UFD-YOLO: a lightweight multi-reference model for urban flood risk level detection from surveillance images
7 affiliations
- 1China Meteorological Administration Hydro-Meteorology Key Laboratory, College of Hydrology and Water Resources, Hohai University
- 2School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology
- 3Key Laboratory of Urban Meteorology, China Meteorological Administration
- 4The Business School, Beijing Normal University
- 5Pearl River Water Resources Research Institute
- 6School of Computer Engineering, Nanjing Institute of Technology
- 7National Institute of Education, Nanyang Technological University
Abstract
Flood disasters pose persistent challenges to urban safety and emergency management. Traditional remote sensing technologies remain limited in real-time capability and spatial coverage. In surveillance-based urban flood monitoring, direct physical measurement of flood depth is often unavailable; therefore, flood risk level detection based on visual reference objects provides a feasible alternative for rapid flood assessment. However, existing lightweight YOLO models still struggle to accurately identify submerged targets under partial submergence, large-scale variation, and complex urban conditions. To address these issues, this study proposes UFD-YOLO, a lightweight framework for urban flood risk level detection using pedestrians and vehicles as multi-scale visual references. First, a reference-based flood risk level criterion was established according to the submergence states of pedestrians and vehicles, and a dataset covering diverse urban scenarios was constructed. Second, the DySnakeConv, AIFI, and DetectAux were progressively integrated into YOLO11n to improve local structural perception, strengthen feature interaction, and enhance multi-scale supervisory learning. Compared with YOLO11n, UFD-YOLO improves Precision, Recall, mAP50, and mAP50:95 by 2.5%, 5.1%, 5.8%, and 2.6%, respectively, while maintaining low computational cost. Additional evaluations further demonstrate its accurate and stable performance in challenging scenarios. Overall, this study provides an effective technical approach for urban flood risk assessment.
Related
- GFLNet: A lightweight real-time detector with knowledge-guided compression in remote sensing images
- Multi-Horizon Typhoon Wind Field Prediction via a Lightweight CNN–LSTM Network: Error Growth and Cross-Year Robustness at 6–24 h Lead Times
- Physics‐Informed Fusion Learning for Nowcasting Fault Detection of Hydrological Multi Sensor Network
- DFL-YOLO: Density-Guided Frequency Decoupling and Large Selective Kernels improve dense multi-class tree crown detection
- Collapsed Building Detection from Multi-Temporal Pléiades Imagery: Comparing CNN Architectures and Input Data Strategies
BibTeX
@article{wan2026ufdyolo,
title = {{UFD-YOLO: a lightweight multi-reference model for urban flood risk level detection from surveillance images}},
author = {Jiaquan Wan and Yannian Cheng and Junchao Wang and Ranyu Liu and Hao Song and Wei Zhang and Xing Wang and Fengchang Xue and Jingyu Wang and Quan J. Wang and Tao Yang},
journal = {npj Natural Hazards},
year = {2026},
month = jun,
doi = {10.1038/s44304-026-00224-5},
url = {https://doi.org/10.1038/s44304-026-00224-5},
note = {CC BY},
}
RIS
TY - JOUR
TI - UFD-YOLO: a lightweight multi-reference model for urban flood risk level detection from surveillance images
AU - Jiaquan Wan
AU - Yannian Cheng
AU - Junchao Wang
AU - Ranyu Liu
AU - Hao Song
AU - Wei Zhang
AU - Xing Wang
AU - Fengchang Xue
AU - Jingyu Wang
AU - Quan J. Wang
AU - Tao Yang
PY - 2026
DA - 2026/06/01
JO - npj Natural Hazards
DO - 10.1038/s44304-026-00224-5
UR - https://doi.org/10.1038/s44304-026-00224-5
AB - Flood disasters pose persistent challenges to urban safety and emergency management. Traditional remote sensing technologies remain limited in real-time capability and spatial coverage. In surveillance-based urban flood monitoring, direct physical measurement of flood depth is often unavailable; therefore, flood risk level detection based on visual reference objects provides a feasible alternative for rapid flood assessment. However, existing lightweight YOLO models still struggle to accurately identify submerged targets under partial submergence, large-scale variation, and complex urban conditions. To address these issues, this study proposes UFD-YOLO, a lightweight framework for urban flood risk level detection using pedestrians and vehicles as multi-scale visual references. First, a reference-based flood risk level criterion was established according to the submergence states of pedestrians and vehicles, and a dataset covering diverse urban scenarios was constructed. Second, the DySnakeConv, AIFI, and DetectAux were progressively integrated into YOLO11n to improve local structural perception, strengthen feature interaction, and enhance multi-scale supervisory learning. Compared with YOLO11n, UFD-YOLO improves Precision, Recall, mAP50, and mAP50:95 by 2.5%, 5.1%, 5.8%, and 2.6%, respectively, while maintaining low computational cost. Additional evaluations further demonstrate its accurate and stable performance in challenging scenarios. Overall, this study provides an effective technical approach for urban flood risk assessment.
SN - 2948-2100
ER -