Block-Based and Segmentation-Based Approaches for Component Substitution based Hyperspectral Pansharpening

Abstract

Pansharpening is the fusion of panchromatic (PAN) image and multispectral (MS) or hyperspectral (HS) images and provides high spatial and high spectral resolution MS or HS images. Pansharpening mainly extracs the high frequency details from the PAN image, and then injects these details to the MS or HS image. This detail injection procedure can be performed in a variety of ways: using global, block-based or clustering-based techniques. In this paper, block-based and clustering-based approaches are utilized for standart component substitution pansharpening approaches, namely Intensity Hue Saturation (IHS), Brovey Transform (BT), Gram Schmidt (GS) orthagonalization procedure and Principal Component Analysis (PCA) techniques. Both nonoverlapping and overlapping blocks are considered, along with various segmentation approaches such as k-means, Iterative Self Organizing Data Analysis Techniques Algorithm (ISODATA) and Simple Linear Iterative Clustering (SLIC). Two datasets with different characteristics are used in order to evaluate the approaches, and the block-based and segmentation-based approaches are shown to provide enhanced performance.