EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Topology-Aware Road Extraction from Remote Sensing Images Using Deep Learning and Graph-Based Connectivity Refinement

Zixuan Teng, Zezhong Zheng, Xiangyang Sun, Hao Xue

ISPRS International Journal of Geo-Information · 09.05.2026 · 15 (5) · 208

DOI: 10.3390/ijgi15050208 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISPRS International Journal of Geo-Information, online erschienen am 09.05.2026. Verfasst von Zixuan Teng und 3 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Huzhou Municipal Science and Technology Bureau, Natural Science Foundation of Sichuan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Road networks are fundamental components of transportation infrastructure and play a crucial role in various geospatial applications. Although deep learning-based semantic segmentation models have achieved promising results in extracting roads from high-resolution remote sensing imagery, the resulting networks often suffer from topological fragmentation due to occlusions and shadows. To address this issue, we propose a topology-aware road extraction method that integrates deep learning-based segmentation with a graph-based connectivity refinement strategy. Specifically, a Pyramid Scene Parsing Network (PSPNet) is first employed to generate initial road probability maps. Subsequently, a connectivity-oriented post-processing pipeline is introduced, which incorporates a multi-source cost function strategy and a direction-aware Dijkstra search algorithm. By utilizing endpoint tangent vectors as inertial weights, the algorithm effectively reconstructs fragmented segments while ensuring geometric smoothness and topological consistency. Furthermore, a dynamic road width restoration strategy is applied to transform refined skeletons into physically consistent road entities. Experiments conducted on two publicly available datasets, CHN6-CUG and DeepGlobe, demonstrate the effectiveness of the proposed method. Quantitative results show that the refinement process significantly enhances road connectivity with a minimal trade-off in pixel-level accuracy. Specifically, the Conn metric increases by 0.1989 on the CHN6-CUG dataset and 0.3055 on the DeepGlobe dataset, while MIoU remains high with only marginal decreases of 1.07% and 0.45%, respectively. These findings indicate that the method effectively restores structural continuity, helping with reliable road network generation and subsequent integration into Geographic Information System (GIS)-based applications such as urban planning and autonomous navigation.

Förderung

  • Huzhou Municipal Science and Technology Bureau
  • Natural Science Foundation of Sichuan Province

Zitieren

APA

Teng, Z., Zheng, Z., Sun, X., & Xue, H. (2026). Topology-Aware Road Extraction from Remote Sensing Images Using Deep Learning and Graph-Based Connectivity Refinement. ISPRS International Journal of Geo-Information, 15(5), 208. https://doi.org/10.3390/ijgi15050208

Vancouver

Teng Z, Zheng Z, Sun X, Xue H. Topology-Aware Road Extraction from Remote Sensing Images Using Deep Learning and Graph-Based Connectivity Refinement. ISPRS International Journal of Geo-Information. 2026;15(5):208. doi:10.3390/ijgi15050208

BibTeX
@article{Teng2026,
  author = {Teng, Zixuan and Zheng, Zezhong and Sun, Xiangyang and Xue, Hao},
  title = {Topology-Aware Road Extraction from Remote Sensing Images Using Deep Learning and Graph-Based Connectivity Refinement},
  journal = {ISPRS International Journal of Geo-Information},
  year = {2026},
  volume = {15},
  number = {5},
  pages = {208},
  doi = {10.3390/ijgi15050208}
}
Kostenlos starten →