SEARCH · Engineering Papers

Results for “Image databases”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Power System Waveform Datasets for Machine Learning

The desire for increased visibility across the electricity grid will necessarily increase the deployment of sensing and measurement devices and associated data management needs to unprecedented levels. For the existing sensing and measurement infrastructure, there remains a great amount of “value” yet to be extracted through advanced data management and analytics. Availability of more data will not, by itself, lead to changes in grid visibility, security, and resiliency. To create the predictive and prescriptive environment required to enable new markets and transactions for customer revenue and a reliable grid, the data must be collected, organized, evaluated, and analyzed using sophisticated algorithms to provide actionable information allowing operators and customers to reliably manage an increasingly complex grid. Progress in artificial intelligence (AI) has been largely driven by large, publicly available datasets that can be used to train AI algorithms such as MNIST, a database of handwritten images of digits, and ImageNet, an image database of everyday objects. These types of publicly available databases of real-world training datasets have been largely credited for advancement of image processing, computer vision, and deep learning algorithms that these use cases deploy. However, in the power systems industry to date, there are few databases with proper event labeling, and data access to a publicly available collection of power system event waveforms that will allow users to interact with grid signature data. Publicly available datasets of power system event waveforms, such as the DOE/EPRI dataset, often lack critical metadata or contain limited examples of each event type, and data formats vary widely across these datasets.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

NASA NTRS1995

Trainable Cataloging for Digital Image Libraries with Applications to Volcano Detection

Users of digital image libraries are often not interested in image data per se but in derived products such as catalogs of objects of interest. Converting an image database into a usable catalog is typically carried out manually at present. For many larger image databases the purely manual approach is completely impractical. In this paper we describe the development of a trainable cataloging system: the user indicates the location of the objects of interest for a number of training images and the system learns to detect and catalog these objects in the rest of the database. In particular we describe the application of this system to the cataloging of small volcanoes in radar images of Venus. The volcano problem is of interest because of the scale (30,000 images, order of 1 million detectable volcanoes), technical difficulty (the variability of the volcanoes in appearance) and the scientific importance of the problem. The problem of uncertain or subjective ground truth is of fundamental importance in cataloging problems of this nature and is discussed in some detail. Experimental results are presented which quantify and compare the detection performance of the system relative to human detection performance. The paper concludes by discussing the limitations of the proposed system and the lessons learned of general relevance to the development of digital image libraries.

digital image libraries, trainable cataloging↗

NASA NTRS2004

Extending the ICRF to Higher Radio Frequencies: 24 and 43 GHz Astrometry

We present imaging results and source structure analysis of extragalactic radio sources observed using the Very Long Baseline Array (VLBA) at 24 GHz and 43 GHz as part of an ongoing NASA, USNO, NRAO and Bordeaux Observatory collaboration to extend the International Celestial Reference Frame (ICRF) to higher radio frequencies. The K/Q-band image database now includes images of 108 sources at 43 GHz (Q-band) and images of 230 sources at 24 GHz (K-band). Preliminary analysis of the observations taken to date shows that the sources are generally more compact as one goes from the ICRF frequency of 8.4 GHz to 24 GHz. This result is consistent with the standard theory of compact extragalactic radio sources and suggests that reference frames defined at these higher radio frequencies will be less susceptible to the effects of intrinsic source structure than those defined at lower frequencies.

Jacobs, Christopher S.↗

NASA NTRS2004

Extending the ICRF to Higher Radio Frequencies: Imaging and Source Structure

We present imaging results and source structure analysis of extragalactic radio sources observed using the Very Long Baseline Array (VLBA) at 24 GHz and 43 GHz as part of an ongoing NASA, USNO, NRAO and Bordeaux Observatory collaboration to extend the International Celestial Reference Frame (ICRF) to higher radio frequencies. The K/Q-band image database now includes images of 108 sources at 43 GHz (Q-braid) and images of 230 sources at 24 GHz (K-band). Preliminary analysis of the observations taken to date shows that the sources are generally more compact as one goes from the ICRF frequency of 8.4 GHz to 24 GHz. This result is consistent with the standard theory of compact extragalactic radio sources and suggests that reference frames defined at these higher radio frequencies will be less susceptible to the effects of intrinsic source structure than those defined at lower frequencies.

Boboltz, David A.↗

NASA NTRS2011

Stereoscopic wide field of view imaging system

A stereoscopic imaging system incorporates a plurality of imaging devices or cameras to generate a high resolution, wide field of view image database from which images can be combined in real time to provide wide field of view or panoramic or omni-directional still or video images.

