DatasetinthePaper    2023 No.1

Guest Editor: Xiaoling Zhang, Tianwen Zhang, Tianjiao Zeng, Xiaowo Xu

The large-scale SAR ship detection dataset-v1.0 (LS-SSDD-v1.0) was built on the Sentinel-1 satellite, including 30 large-scale SAR images. The large-scale images are collected from 15 original large-scene space-borne SAR images. The polarization modes include VV and VH, the imaging mode is IW and LS-SSDD-v1.0 has the characteristics of large-scale ocean observation, small ship detection, abundant pure backgrounds, fully automatic detection flow and numerous standardized research baselines. Fig. 1 is an example of a large-scale image in LS-SSDD-v1.0.


Fig. 1 Example of a large-scale image in LS-SSDD-v1.0

The large-scale image size of LS-SSDD-v1.0 is unified to 24000 × 16000 pixels, the format is a three-channel, 24-bit, grayscale, .JPG images, and the annotation format is a .XML format file. The annotation file records the target location information, in which the location information is composed of Xmin, Xmax, Ymin and Ymax. For an example of the annotation file, see the “LS-SSDD-v1.0 Usage Instruction”. 

For the dataset usage instructions, you can see “LS-SSDD-v1.0 Usage Instruction”.

Reference format of LS-SSDD-v1.0:

Tianwen Zhang, Xiaoling Zhang, Xiao Ke, Xu Zhan, Jun Shi, Shunjun Wei, Dece Pan, Jianwei Li, Hao Su, Yue Zhou, Durga Kumar. LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images[J]. Remote Sensing, 2020, 12(18): 2997.

Release date: January 30, 2023

Data Usage Protocol of Journal of Radars

The data can be used free of charge for scientific research, teaching and so on, but the data source should be marked in the reference according to the citation format.

Data use for commercial purposes requires permission from the Editorial Department of Journal of Radars.