| title_sort | real time detection of road surface friction coefficient a new framework integrating diffusion model and transformer in transformer algorithms |
| topic | Road engineering Road surface friction coefficient detection Image classification Data augmentation Diffusion model Transform in transform |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824014170 |
| work_keys_str_mv | AT zhangcunyan realtimedetectionofroadsurfacefrictioncoefficientanewframeworkintegratingdiffusionmodelandtransformerintransformeralgorithms AT lishengsayue realtimedetectionofroadsurfacefrictioncoefficientanewframeworkintegratingdiffusionmodelandtransformerintransformeralgorithms AT wangluo realtimedetectionofroadsurfacefrictioncoefficientanewframeworkintegratingdiffusionmodelandtransformerintransformeralgorithms AT jiansun realtimedetectionofroadsurfacefrictioncoefficientanewframeworkintegratingdiffusionmodelandtransformerintransformeralgorithms |