ASTTV-NTLA

Matlab implementation of "Nonconvex Tensor Low-Rank Approximation for Infrared Small Target Detection", [pdf].

Highlights:

1. *we propose a non-convex tensor low-rank approximation (NTLA) method for infrared small target detection. In our method, NTLA regularization adaptively assigns different weights to different singular values for accurate background estimation. Based on the proposed NTLA, we propose asymmetric spatial-temporal total variation (ASTTV) regularization to achieve more accurate background estimation in complex scenes.

2. To demonstrate the advantages of the ASTTV-NTLA method, we compare it with other ten methods on six different real infrared image scenes.

3. Ablation experiments of each regularization of ASTTV-NTLA method.

## Get Started Run Demo_ASTTV_NTLA.

Details

For details such as parameter setting, please refer to [pdf].

Citation

@article{liu2021nonconvex,
  title={Nonconvex Tensor Low-Rank Approximation for Infrared Small Target Detection},
  author={Liu, Ting and Yang, Jungang and Li, Boyang and Xiao, Chao and Sun, Yang and Wang, Yingqian and An, Wei},
  journal={IEEE Transactions on Geoscience and Remote Sensing},
  volume={60},
  pages={1--18},
  year={2021},
  publisher={IEEE}
}

Contact

Any question regarding this work can be addressed to liuting@nudt.edu.cn.