CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection
Existing traffic flow modeling approaches typically rely on real-time observations, such as road sensors or GPS trajectories, which constrain their research scope and application scenarios. This study proposes a novel cross-spatiotemporal graph-based network method to rapidly reconstruct traffic flo...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-08-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/17538947.2025.2528640 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849224363807604736 |
|---|---|
| author | Yan Zhang Mei-Po Kwan Jiannan Cai Jianying Wang Peifeng Ma |
| author_facet | Yan Zhang Mei-Po Kwan Jiannan Cai Jianying Wang Peifeng Ma |
| author_sort | Yan Zhang |
| collection | DOAJ |
| description | Existing traffic flow modeling approaches typically rely on real-time observations, such as road sensors or GPS trajectories, which constrain their research scope and application scenarios. This study proposes a novel cross-spatiotemporal graph-based network method to rapidly reconstruct traffic flow speed based on remote sensing images. The method is designed to address the challenges of traffic modeling in the absence of ground observation data. Combining high-resolution remote sensing imagery, vehicle object detection, and graph modeling technology, our approach could handle the discontinuous spatiotemporal graph information. The method incorporates two key modules: a two-layer masked structure mechanism and a cross-spatiotemporal attention computation. This innovative design enables the model to continuously synthesize learning from discontinuous remote sensing images and sparse ground-based sensor data during pre-training, optimizing its parameters and improving prediction accuracy over time. Once pre-trained, the graph model can directly estimate street-level traffic flow speed based solely on remote sensing images. Our results demonstrate state-of-the-art performance (MSE=40.117, MAE=4.768, RMSE=6.334, RSE=0.228), outperforming previous graph-based and sequence-based models. This study showcases the potential of utilizing remote sensing techniques to reconstruct traffic speed in urbanizing regions. It can even be used in scenarios lacking sufficient ground stations and with discontinuous remote sensing data, and enables low-cost, large-scale, and multi-temporal traffic flow speed reconstruction. |
| format | Article |
| id | doaj-art-5f4d01c68904444586012defcebe1fb1 |
| institution | Kabale University |
| issn | 1753-8947 1753-8955 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj-art-5f4d01c68904444586012defcebe1fb12025-08-25T11:25:08ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2528640CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detectionYan Zhang0Mei-Po Kwan1Jiannan Cai2Jianying Wang3Peifeng Ma4Institute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaInstitute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaInstitute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaInstitute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaInstitute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong SAR, People's Republic of ChinaExisting traffic flow modeling approaches typically rely on real-time observations, such as road sensors or GPS trajectories, which constrain their research scope and application scenarios. This study proposes a novel cross-spatiotemporal graph-based network method to rapidly reconstruct traffic flow speed based on remote sensing images. The method is designed to address the challenges of traffic modeling in the absence of ground observation data. Combining high-resolution remote sensing imagery, vehicle object detection, and graph modeling technology, our approach could handle the discontinuous spatiotemporal graph information. The method incorporates two key modules: a two-layer masked structure mechanism and a cross-spatiotemporal attention computation. This innovative design enables the model to continuously synthesize learning from discontinuous remote sensing images and sparse ground-based sensor data during pre-training, optimizing its parameters and improving prediction accuracy over time. Once pre-trained, the graph model can directly estimate street-level traffic flow speed based solely on remote sensing images. Our results demonstrate state-of-the-art performance (MSE=40.117, MAE=4.768, RMSE=6.334, RSE=0.228), outperforming previous graph-based and sequence-based models. This study showcases the potential of utilizing remote sensing techniques to reconstruct traffic speed in urbanizing regions. It can even be used in scenarios lacking sufficient ground stations and with discontinuous remote sensing data, and enables low-cost, large-scale, and multi-temporal traffic flow speed reconstruction.https://www.tandfonline.com/doi/10.1080/17538947.2025.2528640Traffic flow reconstructionGeoAIvehicle detectiongraph neural networkmultimodal fusionground-based sensors |
| spellingShingle | Yan Zhang Mei-Po Kwan Jiannan Cai Jianying Wang Peifeng Ma CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection International Journal of Digital Earth Traffic flow reconstruction GeoAI vehicle detection graph neural network multimodal fusion ground-based sensors |
| title | CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection |
| title_full | CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection |
| title_fullStr | CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection |
| title_full_unstemmed | CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection |
| title_short | CrossGraphNet: a cross-spatiotemporal graph-based method for traffic speed reconstruction using remote sensing vehicle detection |
| title_sort | crossgraphnet a cross spatiotemporal graph based method for traffic speed reconstruction using remote sensing vehicle detection |
| topic | Traffic flow reconstruction GeoAI vehicle detection graph neural network multimodal fusion ground-based sensors |
| url | https://www.tandfonline.com/doi/10.1080/17538947.2025.2528640 |
| work_keys_str_mv | AT yanzhang crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection AT meipokwan crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection AT jiannancai crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection AT jianyingwang crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection AT peifengma crossgraphnetacrossspatiotemporalgraphbasedmethodfortrafficspeedreconstructionusingremotesensingvehicledetection |