Smart City Gnosys
Smart city article details
| Title | Sturm-Flooddepth: A Deep Learning Pipeline For Mapping Urban Flood Depth Using Street-Level And Oblique Aerial Imagery |
|---|---|
| ID_Doc | 53553 |
| Authors | Notarangelo N.M.; Wirion C.; van Winsen F. |
| Year | 2025 |
| Published | Geomatica, 77, 2 |
| DOI | http://dx.doi.org/10.1016/j.geomat.2025.100061 |
| Abstract | Flooding remains one of the most frequent and damaging natural disasters, intensified by climate change and urbanization. High-resolution real-time flood depth observations at the urban scale remain spatially sparse, thus alternative data sources are required to support risk assessment and emergency response. This study introduces STURM-FloodDepth, a deep learning pipeline to estimate and map urban flood depths using street-level and oblique aerial imagery. The workflow consists of two sequential modules: A. flood depth estimation, proceeding through vehicle detection (YOLO-World and SAHI), contextual cropping, super-resolution enhancement (EDSR), and flood level classification (fine-tuned ResNet-50); and B. georeferencing and mapping, proceeding through orthographic reference image construction, feature matching (SuperGlue), homography estimation (RANSAC), geospatial projection and mapping, conversion and export to GeoJSON. The classifier achieved AUC values ranging from 0.78 to 0.98 across all classes. Real-world qualitative validation confirmed its accuracy in operational conditions. STURM-FloodDepth is a modular, scalable, sensor-agnostic tool for urban flood monitoring, with applications for urban resilience, disaster management, and smart city. The framework is released as an open-source tool to foster further research and operational deployments. © 2025 |
| Author Keywords | Computer vision; Deep learning; Flood depth; Oblique aerial imagery; Smart city; Street-level imagery; Urban flood; Urban resilience |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
26675  | 0.879 | Meng Z.; Peng B.; Huang Q. | Flood Depth Estimation From Web Images | Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities, ARIC 2019 (2019) |
| 8598 | 0.878 | Ahmed I.; Ahmad M.; Jeon G.; Chehri A. | An Internet Of Things And Ai-Powered Framework For Long-Term Flood Risk Evaluation | IEEE Internet of Things Journal, 11, 3 (2024) |
| 922 | 0.869 | Liu B.; Li Y.; Ma M.; Mao B. | A Comprehensive Review Of Machine Learning Approaches For Flood Depth Estimation | International Journal of Disaster Risk Science, 16, 3 (2025) |
| 48317 | 0.861 | Wang R.-Q.; Ding Y. | Semi-Supervised Identification And Mapping Of Surface Water Extent Using Street-Level Monitoring Videos | Big Earth Data, 7, 4 (2023) |
| 44487 | 0.86 | Sheng Z.; Chen F.; Liu Q.; Gao B.; Zhang J.; Zhao K.; Liu Q.; Zang Y. | Real-Time Waterlogging Monitoring On Urban Roads Using Edge Computing | Water Resources Management (2025) |
| 17968 | 0.856 | 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) |
| 26689 | 0.855 | Peixoto J.P.J.; Costa D.G.; Portugal P.; Vasques F. | Flood-Resilient Smart Cities: A Data-Driven Risk Assessment Approach Based On Geographical Risks And Emergency Response Infrastructure | Smart Cities, 7, 1 (2024) |
| 60525 | 0.854 | Mishra B.K.; Thakker D.; Mazumdar S.; Simpson S.; Neagu D. | Using Deep Learning For Iot-Enabled Camera: A Use Case Of Flood Monitoring | Conference Proceedings of 2019 10th International Conference on Dependable Systems, Services and Technologies, DESSERT 2019 (2019) |
| 10738 | 0.852 | Righetti F.; Vallati C.; Tubak A.K.; Roy N.; Basnyat B.; Anastasi G. | Assessing The Feasibility Of Exploiting Edge Computing For Real-Time Monitoring Of Flash Floods | Proceedings - 2022 IEEE International Conference on Smart Computing, SMARTCOMP 2022 (2022) |