Search NASA⌕ Search

SEARCH · Search NASA

Results for “Image segmentation”

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.

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

At least 505 records · Page 28
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Bragg Spot Finder (BSF): a new machine-learning-aided approach to deal with spot finding for rapidly filtering diffraction pattern images

Macromolecular crystallography contributes significantly to understanding diseases and, more importantly, how to treat them by providing atomic resolution 3D structures of proteins. This is achieved by collecting X-ray diffraction images of protein crystals from important biological pathways. Spotfinders are used to detect the presence of crystals with usable data, and the spots from such crystals are the primary data used to solve the relevant structures. Having fast and accurate spot finding is essential, but recent advances in synchrotron beamlines used to generate X-ray diffraction images have brought us to the limits of what the best existing spotfinders can do. This bottleneck must be removed so spotfinder software can keep pace with the X-ray beamline hardware improvements and be able to see the weak or diffuse spots required to solve the most challenging problems encountered when working with diffraction images. In this paper, we first present Bragg Spot Detection (BSD), a large benchmark Bragg spot image dataset that contains 304 images with more than 66 000 spots. We then discuss the open source extensible U-Net-based spotfinder Bragg Spot Finder (BSF), with image pre-processing, a U-Net segmentation backbone, and post-processing that includes artifact removal and watershed segmentation. Finally, we perform experiments on the BSD benchmark and obtain results that are (in terms of accuracy) comparable to or better than those obtained with two popular spotfinder software packages ( Dozor and DIALS ), demonstrating that this is an appropriate framework to support future extensions and improvements.

36 MATERIALS SCIENCE↗
DOE OSTI2025

DeepAndes: A Self-Supervised Vision Foundation Model for Multispectral Remote Sensing Imagery of the Andes

By mapping sites at large scales usingremotely sensed data, archaeologists can generate unique insights into long-term demographic trends, interregional social networks, and human adaptations in the past. Remote sensing surveys complement field-based approaches, and their reach can be especially great when combined with deep learning and computer vision techniques. However, conventional supervised deep learning methods face challenges in annotating fine-grained archaeological features at scale. In addition, while recent vision foundation models have shown remarkable success in learning large-scale remote sensing data with minimal annotations, most off-the-shelf solutions are designed for RGB images rather than multispectral satellite imagery, such as the eight-band data used in our study. In this article, we introduce DeepAndes, a transformer-based vision foundation model trained on three million multispectral satellite images, specifically tailored for Andean archaeology. DeepAndes incorporates a customized DINOv2 self-supervised learning algorithm optimized for eight-band multispectral imagery, marking the first foundation model designed explicitly for the Andes region. We evaluate its image understanding performance through imbalanced image classification, image instance retrieval, and pixel-level semantic segmentation tasks. Our experiments show that DeepAndes achieves superior F1 scores, mean average precision, and Dice scores in few-shot learning scenarios, significantly outperforming models trained from scratch or pretrained on smaller datasets. This underscores the effectiveness of large-scale self-supervised pretraining in archaeological remote sensing.

Guo, Junlin [Vanderbilt Univ., Nashville, TN (Unit↗
NASA NTRS1983

NASA TM processing system description and status

An overview of the processing system for LANDSAT 4 imagery is given. Charts show system requirements; the LANDSAT 4 ground segment with its elements, configurations, and data flow; image generation requirements; and the major functions, interfaces, and hardware of the image generation facility and the image processing systems for the TM and MSS. The laser beam film recorder and the high density digital recorder are covered as well as the data available at EDC.

Watt, W.↗
NASA NTRS1988

Model-based orientation-independent 3-D machine vision techniques

Orientation-dependent techniques for the identification of a three-dimensional object by a machine vision system are represented in parts. In the first part, the data consist of intensity images of polyhedral objects obtained by a single camera, while in the second part, the data consist of range images of curved objects obtained by a laser scanner. In both cases, the attributed graphic representation of the object surface is used to drive the respective algorithm. In this representation, a graph node represents a surface patch and a link represents the adjacency between two patches. The attributes assigned to nodes are moment invariants of the corresponding face for polyhedral objects. For range images, the Gaussian curvature is used as a segmentation criterion for providing symbolic shape attributes. Identification is achieved by an efficient graph-matching algorithm used to match the graph obtained from the data to a subgraph of one of the model graphs stored in the commputer memory.

