Hyperspectral Image Segmentation based on Graph Processing over Multilayer Networks
This work addresses hyperspectral image segmentation for applications in environmental science and geo/space exploration, presenting an incremental advancement using existing methods on new data.
The paper tackled hyperspectral image segmentation by proposing graph processing methods over multilayer networks to extract spectral-spatial features, resulting in experimental demonstrations of the approach's strength in HSI processing.
Hyperspectral imaging is an important sensing technology with broad applications and impact in areas including environmental science, weather, and geo/space exploration. One important task of hyperspectral image (HSI) processing is the extraction of spectral-spatial features. Leveraging on the recent-developed graph signal processing over multilayer networks (M-GSP), this work proposes several approaches to HSI segmentation based on M-GSP feature extraction. To capture joint spectral-spatial information, we first customize a tensor-based multilayer network (MLN) model for HSI, and define a MLN singular space for feature extraction. We then develop an unsupervised HSI segmentation method by utilizing MLN spectral clustering. Regrouping HSI pixels via MLN-based clustering, we further propose a semi-supervised HSI classification based on multi-resolution fusions of superpixels. Our experimental results demonstrate the strength of M-GSP in HSI processing and spectral-spatial information extraction.