SAR Image Object Detection Dataset    2020 No.1

Guest Editor: Sun Xian


High-resolution SAR ship objection detection dataset-2.0 (AIR-SARShip-2.0) releases 300 images. The resolution of images includes 1m and 3m, imaging mode covers both spotlight and strip, and polarization is single polarization. The scene type includes ports, islands and reefs, and seas of different grades. The target contains thousands ships with more than ten categories such as transport vessels, oil tankers and fishing boats.

In dataset, each image size is about 1000×1000 pixels, with Tiff format, single channel, 16-bit image depth. The corresponding annotation file provides the detail information, including the length and width dimensions, the category and the position of the targets.

For details of the data, you can see the paper "AIR-SARShip-1.0: High Resolution SAR Ship Detection Dataset" and "The instruction of SAR image object detection dataset.pdf".


The current data reference format is as follows:
Xian Sun, Zhirui Wang, Yuanrui Sun, et al. AIR-SARShip-1.0: High Resolution SAR Ship Detection Dataset[J]. Journal of Radars, in press. doi: 10.12000/JR19097

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.