A lightweight end to end traffic congestion detection framework using HRTNet on the Qinghai Tibet plateau
Abstract Managing traffic in plateau regions, particularly on critical routes like the Qinghai-Tibet Line, presents significant challenges from extreme climate and terrain. Traditional monitoring methods struggle with image distortion and information loss in rain, compromising congestion detection....
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-13550-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849333194095067136 |
|---|---|
| author | Yuhao Zhang Qiuhong Tong Zhaorong Zhang Xueqi Dai Junzheng Wang Daifang Hu Shengjun Su |
| author_facet | Yuhao Zhang Qiuhong Tong Zhaorong Zhang Xueqi Dai Junzheng Wang Daifang Hu Shengjun Su |
| author_sort | Yuhao Zhang |
| collection | DOAJ |
| description | Abstract Managing traffic in plateau regions, particularly on critical routes like the Qinghai-Tibet Line, presents significant challenges from extreme climate and terrain. Traditional monitoring methods struggle with image distortion and information loss in rain, compromising congestion detection. To address these issues, we propose HRTNet, a lightweight real-time end-to-end model for congestion monitoring. HRTNet uses a clever design to clear rain streaks and highlight key details, making it easier to spot vehicles in bad weather. We also introduce the RainyRoad-PlateauDataset (RRPD), the first of its kind, with 3750 images capturing high-altitude rainy roads. This dataset is tailored to test performance under tough meteorological and topographical conditions. Evaluations show HRTNet achieves an average precision of 46.8% on the COCO val2017 and 134 FPS on an NVIDIA A6000 GPU. On RRPD, its precision rises to 50.5%, beating RT-DETR-r18 by 9.2%. HRTNet was deployed to monitor traffic congestion on rainy plateaus, enabling accurate calculation of congestion duration and distance. This provides critical support for intelligent traffic management systems like dynamic congestion warning and adaptive signal control. Beyond plateaus, this work offers solutions for traffic systems in other harsh environments. |
| format | Article |
| id | doaj-art-8cc540fd7f2a4c0eb782779d105d2bb1 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-8cc540fd7f2a4c0eb782779d105d2bb12025-08-20T03:45:57ZengNature PortfolioScientific Reports2045-23222025-08-0115111610.1038/s41598-025-13550-xA lightweight end to end traffic congestion detection framework using HRTNet on the Qinghai Tibet plateauYuhao Zhang0Qiuhong Tong1Zhaorong Zhang2Xueqi Dai3Junzheng Wang4Daifang Hu5Shengjun Su6School of Automobile, Chang’an UniversityXi’an Institute of Optics and Precision Mechanics of CASSchool of Automobile, Chang’an UniversitySchool of Automobile, Chang’an UniversitySchool of Automobile, Chang’an UniversitySchool of Automobile, Chang’an UniversitySchool of Automobile, Chang’an UniversityAbstract Managing traffic in plateau regions, particularly on critical routes like the Qinghai-Tibet Line, presents significant challenges from extreme climate and terrain. Traditional monitoring methods struggle with image distortion and information loss in rain, compromising congestion detection. To address these issues, we propose HRTNet, a lightweight real-time end-to-end model for congestion monitoring. HRTNet uses a clever design to clear rain streaks and highlight key details, making it easier to spot vehicles in bad weather. We also introduce the RainyRoad-PlateauDataset (RRPD), the first of its kind, with 3750 images capturing high-altitude rainy roads. This dataset is tailored to test performance under tough meteorological and topographical conditions. Evaluations show HRTNet achieves an average precision of 46.8% on the COCO val2017 and 134 FPS on an NVIDIA A6000 GPU. On RRPD, its precision rises to 50.5%, beating RT-DETR-r18 by 9.2%. HRTNet was deployed to monitor traffic congestion on rainy plateaus, enabling accurate calculation of congestion duration and distance. This provides critical support for intelligent traffic management systems like dynamic congestion warning and adaptive signal control. Beyond plateaus, this work offers solutions for traffic systems in other harsh environments.https://doi.org/10.1038/s41598-025-13550-xTraffic congestion detectionRain streak removalEnd-to-endTransformer |
| spellingShingle | Yuhao Zhang Qiuhong Tong Zhaorong Zhang Xueqi Dai Junzheng Wang Daifang Hu Shengjun Su A lightweight end to end traffic congestion detection framework using HRTNet on the Qinghai Tibet plateau Scientific Reports Traffic congestion detection Rain streak removal End-to-end Transformer |
| title | A lightweight end to end traffic congestion detection framework using HRTNet on the Qinghai Tibet plateau |
| title_full | A lightweight end to end traffic congestion detection framework using HRTNet on the Qinghai Tibet plateau |
| title_fullStr | A lightweight end to end traffic congestion detection framework using HRTNet on the Qinghai Tibet plateau |
| title_full_unstemmed | A lightweight end to end traffic congestion detection framework using HRTNet on the Qinghai Tibet plateau |
| title_short | A lightweight end to end traffic congestion detection framework using HRTNet on the Qinghai Tibet plateau |
| title_sort | lightweight end to end traffic congestion detection framework using hrtnet on the qinghai tibet plateau |
| topic | Traffic congestion detection Rain streak removal End-to-end Transformer |
| url | https://doi.org/10.1038/s41598-025-13550-x |
| work_keys_str_mv | AT yuhaozhang alightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT qiuhongtong alightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT zhaorongzhang alightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT xueqidai alightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT junzhengwang alightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT daifanghu alightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT shengjunsu alightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT yuhaozhang lightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT qiuhongtong lightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT zhaorongzhang lightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT xueqidai lightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT junzhengwang lightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT daifanghu lightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau AT shengjunsu lightweightendtoendtrafficcongestiondetectionframeworkusinghrtnetontheqinghaitibetplateau |