Prechtl, Eric F.↗

NASA NTRS2011

Stereoscopic wide field of view imaging system

Prechtl, Eric F.↗

DOE OSTI2021

Multiresolution classification of turbulence features in image data through machine learning

During large-scale simulations, intermediate data products such as image databases have become popular due to their low relative storage cost and fast in-situ analysis. Serving as a form of data reduction, these image databases have become more acceptable to perform data analysis on. In this work, we present an image-space detection and classification system for extracting vortices at multiple scales through wavelet-based filtering. A custom image-space descriptor is used to encode a large variety of vortex-types and a machine learning system is trained for fast classification of vortex regions. By combining a radial-based histogram descriptor, a bag of visual words feature descriptor, and a support vector machine, our results show that we are able to detect and classify vortex features at various sizes at multiple scales. Once trained, our framework enables the fast extraction of vortices on new, unknown image datasets for flow analysis.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2004

Response of Sea Ice and Marine Ecosystems to the Observed Warming Trends in the Arctic

Our third (final) year activities have focused on two elements: 1) Creating and evaluating panarctic weekly climatologies of ocean color products for 1998 through 2002, 2) Interacting to assess image databases, submit and revise publications. Comiso and his programmer have principal responsibility for assembling and archiving the monthly and weekly image database at GSFC. There are now five year's (1998-2002) of climatologies. In addition to email correspondence, the PIs have met to prepare a series of publications ranging from panarctic physical-biological interactions to more focused regional studies.

Cota, Glenn F.↗

NASA NTRS1995

Machine learning for a Toolkit for Image Mining

A prototype user environment is described that enables a user with very limited computer skills to collaborate with a computer algorithm to develop search tools (agents) that can be used for image analysis, creating metadata for tagging images, searching for images in an image database on the basis of image content, or as a component of computer vision algorithms. Agents are learned in an ongoing, two-way dialogue between the user and the algorithm. The user points to mistakes made in classification. The algorithm, in response, attempts to discover which image attributes are discriminating between objects of interest and clutter. It then builds a candidate agent and applies it to an input image, producing an 'interest' image highlighting features that are consistent with the set of objects and clutter indicated by the user. The dialogue repeats until the user is satisfied. The prototype environment, called the Toolkit for Image Mining (TIM) is currently capable of learning spectral and textural patterns. Learning exhibits rapid convergence to reasonable levels of performance and, when thoroughly trained, Fo appears to be competitive in discrimination accuracy with other classification techniques.

Delanoy, Richard L.↗

NASA NTRS1988

Cartographic feature extraction with integrated SIR-B and Landsat TM images

A digital cartographic multisensor image database of excellent geometry and improved resolution was created by registering SIR-B images to a rectified Landsat TM reference image and applying intensity-hue-saturation enhancement techniques. When evaluated against geodetic control, RMSE(XY) values of approximately + or - 20 m were noted for the composite SIR-B/TM images. The completeness of cartographic features extracted from the composite images exceeded those obtained from separate SIR-B and TM image data sets by approximately 10 and 25 percent, respectively, indicating that the composite images may prove suitable for planimetric mapping at a scale of 1:100,000 or smaller. At present, the most effective method for extracting cartographic information involves digitizing features directly from the image processing display screen.

Welch, R.↗

DOE OSTI2022

Statistical characterization of experimental magnetized liner inertial fusion stagnation images using deep-learning-based fuel–background segmentation

Significant variety is observed in spherical crystal x-ray imager (SCXI) data for the stagnated fuel–liner system created in Magnetized Liner Inertial Fusion (MagLIF) experiments conducted at the Sandia National Laboratories Z-facility. As a result, image analysis tasks involving, e.g., region-of-interest selection (i.e. segmentation), background subtraction and image registration have generally required tedious manual treatment leading to increased risk of irreproducibility, lack of uncertainty quantification and smaller-scale studies using only a fraction of available data. We present a convolutional neural network (CNN)-based pipeline to automate much of the image processing workflow. This tool enabled batch preprocessing of an ensemble of N scans = 139 SCXI images across N exp = 67 different experiments for subsequent study. The pipeline begins by segmenting images into the stagnated fuel and background using a CNN trained on synthetic images generated from a geometric model of a physical three-dimensional plasma. The resulting segmentation allows for a rules-based registration. Our approach flexibly handles rarely occurring artifacts through minimal user input and avoids the need for extensive hand labelling and augmentation of our experimental dataset that would be needed to train an end-to-end pipeline. Here we also fit background pixels using low-degree polynomials, and perform a statistical assessment of the background and noise properties over the entire image database. Our results provide a guide for choices made in statistical inference models using stagnation image data and can be applied in the generation of synthetic datasets with realistic choices of noise statistics and background models used for machine learning tasks in MagLIF data analysis. We anticipate that the method may be readily extended to automate other MagLIF stagnation imaging applications.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2023

Deep Deception: Exemplars of Adversarial Machine Learning and Countermeasures Applicable to International Safeguards

