Samuel Rosario-Torres

Speeding up the MATLAB ™ Hyperspectral Image Analysis Toolbox using GPUs and the Jacket Toolbox

The Hyperspectral Image Analysis Toolbox (HIAT) is a MATLAB™ toolbox for the analysis of hyperspectral imagery. HIAT includes a collection of algorithms for processing of hyperspectral and multispectral imagery under the MATLAB environment. The objective of HIAT is to provide a suite of information extraction algorithms to users of hyperspectral and multispectral imagery across different application domains. HIAT has been developed as part of the NSF Bernard M. Gordon Center for Subsurface Sensing and Imaging Solutionware that seeks to develop a repository of reliable and reusable software tools that can be shared by researchers across research domains. HIAT includes feature extraction and selection, supervised and unsupervised classification algorithms, unmixing, and visualization algorithms developed at the UPRM Laboratory for Applied Remote Sensing and Image Processing. A key limitation of the MATLAB environment is its difficulty in managing large images. Here we investigate the use of the recently released MATLAB Jacket Toolbox that allows implementation of MATLAB programs in GPUs. This paper presents a comparison of the CPU implementation with the GPU implementation of different routines of HIAT.

An algorithm for fully constrained abundance estimation in hyperspectral unmixing

This paper presents an algorithm for abundance estimation in hyperspectral imagery. The fully constrained abundance estimation problem where the positivity and the sum to less than or equal to one (or sum equal to one) constraints are enforced is solved by reformulating the problem as a least distance (LSD) least squares (LS) problem. The advantage of reformulating the problem as a least distance problem is that the resulting LSD problem can be solved using a duality theory using a nonnegative LS problem (NNLS). The NNLS problem can then be solved using Hanson and Lawson algorithm or one of several multiplicative iterative algorithms presented in the literature. The paper presents the derivation of the algorithm and a comparison to other approaches described in the literature. Application to HYPERION image taken over La Parguera, Puerto Rico is presented.

Abundance estimation algorithms using NVIDIA CUDA technology

Spectral unmixing of hyperspectral images is a process by which the constituents members of a pixel scene are determined and the fraction of the abundance of the elements is estimated. Several algorithms have been developed in the past in order to obtain abundance estimation from hyperspectral data, however, most of them are characterized by being highly computational and time consuming due to the magnitude of the data involved. In this research we present the use of Graphic Processing Units (GPUs) as a computing platform in order to reduce computation time related to abundance estimation for hyperspectral images. Our implementation was developed in C using NVIDIA(R) Compute Unified Device Architecture (CUDATM). The recently introduced CUDA platform allows developers to directly use a GPUs processing power to perform arbitrary mathematical computations. We describe our implementation of the Image Space Reconstruction Algorithm (ISRA) and Expectation Maximization Maximum Likelihood (EMML) algorithm for abundance estimation and present a performance comparison against implementations using C and Matlab. Results show that the CUDA technology produced results around 10 times better than the fastest implementation done on previous platforms.

An algorithm for unsupervised unmixing of hyperspectral imagery using positive matrix factorization

This paper presents an approach for simultaneous determination of endmembers and their abundances in hyperspectral imagery using a constrained positive matrix factorization. The algorithm presented here solves the constrained PMF by formulating it as a nonnegative least squares problem where the cost function is expanded with a penalty term to enforce the sum to one constraint. Preliminary results using simulated and AVIRIS-Cuprite data are presented. These results show the potential of the method to solve the unsupervised unmixing problem.

A comparison of unmixing algorithms for hyperspectral imagery

In this paper, we present an experimental comparison of unmixing using the constrained positive matrix factorization (cPMF) with SMACC and MaxD unmixing algorithms that retrieve endmembers from the image pixels. The comparison was made using hyperspectral images collected over Vieques Island in Puerto Rico using the AISA sensor. Based on field work, six information classes were identified in the area of interest and the algorithms are evaluated in their capability to retrieve information about the classes of interest. The cPMF was the only approach capable of identifying all six informational classes with one or more spectral classes assigned to them. SMACC and MaxD were unable to extract one of the classes. The abundance maps from cPMF describe the spatial distribution of the information classes.

New developments and application of the UPRM MATLAB hyperspectral image analysis toolbox

The Hyperspectral Image Analysis Toolbox (HIAT) is a collection of algorithms that extend the capability of the MATLAB numerical computing environment for the processing of hyperspectral and multispectral imagery. The purpose the Toolbox is to provide a suite of information extraction algorithms to users of hyperspectral and multispectral imagery. HIAT has been developed as part of the NSF Center for Subsurface Sensing and Imaging (CenSSIS) Solutionware that seeks to develop a repository of reliable and reusable software tools that can be shared by researchers across research domains. HIAT provides easy access to feature extraction/selection, supervised and unsupervised classification algorithms, unmixing and visualization developed at Laboratory of Remote Sensing and Image Processing (LARSIP). This paper presents an overview of the tools, application available in HIAT using as example an AVIRIS image. In addition, we present the new HIAT developments, unmixing, new oversampling algorithm, true color visualization, crop tool and GUI enhancement.

