Foreword to the Special Issue on Hyperspectral Remote Sensing and Imaging Spectroscopy
暂无分享,去创建一个
HYPERSPECTRAL remote sensing has emerged as a powerful tool to understand phenomena at local and global scales by virtue of imaging through a diverse range of platforms, including terrestrial in-situ imaging platforms, unmanned and manned aerial vehicles, and satellite platforms. By virtue of imaging over a wide range of spectral wavelengths, it is possible to characterize object specific properties very accurately. As a result, hyperspectral imaging (also known as imaging spectroscopy) has gained popularity for a wide variety of applications, including environment monitoring, precision agriculture, mineralogy, forestry, urban planning, and defense applications. The increased analysis capability comes at a cost—there are a variety of challenges that must be overcome for robust image analysis of such data, including high dimensionality, limited sample size for training supervised models, noise and atmospheric affects, mixed pixels, etc. This special issue (SI) presents 26 papers that represent some of the recent developments in image analysis algorithms and unique applications of hyperspectral imaging data. Specifically, this SI represents the following broad topics. 1) Contemporary and emerging machine learning architectures for image analysis. 2) Advances in spectral unmixing for image analysis. 3) Real-time compression and compressive sensing. 4) Denoising. 5) Applications leveraging the information provided by hyperspectral earth observations. In Wang et al. a group low-rank nonnegative matrix factorization approach is proposed for spectral unmixing. In Zhang et al. image fusion of multispectral and hyperspectral imagery is undertaken via a spatial-spectral graph-regularized low-rank tensor decomposition. Al-Suwaidi et al. propose feature ensemble based novelty detection for analysis of plant hyperspectral datasets. Matteoli et al. present a target recognition approach within anomalous regions of interest in hyperspectral images. In Du et al. a low-rank matrix factorization based approach is paired with a band-specific noise model for hyperspectral denoising. In Zhang et al. cascaded random forests are proposed for hyperspectral image classification. In Yu et al. a mixed pixel hyperspectral classification approach is developed and presented. In Gan et al. a weighted kernel sparse representation model is developed for hyperspectral classification. Wu et al. present a GPU parallel implementation for hyperspectral image classification that utilizes spatial information. Liu et al. undertake hyperspectral classification via least-square support vector machines. Bascones et al. present an FPGA implementation for real-time hyperspectral lossless compression. Kang et al.