Work

DroneRiver: An Aerial Semantic Segmentation Dataset for Analysis of River Leakage

Year: 2025

Type: article

Abstract: Currently, existing drone datasets mainly focus on collecting data in urban environments. However, there are numerous residential and farming areas located alongside the river in rural regions. If there is heavy rain and flooding, the river is likely to overflow, posing a threat to human lives and property. In this paper, we collect a novel drone-captured dataset, called DroneRiver, tailored for water management of pre-disaster scenarios and analysis of preliminary river leakage in rural areas. DroneRiver provides annotations for the objects on both sides of the river, such as people, vehicles, levee roads, farms, vegetation, etc. Additionally, to overcome the difficulty of collecting real-world river leakage scenes without environmental harm, based on the recent generative model, preliminary river leakage images can be generated in our datasets for pre-disaster prevention and alerts. Finally, our dataset annotates the original and generated aerial at the pixel level for semantic segmentation. We also conduct extensive experiments using state-of-the-art segmentation models and evaluate the quality of the generated aerial images. The results demonstrate the significance of the DroneRiver dataset for river leakage analysis.

Source: IEEE Access

DOI: 10.1109/access.2025.3595602

Authors: Yi Tang, Pengfei Lyu, Hidekazu Shirai, Yasuharu Watanabe, Hiroshi Masui

Institution: Kitami Institute of Technology

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDGs: Clean water and sanitation, Sustainable cities and communities

Open Access status: gold

Estimated APC paid: $2,075