RLGD: A High-Resolution UAV Dataset and Benchmark for Semantic Segmentation and Revetment Extraction in Waterway Scenes
Open Access
- 24 October 2026
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 18 (21) , 3656
Abstract
High-resolution unmanned aerial vehicle (UAV) imagery is increasingly used for waterway inspection, but automated scene understanding remains constrained by the lack of pixel-level datasets that explicitly represent revetments and their complex interfaces with water, vegetation, roads, and riverside structures. We introduce the Riverway and Landscape Ground Dataset (RLGD), a dedicated UAV semantic segmentation dataset for waterway scenes. RLGD contains 100 images at pixels, corresponding to 1.2 billion labeled pixels. Its public RLGD taxonomy explicitly includes revetment. Seven semantic segmentation models are evaluated under a unified protocol. Across five training runs with different random seeds, mean mIoU ranges from 69.27% to 77.02%, while Hierarchical Joint Network with Boundary Guidance (GHJNet) achieves 77.02 ± 0.41% mIoU and 83.51 ± 1.18% revetment IoU. Direct transfer from Varied Drone Dataset (VDD) to RLGD results in relative mIoU reductions of 11.29–49.81%, whereas adaptation using 20% of the RLGD training source images closes 65.5% of the measured domain gap. For the GHJNet run used in the downstream analysis, object-prior refinement using the Segment Anything Model (SAM) increases revetment IoU from 84.10% to 87.25%. A 42-image visual-completeness screening case study further achieves 83.93% macro-F1 and 81.25% balanced accuracy against image-level interpretations by three experts. Overall, RLGD provides a densely annotated, task-specific benchmark for dry-season waterway semantic segmentation, revetment extraction, and image-level inspection prioritization within the surveyed Yangtze River corridor.
Keywords
Funding Information
- Changjiang River Administration of Navigational Affairs (2025-020-6-Z-Y)
- Key Research and Development Project of Hubei Province (2024BCB101)
This publication has 33 references indexed in Scilit:
- Smart UAV-assisted blueberry maturity monitoring with Mamba-based computer visionPrecision Agriculture, 2025
- VDD: Varied Drone Dataset for semantic segmentationJournal of Visual Communication and Image Representation, 2025
- Advanced ship detection and ocean monitoring with satellite imagery and deep learning for marine science applicationsRegional Studies in Marine Science, 2024
- Methods and datasets on semantic segmentation for Unmanned Aerial Vehicle remote sensing images: A reviewISPRS Journal of Photogrammetry and Remote Sensing, 2024
- The Segment Anything Model (SAM) for remote sensing applications: From zero to one shotInternational Journal of Applied Earth Observation and Geoinformation, 2023
- Detect and identify earth rock embankment leakage based on UAV visible and infrared imagesInfrared Physics & Technology, 2022
- UAVid: A semantic segmentation dataset for UAV imageryISPRS Journal of Photogrammetry and Remote Sensing, 2020
- HRSID: A High-Resolution SAR Images Dataset for Ship Detection and Instance SegmentationIEEE Access, 2020
- Monitoring river morphology & bank erosion using UAV imagery – A case study of the river Buëch, Hautes-Alpes, FranceInternational Journal of Applied Earth Observation and Geoinformation, 2018
- Topological structural analysis of digitized binary images by border followingComputer Vision, Graphics, and Image Processing, 1985