Jorge Sevilla

Unmixing-based content retrieval system for remotely sensed hyperspectral imagery on GPUs

This paper presents a new unmixing-based retrieval system for remotely sensed hyperspectral imagery. The need for this kind of system is justified by the exponential growth in the volume and number of remotely sensed data sets from the surface of the Earth. This is particularly the case for hyperspectral images, which comprise hundreds of spectral bands at different (almost contiguous) wavelength channels. To deal with the high computational cost of extracting the spectral information needed to catalog new hyperspectral images in our system, we resort to efficient implementations of spectral unmixing algorithms on commodity graphics processing units (GPUs). Spectral unmixing is a very popular approach for interpreting hyperspectral data with sub-pixel precision. This paper particularly focuses on the design of the proposed framework as a web service, as well as on the efficient implementation of the system on GPUs. In addition, we present a comparison of spectral unmixing algorithms available in the system on both CPU and GPU architectures.

Grid infrastructures for developing mammography CAD systems

This paper presents a set of technologies developed to exploit Grid infrastructures for breast cancer CAD, that include (1) federated repositories of mammography images and clinical data over Grid storage, (2) a workstation for mammography image analysis and diagnosis and (3) a framework for data analysis and training machine learning classifiers over Grid computing power specially tuned for medical image based data. An experimental mammography digital repository of approximately 300 mammograms from the MIAS database was created and classifiers were built achieving a 0.85 average area under the ROC curve in a dataset of 100 selected mammograms with representative pathological lesions and normal cases. Similar results were achieved with classifiers built for the UCI Breast Cancer Wisconsin dataset (699 features vectors). Now these technologies are being validated in a real medical environment at the Faculty of Medicine in Porto University after a process of integrating the tools within the clinicians workflows and IT systems.

A New Digital Repository for Hyperspectral Imagery With Unmixing-Based Retrieval Functionality Implemented on GPUs

Over the last few years, hyperspectral image data have been collected for a large number of locations over the world, using a variety of instruments for Earth observation. In addition, several new hyperspectral missions will become operational in the near future. Despite the increasing availability and large volume of hyperspectral data in many applications, there is no common repository of hyperspectral data intended to distribute and share free hyperspectral data sets in the community. Quite opposite, the hyperspectral data sets which are available for public use are spread among different storage locations and exhibit significant heterogeneity regarding their format, associated meta-data (if any), or ground-truth information. The development of a standardized hyperspectral data repository is a highly desired goal in the remote sensing community. In this paper, we take a necessary first step toward the development of a completely open digital repository for remotely sensed hyperspectral data. The proposed system (available online for public use at: http://www.hypercomp.es/repository) allows uploading new hyperspectral data sets along with meta-data, ground-truth, analysis results, and pointers to bibliographic references describing the use of the data. The current implementation consists of a front-end which allows management of hyperspectral images through a web interface. The system is implemented on a parallel cluster system in order to guarantee storage availability and fast performance. The system includes a spectral unmixing-guided content-based image retrieval (CBIR) functionality which allows searching for images from the database using queries or available information such as spectral libraries. Specifically, for each new hyperspectral scene which is cataloged in our system, we extract the spectrally pure components (endmembers) and their associated fractional abundances, and then store this information as metadata associated to the hyperspectral image. The meta-data can be used to efficiently retrieve images based on their information content. In order to accelerate the process of obtaining the metadata for a new entry in the system, we develop efficient implementations of spectral unmixing algorithms on graphics processing units (GPUs). This paper particularly focuses on the software design of the system and provides an experimental validation of the unmixing-based retrieval functionality using both synthetic and real hyperspectral images.

