David Valencia

Commodity cluster-based parallel processing of hyperspectral imagery

The rapid development of space and computer technologies has made possible to store a large amount of remotely sensed image data, collected from heterogeneous sources. In particular, NASA is continuously gathering imagery data with hyperspectral Earth observing sensors such as the Airborne Visible-Infrared Imaging Spectrometer (AVIRIS) or the Hyperion imager aboard Earth Observing-1 (EO-1) spacecraft. The development of fast techniques for transforming the massive amount of collected data into scientific understanding is critical for space-based Earth science and planetary exploration. This paper describes commodity cluster-based parallel data analysis strategies for hyperspectral imagery, a new class of image data that comprises hundreds of spectral bands at different wavelength channels for the same area on the surface of the Earth. An unsupervised technique that integrates the spatial and spectral information in the image data using multi-channel morphological transformations is parallelized and compared to other available parallel algorithms. The codes portability, reusability and scalability are illustrated by using two high-performance parallel computing architectures: a distributed memory, multiple instruction multiple data (MIMD)-style multicomputer at European Center for Parallelism of Barcelona, and a Beowulf cluster at NASAs Goddard Space Flight Center. Experimental results suggest that Beowulf clusters are a source of computational power that is both accessible and applicable to obtaining results in valid response times in information extraction applications from hyperspectral imagery.

Parallel implementation of endmember extraction algorithms from hyperspectral data

Automated extraction of spectral endmembers is a crucial task in hyperspectral data analysis. In most cases, the computational complexity of endmember extraction algorithms is very high, in particular, for very high-dimensional datasets. However, the intrinsic properties of available techniques are amenable to the design of parallel implementations. In this letter, we evaluate several parallel algorithms that represent three representative approaches to the problem of extracting endmembers. Two parallel algorithms have been selected to represent a first class of algorithms based on convex geometry concepts. In particular, we develop parallel implementations of approximate versions of the N-FINDR and pixel purity index algorithms, along with a parallel hybrid of both techniques. A second class is given by algorithms based on constrained error minimization and represented by a parallel version of the iterative error analysis algorithm. Finally, a parallel version of the automated morphological endmember extraction algorithm is also presented and discussed. This algorithm integrates the spatial and spectral information as opposed to the other discussed algorithms, a feature that introduces additional considerations for its parallelization. The proposed algorithms are quantitatively compared and assessed in terms of both endmember extraction accuracy and parallel efficiency, using standard AVIRIS hyperspectral datasets. Performance data are measured on Thunderhead, a parallel supercomputer at NASAs Goddard Space Flight Center

FPGA implementation of the pixel purity index algorithm for remotely sensed hyperspectral image analysis

Hyperspectral imaging is a new emerging technology in remote sensing which generates hundreds of images, at different wavelength channels, for the same area on the surface of the Earth. Over the last years, many algorithms have been developed with the purpose of finding endmembers, assumed to be pure spectral signatures in remotely sensed hyperspectral data sets. One of the most popular techniques has been the pixel purity index (PPI). This algorithm is very time-consuming. The reconfigurability, compact size, and high computational power of Field programmable gate arrays (FPGAs) make them particularly attractive for exploitation in remote sensing applications with (near) real-time requirements. In this paper, we present an FPGA design for implementation of the PPI algorithm. Our systolic array design includes a DMA and implements a prefetching technique to reduce the penalties due to the I/O communications. We have also included a hardware module for random number generation. The proposed method has been tested using real hyperspectral data collected by NASAs Airborne Visible Infrared Imaging Spectrometer over the Cuprite mining district in Nevada. Experimental results reveal that the proposed hardware system is easily scalable and able to provide accurate results with compact size in (near) real-time, which make our reconfigurable system appealing for on-board hyperspectral data processing.

Impact of platform heterogeneity on the design of parallel algorithms for morphological processing of high-dimensional image data

Abstract The main objective of this paper is to describe a realistic framework to understand parallel performance of high-dimensional image processing algorithms in the context of heterogeneous networks of workstations (NOWs). As a case study, this paper explores techniques for mapping hyperspectral image analysis techniques onto fully heterogeneous NOWs. Hyperspectral imaging is a new technique in remote sensing that has gained tremendous popularity in many research areas, including satellite imaging and aerial reconnaissance. The automation of techniques able to transform massive amounts of hyperspectral data into scientific understanding in valid response times is critical for space-based Earth science and planetary exploration. Using an evaluation strategy which is based on comparing the efficiency achieved by an heterogeneous algorithm on a fully heterogeneous NOW with that evidenced by its homogeneous version on a homogeneous NOW with the same aggregate performance as the heterogeneous one, we develop a detailed analysis of parallel algorithms that integrate the spatial and spectral information in the image data through mathematical morphology concepts. For comparative purposes, performance data for the tested algorithms on Thunderhead (a large-scale Beowulf cluster at NASA’s Goddard Space Flight Center) are also provided. Our detailed investigation of the parallel properties of the proposed morphological algorithms provides several intriguing findings that may help image analysts in selection of parallel techniques and strategies for specific applications.

