Multimodal Fusion of Remote Sensing Images
Abstract
In recent years, there has been greater interest in the field of remote sensing, especially in Hyperspectral sensing technology as the information that resides in the HS spectral domain provides significant advantages over the traditional Panchromatic and Multispectral imageries. The inherent tradeoff between the spectral and spatial resolutions has resulted in the development of newer remote sensing systems that include low resolution HS data coupled with high resolution Panchromatic or Multispectral imaging subsystems. In this paper, a novel method called Coupled Non negative Matrix Factorization (CNMF) unmixing based fusion method is used for the fusion of low-spectral-resolution Multispectral data and a low-spatial-resolution Hyperspectral data inorder to produce a fused image data that will be enhanced in terms of its both spatial and spectral qualities which in turn contributes for the accurate identification and classification of various materials in the observed image scene. This algorithm is very straight forward and easy to implement owing to its simple update rules.
Keywords
Hyperspectral Data, Multispectral Data, Unmixing, Endmember Extraction.