Optimization of a Hyperspectral Image Processing Chain Using Heterogeneous and GPU-Based Parallel Computing Architectures

Hyperspectral imaging is a new technique in remote sensing that generates hundreds of images, at different wavelength channels, for the same area on the surface of the Earth. In recent years, several efforts have been directed towards the incorporation of high-performance computing systems and architectures into remote sensing missions. With the aim of providing an overview of current and new trends in the design of parallel and distributed systems for remote sensing applications, this paper presents two solutions for efficient implementation of a hyperspectral image processing chain based on mixed pixel analysis. The first solution is intended for efficient exploitation of hyperspectral data after being transmitted to Earth, and is tested on a heterogeneous network of workstations at University of Maryland. The second solution is intended for on-board, real-time exploitation of hyperspectral data, and is tested on an NVidia graphics processing unit (GPU). Combined, the two discussed approaches integrate a system with different levels of priority in processing of the hyperspectral data, which can be tuned depending on the specific requirements of the application scenario. The proposed implementations are evaluated using hyperspectral data collected by the Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) operated by NASA/JPL.