Loading...
Loading...
Contributors:
Dataset URI:
10.6084/m9.figshare.32616651.v1This dataset provides high-resolution UAV orthophoto imagery and derived raster data for oyster reef spatial distribution extraction and area quantification in the Liya Mountain National Marine Park, Nantong City, Jiangsu Province, China.Field experiments were conducted from December 3 to 8, 2025, in an intertidal coastal zone located at approximately 121°32′15″ E, 32°9′5″ N. This region hosts the largest natural intertidal oyster reef system in China, with a formation history exceeding 1,400 years and significant ecological and scientific value.The dataset is based on UAV (Unmanned Aerial Vehicle) multispectral imagery, processed through radiometric correction, geometric correction, and orthomosaic generation to produce georeferenced high-resolution orthophotos. All raster data are provided in GeoTIFF format with WGS 84 geographic coordinate system (EPSG:4326), 4 spectral bands, and 8-bit pixel depth.Due to UAV operational constraints (flight endurance, altitude, and sensor field of view), representative subregions were selected for detailed analysis. The dataset explicitly distinguishes between two environmental conditions:Illuminated Area: Regions with sufficient sunlight, showing clear texture and structural featuresShaded Area: Regions affected by shadow (primarily caused by lighthouse obstruction under low solar elevation), exhibiting reduced brightness, weaker texture contrast, and blurred boundariesThe dataset includes the following files:StudyArea.tif: Full UAV orthophoto covering the study regionSharedArea.tif: Representative shaded subregionIlluminatedArea.tif: Representative illuminated subregionFile naming follows a spatial partitioning strategy based on illumination conditions to support comparative analysis.This dataset was used to develop and evaluate an automated oyster reef extraction framework based on the Segment Anything Model (SAM) combined with Random Forest classification. The SAM model was applied to extract candidate regions, while the Random Forest model refined segmentation results using spectral and texture features.
Keyword(s):
Coastal ecology; High-resolution Remote Sensing; Other environmental sciences not elsewhere classified; Oyster Reefs; Photogrammetry and remote sensing.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)