Recent Developments in High Performance Computing for Remote Sensing: A Review

Abstract

Remote sensing data have become very widespread in recent years, and the exploitation of this technology has gone from developments mainly conducted by government intelligence agencies to those carried out by general users and companies. There is a great deal more to remote sensing data than meets the eye, and extracting that information turns out to be a major computational challenge. For this purpose, high performance computing (HPC) infrastructure such as clusters, distributed networks or specialized hardware devices provide important architectural developments to accelerate the computations related with information extraction in remote sensing. In this paper, we review recent advances in HPC applied to remote sensing problems; in particular, the HPC-based paradigms included in this review comprise multiprocessor systems, large-scale and heterogeneous networks of computers, grid and cloud computing environments, and hardware systems such as field programmable gate arrays (FPGAs) and graphics processing units (GPUs). Combined, these parts deliver a snapshot of the state-of-the-art and most recent developments in those areas, and offer a thoughtful perspective of the potential and emerging challenges of applying HPC paradigms to remote sensing problems

pipsCloud: High performance cloud computing for remote sensing big data management and processing

“…Meanwhile, the urgent demands for large-scale remote sensing problems with boosted computation requirements ( [5]) have also fostered the widespread applying of multi-core clusters. The first shot goes to the NEX system ( [5]) for global RS applications built by NASA on a cluster platform with 16 computer in the middle of 1990s. "Pixel Factory" system ( [20]) of InforTerra have employed cluster-based HPC platform for massive RS data autoprocessing, especially Ortho-rectification.…”

“…Some related works go with Plaza et al presented parallel processing algorithms for hyperspectral imageries ( [27]), Zhao et al ([28]) implemented soil moisture estimation in parallel on PC cluster, as well as MPIenabled implementing of image mosaicking ( [29], fusion ( [30]) and band registration ( [31]). Obviously, benefiting from the efforts and developments conducted in HPC platforms, plenty of RS applications have enhanced their computational performance in a significant way ( [5]). …”

“…With virtual organization approach, the Digital Earth Communities could lay their joint effort for addressing global challenges, such as biodiversity, climate change and pollution.The ESA (European Space Agency) G-POD 4 , a project to offer on-demand processing for Earth observation data was initially constructed with GRID. Subsequently, Terraduecloud infrastructure was selected to enhance G-POD for resources provisioning ( [5]). …”

“…The proliferation of "RS Big Data" is revolutionizing the way RS data are processed, analyzed and interpreted as knowledge ( [5]). In large-scale RS applications,regional or even global covered multi-spectral and multi-temporal RS datasets are exploited for processing, so as to meet the arising demands for more accurate and up-to-date information.…”

“…Employing clusterbased HPC (High-Performance Computing) paradigm in RS applications turn out to be the most widespread yet effective approach ( [15] [16] [17][18] [19]). Both NASA's NEX system ( [5] for global processing and InforTerra's "Pixel Factory" ( [20]) for massive imagery auto-processing adopt cluster-based platforms for QoS optimization.…”