Non-Convex Tensor Low-Rank Approximation for Infrared Small Target Detection

TL;DR

This paper introduces a novel non-convex tensor low-rank approximation method with adaptive singular value weighting and asymmetric spatial-temporal regularization for improved infrared small target detection, especially in complex scenes.

Contribution

It proposes a non-convex tensor low-rank approximation with adaptive weighting and an asymmetric total variation regularization for more accurate background estimation.

Findings

Outperforms state-of-the-art methods in various metrics.

Demonstrates robustness and low false-alarm rate in complex scenes.

Provides an efficient algorithm for the proposed method.

Abstract

Infrared small target detection is an important fundamental task in the infrared system. Therefore, many infrared small target detection methods have been proposed, in which the low-rank model has been used as a powerful tool. However, most low-rank-based methods assign the same weights for different singular values, which will lead to inaccurate background estimation. Considering that different singular values have different importance and should be treated discriminatively, in this paper, 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. Compared with the traditional total variation approach, ASTTV exploits different smoothness intensities for spatial and temporal regularization. We design an efficient algorithm to find the optimal solution of our method. Compared with some state-of-the-art methods, the proposed method achieves an improvement in terms of various evaluation metrics. Extensive experimental results in various complex scenes demonstrate that our method has strong robustness and low false-alarm rate. Code is available at https://github.com/LiuTing20a/ASTTV-NTLA.