New geo-portal for MODIS/SEVIRI image products with geolocation-based retrieval functionality

Abstract. A large number of remote sensing data sets have been collected in recent years by Earth observation instruments such as the moderate resolution imaging spectroradiometer (MODIS) aboard the Terra/Aqua satellite and the spinning enhanced visible and infrared imager (SEVIRI) aboard the geostationary platform Meteosat Second Generation. The advanced remote sensing products resulting from the analysis of these data are useful in a wide variety of applications but require significant resources in terms of storage, retrieval, and analysis. Despite the wide availability of these MODIS/SEVIRI products, the data coming from these instruments are spread among different locations and retrieved from different sources, and there is no common data repository from which the data or the associated products can be retrieved. We take a first step toward the development of a geo-portal for storing and efficiently retrieving MODIS/SEVIRI remote sensing products. The products are obtained using an automatic system that processes the data as soon as they are provided by the collecting antennas, and then the final products are uploaded with a one day delay in the geo-portal. Our focus in this work is on describing the design and efficient implementation of the geo-portal, which allows for a user-friendly and effective access to a full repository of MODIS/SEVIRI advanced products (comprising tens of terabytes of data) using geolocation retrieval capabilities. The geo-portal has been implemented as a web application composed of different layers. Its modular design provides quality of service and scalability (capacity for growth without any quality losing), allowing for the addition of components without the need to modify the entire system. On the client layer, an intuitive web browser interface provides users with remote access to the system. On the server layer, the system provides advanced data management and storage capabilities. On the storage layer, the system provides a secure massive storage service. An experimental evaluation of the geo-portal in terms of efficiency and product retrieval accuracy is also presented and discussed.

Sparse Unmixing-Based Content Retrieval of Hyperspectral Images on Graphics Processing Units

Content-based image retrieval (CBIR) systems have gained significant importance in the remotely sensed hyperspectral imaging community due to the increasing availability of hyperspectral data collected from different instruments. Spectral unmixing has been a popular technique for not only interpreting hyperspectral images but also retrieving them precisely from databases based on information content. This is due to the fact that the information provided by unmixing (i.e., the spectrally pure components of the scene or endmembers, and their corresponding abundance fractions) provides a very intuitive way to describe the content of the scene in both the spectral and the spatial sense. In this letter, we present a new computationally efficient CBIR system for hyperspectral data (available online: http://hypercomp. es/repositorySparse) which uses sparse unmixing concepts to retrieve hyperspectral scenes, based on their content, from large repositories. The search is guided by a spectral library, which is used as a guide to retrieve the data in a robust and efficient way. Given the large size of libraries and the sparsity of the unmixing solutions, the incorporation of sparse unmixing to the CBIR engine brings significant advantages. To optimize its performance in computational terms, the system has been implemented in parallel by taking advantage of the computational power of commodity graphics processing units. The proposed system is validated using a collection of synthetic and real hyperspectral images, exhibiting state-of-the-art performance.

Hyperspectral image reconstruction from random projections on GPU

Hyperspectral data compression and dimensionality reduction has received considerable interest in recent years due to the high spectral resolution of these images. Contrarily to the conventional dimensionality reduction schemes, the spectral compressive acquisition method (SpeCA) performs dimensionality reduction based on random projections. The SpeCA methodology has applications in Hyperspectral Compressive Sensing and also in dimensionality reduction. Due to the extremely large volumes of data collected by imaging spectrometers, high performance computing architectures are needed for data compression of high dimensional hyperspectral data under real-time constrained applications. In this paper a parallel implementation of SpeCA on Graphics Processing Units (GPUs) using the compute unified device architecture (CUDA) is proposed. The proposed implementation is performed in a pixel-by-pixel fashion using coalesced accesses to memory and exploiting shared memory to store temporary data. Furthermore, the kernels have been optimized to minimize the threads divergence, therefore, achieving high GPU occupancy. The experimental results obtained for simulated and real hyperspectral data sets reveal speedups up to 21 times, which demonstrates that the GPU implementation can significantly accelerate the methods execution over big datasets while maintaining the methods accuracy.

