Dataset Editors: ZHANG Tao

The sea land segmentation V1.1 has released a total of 2113 images. The raw data comes from the publicly available data of Sentinel-1 SAR satellite and is processed using GRD data mode, including orbit correction, thermal noise removal, radiometric calibration, speckle filtering, and terrain correction. The dataset contains images of the southeastern coastal region of China and the coastal regions of various Southeast Asian countries. This dataset adopts manual filtering and annotation processing methods, including raw sea land images and segmentation/coastline edge labels. This dataset has the characteristics of complex scenes and rich categories.

The image and label formats in the dataset are both PNG, and the image size is uniformly 512 × 512.

Reference format for this dataset:

[1] Zhang T, Zhu R,Wei F, Zhang Z,Yu W. The Dataset for Sea-land Segmentation and Coastline Detection Based on GRD Format SAR Images from Sentinel-1 Satellite(sea-land segmentation V1.1）[OL]. Journal of Radars, 2025. https://radars.ac.cn/web/data/getData?dataType=sea-landsegmentation_en&pageType=en.

[2] Zhu R, Zhang T, Li J, et al. A Network for Merging SAR Image Sea-Land Segmentation and Coastline Detection Tasks [J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21: 1-5, Art no. 4017305.

Data release time：2025-05-21