Hyperspectral Anomaly Detection Fused Unified Nonconvex Tensor Ring Factors Regularization
Wenjin Qin, Hailin Wang, Hao Shu, Feng Zhang, Jianjun Wang, Xiangyong Cao, Xi-Le Zhao, Gemine Vivone
TL;DR
The paper tackles hyperspectral anomaly detection by developing HAD-EUNTRFR, a unified nonconvex framework that exploits both global low-rank structure and local smoothness in the background via gradient TR factors. Central to the approach are UNTRFR and its enhanced variant EUNTRFR, which encode the L+S priors directly on the TR factor gradients under a generalized nonconvex penalty, along with a group-sparsity term for anomalies. The model is solved efficiently with an ADMM-based algorithm, with convergence guarantees, and validated on diverse HAD benchmarks where it achieves state-of-the-art or competitive performance, demonstrating robust background suppression and accurate anomaly detection. The work advances tensor-based HAD by unifying prior representations within the TR regime and leveraging nonconvex regularization to better approximate low-rank and sparse structures in the gradient domain, offering significant practical gains for remote sensing analysis.
Abstract
In recent years, tensor decomposition-based approaches for hyperspectral anomaly detection (HAD) have gained significant attention in the field of remote sensing. However, existing methods often fail to fully leverage both the global correlations and local smoothness of the background components in hyperspectral images (HSIs), which exist in both the spectral and spatial domains. This limitation results in suboptimal detection performance. To mitigate this critical issue, we put forward a novel HAD method named HAD-EUNTRFR, which incorporates an enhanced unified nonconvex tensor ring (TR) factors regularization. In the HAD-EUNTRFR framework, the raw HSIs are first decomposed into background and anomaly components. The TR decomposition is then employed to capture the spatial-spectral correlations within the background component. Additionally, we introduce a unified and efficient nonconvex regularizer, induced by tensor singular value decomposition (TSVD), to simultaneously encode the low-rankness and sparsity of the 3-D gradient TR factors into a unique concise form. The above characterization scheme enables the interpretable gradient TR factors to inherit the low-rankness and smoothness of the original background. To further enhance anomaly detection, we design a generalized nonconvex regularization term to exploit the group sparsity of the anomaly component. To solve the resulting doubly nonconvex model, we develop a highly efficient optimization algorithm based on the alternating direction method of multipliers (ADMM) framework. Experimental results on several benchmark datasets demonstrate that our proposed method outperforms existing state-of-the-art (SOTA) approaches in terms of detection accuracy.