[Formula Omitted]T: Deep Denoising Dictionary Tensor for Hyperspectral Anomaly Detection

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 18; pp. 3713 - 3727
• Main Authors: Shen, Qiangqiang, Liu, Zonglin, Wang, Hanzhang, Xu, Yanhui, Chen, Yongyong, Liang, Yongsheng
• Format: Journal Article
• Language: English
• Published: Piscataway The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 01.01.2025; IEEE
• Subjects: Anomalies; Deep denoising; Dictionaries; Glossaries; hyperspectral anomaly detection (HAD); Hyperspectral imaging; low-rank representation (LRR); low-rank tensor; Noise reduction; Pixels; Representations; Spatial data; Tensors
• DOI: 10.1109/JSTARS.2024.3523133
• ISSN: 1939-1404

Hyperspectral anomaly detection (HAD) approaches with tensor low-rank representation (TLRR) have shown engaging performance, which are capable of capturing abundant spectral and spatial information and, hence, extracting sparse anomalies from the low-rank background without ruining the intrinsic geometric structures of tensor data. However, existing HAD approaches construct the low-rank representation by a handcrafted dictionary that still contains the anomalies, resulting in an inferior representation. To this end, we propose a deep denoising dictionary tensor for hyperspectral anomaly detection ([Formula Omitted]T), which can balance performance and interpretability by fusing two intuitive priors, i.e., low-rankness and deep denoising, into the dictionary tensor and coefficient tensor. In particular, the proposed [Formula Omitted]T first designs a tensor recovery module for dividing the low-rank background and sparse anomalies, where the background is optimized as a denoising dictionary tensor by the joint low-rankness and deep denoising. Following that, we build the TLRR model based on the denoising dictionary tensor to explore the latent representation of the input hyperspectral images, and hence, each background pixel is represented by the other clear background pixels in place of the anomaly pixels. Meanwhile, the coefficient tensor in TLRR is also optimized by the two priors to fully explore the spatial and spectral correlations in the background, and hence, the anomalies can be accurately detected. Numerous experimental results from various real-world datasets validate the effectiveness of our [Formula Omitted]T.