An experimental comparison of parallel algorithms for hyperspectral analysis using heterogeneous and homogeneous networks of workstations

Imaging spectroscopy, also known as hyperspectral imaging, is a new technique that has gained tremendous popularity in many research areas, including satellite imaging and aerial reconnaissance. In particular, NASA is continuously gathering high-dimensional image data from the surface of the earth with hyperspectral sensors such as the Jet Propulsion Laboratorys Airborne Visible-Infrared Imaging Spectrometer (AVIRIS) or the Hyperion hyperspectral imager aboard NASAs Earth Observing-1 (EO-1) spacecraft. Despite the massive volume of scientific data commonly involved in hyperspectral imaging applications, very few parallel strategies for hyperspectral analysis are currently available, and most of them have been designed in the context of homogeneous computing platforms. However, heterogeneous networks of workstations represent a very promising cost-effective solution that is expected to play a major role in the design of high-performance computing platforms for many on-going and planned remote sensing missions. Our main goal in this paper is to understand parallel performance of hyperspectral imaging algorithms comprising the standard hyperspectral data processing chain (which includes pre-processing, selection of pure spectral components and linear spectral unmixing) in the context of fully heterogeneous computing platforms. For that purpose, we develop an exhaustive quantitative and comparative analysis of several available and new parallel hyperspectral imaging algorithms by comparing their efficiency on both a fully heterogeneous network of workstations and a massively parallel homogeneous cluster at NASAs Goddard Space Flight Center in Maryland.

Parallel Processing of Remotely Sensed Hyperspectral Images On Heterogeneous Networks of Workstations Using HeteroMPI

The development of efficient techniques for transforming massive volumes of remotely sensed hyperspectral data into scientific understanding is critical for space-based Earth science and planetary exploration. Although most available parallel processing strategies for information extraction and mining from hyperspectral imagery assume homogeneity in the underlying computing platform, heterogeneous networks of computers (HNOCs) have become a promising cost-effective solution, expected to play a major role in many on-going and planned remote sensing missions. In this paper, we develop a new morphological parallel algorithm for hyperspectral image classification using HeteroMPI, an extension of MPI for programming high-performance computations on HNOCs. The main idea of HeteroMPI is to automate and optimize the selection of a group of processes that executes a heterogeneous algorithm faster than any other possible group in a heterogeneous environment. In order to analyze the impact of many-to-one (gather) communication operations introduced by our proposed algorithm, we resort to a recently proposed collective communication model. The parallel algorithm is validated using two heterogeneous clusters at University College Dublin and a massively parallel Beowulf cluster at NASAs Goddard Space Flight Center.

FPGA-Based hyperspectral data compression using spectral unmixing and the pixel purity index algorithm

Hyperspectral data compression is expected to play a crucial role in remote sensing applications. Most available approaches have largely overlooked the impact of mixed pixels and subpixel targets, which can be accurately modeled and uncovered by resorting to the wealth of spectral information provided by hyperspectral image data. In this paper, we develop an FPGA-based data compression technique based on the concept of spectral unmixing. It has been implemented on a Xilinx Virtex-II FPGA formed by several millions of gates, and with high computational power and compact size, which make this reconfigurable device very appealing for onboard, real-time data processing.

Parallel morphological/neural processing of hyperspectral images using heterogeneous and homogeneous platforms

Abstract The wealth spatial and spectral information available from last-generation Earth observation instruments has introduced extremely high computational requirements in many applications. Most currently available parallel techniques treat remotely sensed data not as images, but as unordered listings of spectral measurements with no spatial arrangement. In thematic classification applications, however, the integration of spatial and spectral information can be greatly beneficial. Although such integrated approaches can be efficiently mapped in homogeneous commodity clusters, low-cost heterogeneous networks of computers (HNOCs) have soon become a standard tool of choice for dealing with the massive amount of image data produced by Earth observation missions. In this paper, we develop a new morphological/neural algorithm for parallel classification of high-dimensional (hyperspectral) remotely sensed image data sets. The algorithm’s accuracy and parallel performance is tested in a variety of homogeneous and heterogeneous computing platforms, using two networks of workstations distributed among different locations, and also a massively parallel Beowulf cluster at NASA’s Goddard Space Flight Center in Maryland.

Parallel hyperspectral image processing on commodity graphics hardware

Many recent research efforts have been devoted to the use of commodity hardware for solving computationally-intensive scientific problems. Among such problems, hyperspectral imaging has created new processing challenges in the remote sensing community. Hyperspectral sensors are now capable of collecting hundreds of images, corresponding to different wavelength channels, for the same area on the surface of the Earth. For instance, NASA is continuously gathering high-dimensional image data with hyperspectral sensors such as Jet Propulsion Laboratorys airborne visible-infrared imaging spectrometer (AVIRIS). The increasing programmability and parallelism of commodity graphics processing units (GPUs) makes them strong candidates for addressing some of these challenges. In this paper, we describe a GPU-based framework for implementation of hyperspectral image processing algorithms which takes advantage of multiple levels of parallelism found in modern GPUs. This framework is inexpensive, uses readily available PC graphics hardware boards, and provides the desired performance at the quality required. Experimental results are presented and discussed in the context of a realistic application, based on hyperspectral data collected by NASAs AVIRIS system

AMEEPAR: parallel morphological algorithm for hyperspectral image classification on heterogeneous networks of workstations

Hyperspectral imaging is a new technique in remote sensing that generates hundreds of images corresponding to different wavelength channels for the same area on the surface of the Earth. Most available techniques for hyperspectral image classification focus on analyzing the data without incorporating the spatial information; i.e. the data is treated not as an image but as an unordered listing of spectral measurements where the spatial coordinates can be shuffled arbitrarily without affecting the final analysis. Despite the growing interest in the development of techniques for interpretation and classification of such high-dimensional imagery, only a few efforts devoted to the design of parallel implementations exist in the open literature. In this paper, we describe AMEEPAR, a parallel morphological algorithm that integrates the spatial and spectral information. The algorithm has been specifically optimized in this work for execution on heterogeneous networks of workstations. The parallel properties and classification accuracy of the proposed approach are evaluated using four networks of workstations distributed among different locations, and a massively parallel Beowulf cluster at NASA’s Goddard Space Flight Center.