Efficient Low-Rank Representation for Hyperspectral Anomaly Detection via Pixel Segmentation

Kun Yu

doi:10.1109/TGRS.2025.3555958

Efficient Low-Rank Representation for Hyperspectral Anomaly Detection via Pixel Segmentation

2025-01-01

0

PRE

AI

DOI：10.1109/TGRS.2025.3555958

Original

Original request for help

Save

Abstract

En 中文

Low-rank representation is a popularly used method in remote sensing and image processing systems. Existing low-rank representation-based algorithms often neglect the varying sensitivities of different pixels to the dictionary, which may lead to inaccurate detection. Also, the dense iterative computations involved in these algorithms could induce high computation overheads. This article proposes an efficient low-rank representation method for hyperspectral anomaly detection (HAD) on a central processing unit (CPU)-field programmable gate array (FPGA) hybrid computing platform. The proposed method starts with segmenting the hyperspectral image into superpixels based on the selected number of dictionary categories. The image is divided into center and edge parts using a sliding window along the segmentation boundaries. Then, we use a low-rank and sparse representation (LRASR) to process center pixels that are well-adapted to the dictionary, and a weighted low-rank and collaborative representation model to process edge pixels that are less adaptive to the dictionary. The aforementioned two representation models are integrated to obtain the final reconstructed image. Moreover, we propose the Nesterov acceleration method by incorporating an adaptive step size into the linearized alternating direction method with adaptive penalty (LADMAP). At the hardware level, the acceleration method is deployed on the CPU-FPGA platform to speed up the proposed HAD flow. Experimental results demonstrate that the proposed method outperforms most existing methods in detection accuracy and achieves significant improvement in computational efficiency.

Keywords:

Hyperspectral imaging

Dictionaries

Anomaly detection

Tensors

Optimization

Sparse matrices

Matrix decomposition

Image segmentation

Image reconstruction

Image edge detection

central processing unit (CPU)-field programmable gate array (FPGA)

hardware acceleration

hyperspectral anomaly detection (HAD)

low-rank representation

Nesterov

Efficient Low-Rank Representation for Hyperspectral Anomaly Detection via Pixel Segmentation

Abstract

Journal

Organization