Parallel Hyperspectral Unmixing Method via Split Augmented Lagrangian on GPU

One of the main problems of hyperspectral data analysis is the presence of mixed pixels due to the low spatial resolution of such images. Linear spectral unmixing aims at inferring pure spectral signatures and their fractions at each pixel of the scene. The huge data volumes acquired by hyperspectral sensors put stringent requirements on processing and unmixing methods. This letter proposes an efficient implementation of the method called simplex identification via split augmented Lagrangian (SISAL) which exploits the graphics processing unit (GPU) architecture at low level using Compute Unified Device Architecture. SISAL aims to identify the endmembers of a scene, i.e., is able to unmix hyperspectral data sets in which the pure pixel assumption is violated. The proposed implementation is performed in a pixel-by-pixel fashion using coalesced accesses to memory and exploiting shared memory to store temporary data. Furthermore, the kernels have been optimized to minimize the threads divergence, therefore achieving high GPU occupancy. The experimental results obtained for the simulated and real hyperspectral data sets reveal speedups up to 49 times, which demonstrates that the GPU implementation can significantly accelerate the methods execution over big data sets while maintaining the methods accuracy.

A new digital repository for remotely sensed hyperspectral imagery with unmixing-based retrieval functionality

Hyperspectral imaging is concerned with the measurement, analysis, and interpretation of spectra acquired from a given scene (or specific object) at a short, medium or long distance by an airbone or satellite sensor. Over the last few years, hyperspectral image data sets have been collected for a great amount of locations over the world, using a variety of instruments for Earth observation. Despite the increasing importance of hyperspectral images in remote sensing applications, there is no common repository of hyperspectral data intended to distribute and share hyperspectral data sets in the community. Quite opposite, the hyperspectral data sets which are available for public use are spread among different storage locations and present significant heterogeneity regarding the storage format, associated meta-data (if any), or ground-truth availability. As a result, the development of a standardized hyperspectral data repository is a highly desired goal in the remote sensing community. In this paper, we take a necessary first step towards the development of a digital repository for remotely sensed hyperspectral data. The proposed system allows uploading new hyperspectral data sets along with meta-data, ground-truth and analysis results, with the ultimate goal of sharing publicly available hyperspectral images within the remote sensing community. The database has been designed in order to allow storing relevant information for the hyperspectral data available through the system, including basic image characteristics (width, height, number of bands, format) and more advanced meta-data (ground-truth information, publications in which the data has been used). The current implementation consists of a front-end to ease the management of images through a web interface, thus containing both synthetic and real hyperspectral images from two highly representative instruments, such as NASAs Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) over the Cuprite Mining District in Nevada. Most importantly, the developed system includes a spectral unmixing-based content based image retrieval (CBIR) functionality which allows searching for images on the spectral unmixing information (spectrally pure components or endmembers and their associated abundances in the scene). This information is stored as meta-data associated to each hyperspectral image instance, and then used to search and retrieve images based on information content. This paper presents the design of the system and a preliminary validation of the unmixing-based retrieval functionality using both synthetic and real hyperspectral images stored in the database.

Cultural heritage digital libraries on data grids

Data Grids offer redundant and huge distributed storage capabilities, providing an ideal and secure place for the long-term preservation of digitized literary works and documents of artistic and historical relevance. In this demo, we are going to show how we deployed some digital repositories of ancient manuscripts making use of gLibrary, a grid-based system to host and manage digital libraries.

Parallel hyperspectral image reconstruction using random projections

Spaceborne sensors systems are characterized by scarce onboard computing and storage resources and by communication links with reduced bandwidth. Random projections techniques have been demonstrated as an effective and very light way to reduce the number of measurements in hyperspectral data, thus, the data to be transmitted to the Earth station is reduced. However, the reconstruction of the original data from the random projections may be computationally expensive. SpeCA is a blind hyperspectral reconstruction technique that exploits the fact that hyperspectral vectors often belong to a low dimensional subspace. SpeCA has shown promising results in the task of recovering hyperspectral data from a reduced number of random measurements. In this manuscript we focus on the implementation of the SpeCA algorithm for graphics processing units (GPU) using the compute unified device architecture (CUDA). Experimental results conducted using synthetic and real hyperspectral datasets on the GPU architecture by NVIDIA: GeForce GTX 980, reveal that the use of GPUs can provide real-time reconstruction. The achieved speedup is up to 22 times when compared with the processing time of SpeCA running on one core of the Intel i7-4790K CPU (3.4GHz), with 32 Gbyte memory.