Evaluation of the graphics processing unit architecture for the implementation of target detection algorithms for hyperspectral imagery

Recent advances in hyperspectral imaging sensors allow the acquisition of images of a scene at hundreds of contiguous narrow spectral bands. Target detection algorithms try to exploit this high-resolution spectral information to detect target materials present in a scene, but this process may be computationally intensive due to the large data volumes generated by the hyperspectral sensors, typically hundreds of megabytes. Previous works have shown that hyperspectral data processing can significantly benefit from the parallel computing resources of graphics processing units (GPUs), due to their highly parallel structure and the high computational capabilities that can be achieved at relative low costs. We studied the parallel implementation of three target detection algorithms (RX algorithm, matched filter, and adaptive matched subspace detector) for hyperspectral images in order to identify the aspects in the structure of these algorithms that can exploit the CUDA™ architecture of NVIDIA® GPUs. A data set was generated using a SOC-700 hyperspectral imager to evaluate the performance and detection accuracy of the parallel implementations on a NVIDIA® Tesla™ C1060 graphics card, achieving real-time performance in the GPU implementations based on global statistics.

Evaluation of the GPU architecture for the implementation of target detection algorithms for hyperspectral imagery

Hyperspectral sensors can collect hundreds of images taken at different narrow and contiguously spaced spectral bands. This high-resolution spectral information can be used to identify materials and objects within the field of view of the sensor by their spectral signature, but this process may be computationally intensive due to the large data sizes generated by the hyperspectral sensors, typically hundreds of megabytes. This can be an important limitation for some applications where the detection process must be performed in real time (surveillance, explosive detection, etc.). In this work, we developed a parallel implementation of three state-ofthe- art target detection algorithms (RX algorithm, matched filter and adaptive matched subspace detector) using a graphics processing unit (GPU) based on the NVIDIA® CUDA™ architecture. In addition, a multi-core CPUbased implementation of each algorithm was developed to be used as a baseline for the speedups estimation. We evaluated the performance of the GPU-based implementations using an NVIDIA ® Tesla® C1060 GPU card, and the detection accuracy of the implemented algorithms was evaluated using a set of phantom images simulating traces of different materials on clothing. We achieved a maximum speedup in the GPU implementations of around 20x over a multicore CPU-based implementation, which suggests that applications for real-time detection of targets in HSI can greatly benefit from the performance of GPUs as processing hardware.

An update on SeaBED: A TesBED for validating subsurface aquatic hyperspectral remote sensing algorithms

SeaBED is an integrated data set and testing infrastructure for researchers to validate subsurface aquatic remote sensing algorithms. The purpose behind developing SeaBED is to collect multiple levels of image, field, and laboratory data with which to validate physical models, inversion algorithms, feature extraction tools and classification methods for subsurface aquatic sensing using hyperspectral imaging. The focus of this testbed facility is a field site located on Enrique Reef in southwestern Puerto Rico. This field site, which includes a heterogeneous mixture of both coral reef and seagrass habitats, offers a well defined system for evaluating analysis techniques under natural environmental conditions. Data produced from the field site currently includes airborne, satellite, and field-level hyperspectral and multispectral images, in situ spectral signatures, and water bio-optical properties. This data provides a valuable combination of sensing imagery and fully characterized ground truth information for developing and validating remote sensing algorithms. A major accomplishment for SeaBED was the collection of high-resolution hyperspectral imagery and associated ground truth of the near shore reefs and coastal ecosystems in southwestern Puerto Rico in 2007. The mission included 1740 km2 of imagery acquired at 4 m spatial resolution, with 110 km2 enhanced coverage of four science areas at 1, 2, 4 and 8 m spatial resolutions to facilitate investigation of spatial scaling issues and the testing of subsurface unmixing algorithms. We present an overview of SeaBED and also describe particulars of the 2007 data collection campaign, including both image acquisition and field data collection efforts.

An update on the MATLAB hyperspectral image analysis toolbox

The Hyperspectral Image Analysis Toolbox (HIAT) is a collection of algorithms that extend the capability of the MATLAB numerical computing environment for the processing of hyperspectral and multispectral imagery. The purpose of the HIAT Toolbox is to provide information extraction algorithms to users of hyperspectral and multispectral imagery in environmental and biomedical applications. HIAT has been developed as part of the NSF Center for Subsurface Sensing and Imaging (CenSSIS) Solutionware that seeks to develop a repository of reliable and reusable software tools that can be shared by researchers across research domains. HIAT provides easy access to supervised and unsupervised classification algorithms developed at LARSIP over the last 8 years.