Multiple scenes Infrared Small Target Dataset A multiple scenes infrared small target dataset (MSISTD) consisting of 1077 images with 1343 instances in more than 15 scenes is constructed as the direct supplement of the training samples. The number of images and the number of instances in MSISTD are 2.4 times and 2.5 times than those of the existing largest ISTD dataset SIRST, respectively. The constructed MSISDT dataset has 1077 images, which includes a total of 1343 instances. It expands the number of images of the original SIRST by 2.4 times and the number of instances by 2.5 times. In addition, it greatly expands the context of single-frame small target detection from being limited to the detection of aerial targets only to the detection of multi-scene, multi-scale, and lower SCR targets. It includes pure sky background, dense cloud sky background, low signal-to-noise ratio sky background, sea-land interface background, woodland sky background, urban sky background, urban building background, forest-to-ground background, inland river scene, and other scenes.

You can get the data from this url. You can get the data from this url https://drive.google.com/file/d/1dYd5w-ElbFYLp0xWAhduY7-pYf1gpaRE/view?usp=sharing

if you find this dataset useful, please cite SIRST and MSISTD and star this repo. I will release the PGDA

@ARTICLE{9954129,
  author={Wang, Ao and Li, Wei and Huang, Zhanchao and Wu, Xin and Jie, Feiran and Tao, Ran},
  journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, 
  title={Prior-Guided Data Augmentation for Infrared Small Target Detection}, 
  year={2022},
  volume={15},
  number={},
  pages={10027-10040},
  doi={10.1109/JSTARS.2022.3222758}}