As a follow-up to our more comprehensive report on Adversarial Machine Learning (AML), here we provide demonstrations of AML attacks against the Limbo image database of UF6 cylinders in a variety of orientations and amongst a variety of distractor images. We demonstrate the Carlini & Wagner AML attack against a subset of Limbo images, with 100% attack success rate; meaning all attacked images were misclassified by a highly accurate trained model, yet the image changes were imperceptible to the human eye. We also demonstrate successful attacks against segmented images (images with more than one targeted object). Finally, we demonstrated the Fast Fourier Transform countermeasure that can be used to detect AML attacks on images. The intent of this and our previous report is to inform the IAEA and stakeholders of both the promise of machine learning, which could greatly improve the efficiency of surveillance monitoring, but also of the real threat of AML and potential defenses.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1995

Studying the Sky/Planets Can Drown You in Images: Machine Learning Solutions at JPL/Caltech

JPL is working to develop a domain-independent system capable of small-scale object recognition in large image databases for science analysis. Two applications discussed are the cataloging of three billion sky objects in the Sky Image Cataloging and Analysis Tool (SKICAT) and the detection of possibly one million small volcanoes visible in the Magellan synthetic aperture radar images of Venus (JPL Adaptive Recognition Tool, JARTool).

geomorphology↗

NASA NTRS1992

Programmability in AIPS++

AIPS++ is an Astronomical Information Processing System being designed and implemented by an international consortium of NRAO and six other radio astronomy institutions in Australia, India, the Netherlands, the United Kingdom, Canada, and the USA. AIPS++ is intended to replace the functionality of AIPS, to be more easily programmable, and will be implemented in C++ using object-oriented techniques. Programmability in AIPS++ is planned at three levels. The first level will be that of a command-line interpreter with characteristics similar to IDL and PV-Wave, but with an intensive set of operations appropriate to telescope data handling, image formation, and image processing. The third level will be in C++ with extensive use of class libraries for both basic operations and advanced applications. The third level will allow input and output of data between external FORTRAN programs and AIPS++ telescope and image databases. In addition to summarizing the above programmability characteristics, this talk will given an overview of the classes currently being designed for telescope data calibration and editing, image formation, and the 'toolkit' of mathematical 'objects' that will perform most of the processing in AIPS++.

Hjellming, R. M.↗

NASA NTRS1988

General-Purpose Image-Data Program

Image Database computer program, IBASE, is general-purpose imagery-information system. Use accomplished either by commands or through hierarchy of menus. Analytical capabilities of IBASE include contigency tables, image filtering (low-, high-, and band-pass), proximity maps, clustering, histograms, regression, slope calculations, scaling, and Boolean manipulations. Also has interface to Cheshire Image Classification expert system. Written in FORTRAN 77.

Engle, Steven W.↗

NASA NTRS2004

The Utility of Auroral Image-based Activities Metrics

Auroral activity indices such as Hemispheric Power and Auroral Boundary are currently key data products used for space weather predictions and nowcasting. However, these products are necessarily based on limited observations which must be extrapolated to provide global coverage. The advent of routine space-based auroral imaging in the last decade offers the seeming advantage of more detailed measures of auroral activity. Examples of image-derived products include energy deposition maps, oval location, cap size, and morphological classification. However, activity metrics derived from auroral images have shortcomings, as well. For example, limited fields-of-view and orbital motion prevent full coverage of the auroral regions. This paper will examine the utility of activity metrics derived h m auroral images for operational purposes. The eight-year collection of Polar UVI images databased in the UVI Online Search Tool (OST) will be used to illustrate the advantages and shortcomings of auroral activity metrics. The potential role of other currently-active imaging missions will also be examined and correlative studies to date using auroral imaging will be summarized.

Germany, G.↗

NASA NTRS1995

Content-based retrieval of remote sensed images using a feature-based approach

A feature-based representation model for content-based retrieval from a remote sensed image database is described in this work. The representation is formed by clustering spatially local pixels, and the cluster features are used to process several types of queries which are expected to occur frequently in the context of remote sensed image retrieval. Preliminary experimental results show that the feature-based representation provides a very promising tool for content-based access.

Vellaikal, Asha↗

NASA NTRS1997

Desktop Access to Full-Text NACA and NASA Reports: Systems Developed by NASA Langley Technical Library

NASA Langley Technical Library has been involved in developing systems for full-text information delivery of NACA/NASA technical reports since 1991. This paper will describe the two prototypes it has developed and the present production system configuration. The prototype systems are a NACA CD-ROM of thirty-three classic paper NACA reports and a network-based Full-text Electronic Reports Documents System (FEDS) constructed from both paper and electronic formats of NACA and NASA reports. The production system is the DigiDoc System (DIGItal Documents) presently being developed based on the experiences gained from the two prototypes. DigiDoc configuration integrates the on-line catalog database World Wide Web interface and PDF technology to provide a powerful and flexible search and retrieval system. It describes in detail significant achievements and lessons learned in terms of data conversion, storage technologies, full-text searching and retrieval, and image databases. The conclusions from the experiences of digitization and full- text access and future plans for DigiDoc system implementation are discussed.

Ambur, Manjula Y.↗