Smart City Gnosys
Smart city article details
| Title | A Comparative Study Of Deep Learning Methods For Automated Road Network Extraction From High-Spatial-Resolution Remotely Sensed Imagery |
|---|---|
| ID_Doc | 789 |
| Authors | Zhou H.; He H.; Xu L.; Ma L.; Zhang D.; Chen N.; Chapman M.A.; Li J. |
| Year | 2025 |
| Published | Photogrammetric Engineering and Remote Sensing, 91, 3 |
| DOI | http://dx.doi.org/10.14358/PERS.24-00100R2 |
| Abstract | Road network data are crucial for various applications, such as road network planning, traffic control, map navigation, autonomous driving, and smart city construction. Automated road network extraction from high-spatial-resolution remotely sensed imagery has shown promise in road network data construction. In recent years, the advent of deep learning algorithms has pushed road network extraction towards auto-mation, achieving very high accuracy. However, the latest deep learning models are often less applied in the field of road network extraction and lack comparative experiments for guidance. Therefore, this research selected three recent deep learning algorithms, including dense prediction transformer (DPT), SegFormer, SEgmentation TRansformer (SETR), and the classic model fully convolutional network-8s (FCN-8s) for a comparative study. Additionally, this research paper compares three different decoder structures within the SETR model (SETR_naive, SETR_mla, SETR_pup) to investigate the effect of different decoders on the road network extraction task. The experiment is conducted on three commonly Delivered bused datasets: the DeepGlobe Dataset, the Massachusetts Dataset, and IP: 125.17.16.94 On: FriRoad Datasets in Complex Mountain Environments (RDCME). The Copyright: American Society for PhoDPT model outperforms other models on the Massachusetts dataset with superior reliability, achieving a high accuracy of 96.31% and excel-ling with a precision of 81.78% and recall of 32.50%, leading to an F1 score of 46.51%. While SegFormer has a slightly higher F1 score, DPT’s precision is particularly valuable for minimizing false positives, making it the most balanced and reliable choice. Similarly, for the DeepGlobe Dataset, DPT achieves an accuracy of 96.76%, precision of 66.12%, recall of 41.37%, and F1 score of 50.89%, and for RDCME, DPT achieves an accuracy of 98.94%, precision of 99.07%, recall of 99.84%, and F1 score of 99.46%, confirming its consistent performance across datasets. This paper provides valuable guidance for future studies on road network extraction techniques using deep learning algorithms. © 2025 American Society for Photogrammetry and Remote Sensing. |
| Author Keywords |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
17968  | 0.933 | Lu X.; Weng Q. | Deep Learning-Based Road Extraction From Remote Sensing Imagery: Progress, Problems, And Perspectives | ISPRS Journal of Photogrammetry and Remote Sensing, 228 (2025) |
| 46779 | 0.924 | Kumar K.M. | Roadtransnet: Advancing Remote Sensing Road Extraction Through Multi-Scale Features And Contextual Information | Signal, Image and Video Processing, 18, 3 (2024) |
| 60739 | 0.912 | Jiang Y.; Zhao J.; Luo W.; Guo B.; An Z.; Xu Y. | Utilizing Gcn-Based Deep Learning For Road Extraction From Remote Sensing Images | Sensors, 25, 13 (2025) |
| 48027 | 0.904 | Tao J.; Chen Z.; Sun Z.; Guo H.; Leng B.; Yu Z.; Wang Y.; He Z.; Lei X.; Yang J. | Seg-Road: A Segmentation Network For Road Extraction Based On Transformer And Cnn With Connectivity Structures | Remote Sensing, 15, 6 (2023) |
| 25932 | 0.899 | Bimanjaya A.; Handayani H.H.; Rachmadi R.F. | Extraction Of Road Network In Urban Area From Orthophoto Using Deep Learning And Douglas-Peucker Post-Processing Algorithm | IOP Conference Series: Earth and Environmental Science, 1127, 1 (2023) |
| 4194 | 0.898 | Pruthi J.; Dhingra S. | A Review Of Research On Road Feature Extraction Through Remote Sensing Images Based On Deep Learning Algorithms | Proceedings - 2023 3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023 (2023) |
| 28317 | 0.897 | Lu X.; Zhong Y.; Zheng Z.; Chen D. | Gre And Beyond: A Global Road Extraction Dataset | International Geoscience and Remote Sensing Symposium (IGARSS), 2022-July (2022) |
| 35155 | 0.896 | Niu P.; Cai T.; Zhang Y.; Zhang P.; Xu W.; Gu J.; Han J. | Lg-Umer: Unet-Like Network Integrate Local-Global Feature With Novel Attention For Road Extraction From Remote Sensing Images | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2025) |
| 45994 | 0.894 | Xu Y.; Shi Z.; Xie X.; Chen Z.; Xie Z. | Residual Channel Attention Fusion Network For Road Extraction Based On Remote Sensing Images And Gps Trajectories | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17 (2024) |
| 38457 | 0.89 | Li S.; Liu X. | Multi-Type Road Extraction And Analysis Of High-Resolution Images With D-Linknet50 | 2022 3rd International Conference on Geology, Mapping and Remote Sensing, ICGMRS 2022 (2022) |