Combining Deep Denoiser and Low-rank Priors for Infrared Small Target Detection. (March 2023)

• Record Type: Journal Article
• Authors: Liu, Ting; Yin, Qian; Yang, Jungang; Wang, Yingqian; An, Wei
• Is Part Of: Pattern recognition. Volume 135(2023)
• Publication Date: 2023-03
• Subjects: Low-rank prior -- Deep denoiser prior -- Infrared small target detection -- Plug-and-play; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109184
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We make the first attempt to incorporate the deep denoiser prior for infrared small target detection. Through the plug-and-play framework, the proposed method can better preserve fine image details and remove noise. Considering that different singular values have different importance, we use the weighted sum of weighted tensor nuclear norm for more accurate background estimation. An efficient algorithm is developed for solving the proposed problem based on alternating direction multiplier method. Abstract: Many existing low-rank methods have achieved good detection performance in uniform scenes, but they suffer from a high false alarm rate in complex noisy scenes. Therefore, it is important to improve the detection performance of low-rank models in noisy scenes. In this paper, we first formulate an implicit regularizer by plugging a denoising neural network (termed as deep denoiser), which can learn deep image priors from a large number of natural images. Then, we use the weighted sum of weighted tensor nuclear norm for more accurate background estimation. Finally, alternating direction multiplier method is used to solve the model under the plug-and-play framework. By integrating low-rank prior with deep denoiser prior, our model achieves higher accuracy. Experiments on different scenes demonstrate that our method achieves an improved performance in terms of visual effects and quantitative metrics. Specially, the overall accuracy of AUC value ( AU C OA ) achieved by the proposed method on Sequences 1-6 are 1.24 %, 1.16 %, 0.63 %, 1.9 %, 0.82 %, 2.06 % higher than those achieved by the second top performing methods, respectively.