De Figueiredo, R. J. P.↗
NASA NTRS1994

Unsupervised Segmentation Of Polarimetric SAR Data

Method of unsupervised segmentation of polarimetric synthetic-aperture-radar (SAR) image data into classes involves selection of classes on basis of multidimensional fuzzy clustering of logarithms of parameters of polarimetric covariance matrix. Data in each class represent parts of image wherein polarimetric SAR backscattering characteristics of terrain regarded as homogeneous. Desirable to have each class represent type of terrain, sea ice, or ocean surface distinguishable from other types via backscattering characteristics. Unsupervised classification does not require training areas, is nearly automated computerized process, and provides nonsubjective selection of image classes naturally well separated by radar.

Rignot, Eric J.↗
NASA NTRS1994

Segmentation Of Polarimetric SAR Data

Report presents one in continuing series of studies of segmentation of polarimetric synthetic-aperture-radar, SAR, image data into regions. Studies directed toward refinement of method of automated analysis of SAR data.

Rignot, Eric J. M.↗
NASA NTRS1994

Neural networks: Application to medical imaging

The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.

Clarke, Laurence P.↗
NASA NTRS2002

Highlights of 10-Year Remote Sensing Industry Analysis

A background and highlights of a 10 year remote sensing industry analysis are provided.Included are the following:Training, educational analysis, staff levels, and end-users analysis, market drivers, market segments,application areas, spatial resolution needs, use of image types.

Rabin, Ron↗
NASA NTRS1998

Segmentation and tracking in echocardiographic sequences: active contours guided by optical flow estimates

This paper presents a method for segmentation and tracking of cardiac structures in ultrasound image sequences. The developed algorithm is based on the active contour framework. This approach requires initial placement of the contour close to the desired position in the image, usually an object outline. Best contour shape and position are then calculated, assuming that at this configuration a global energy function, associated with a contour, attains its minimum. Active contours can be used for tracking by selecting a solution from a previous frame as an initial position in a present frame. Such an approach, however, fails for large displacements of the object of interest. This paper presents a technique that incorporates the information on pixel velocities (optical flow) into the estimate of initial contour to enable tracking of fast-moving objects. The algorithm was tested on several ultrasound image sequences, each covering one complete cardiac cycle. The contour successfully tracked boundaries of mitral valve leaflets, aortic root and endocardial borders of the left ventricle. The algorithm-generated outlines were compared against manual tracings by expert physicians. The automated method resulted in contours that were within the boundaries of intraobserver variability.

Non-NASA Center↗
NASA NTRS2018

Alignment and Bonding of Silicon Mirrors for High-Resolution Astronomical X-Ray Optics [10699-141]

Future large x-ray astronomy missions require large area and high resolution. The present consensus is to integrate thin, lightweight, segmented mirrors to form a compact but large telescope with high resolution (better than 1 sec). Key technologies: 1) Accurate mirror substrates: polishing high quality mono-crystalline silicon. 2) Stress-free reflective coating: stress-based distortion cancellation. 3) Precise alignment and integration: kinematic mounting and distortion-free bonding. Four-point alignment for quasi-cylindrically symmetric mirrors (segments) - 4-Point alignment: Pitch and yaw angles, image center (X, Y) are controlled by heights of the 4 mount points; Alignment Precision: better than 1 sec; Bonding error: approx. 0.1 micrometers (approx. 1 sec); Current single mirror pair x-ray tested: 3 sec (Half-Power Diameter). Integration into (meta) shell: Shell structure has rotationally defined axis; Interlocking mirrors means lightweight, mechanically strong telescope.

Chan, Kai-Wing↗
DOE OSTI2025

Examining Constituent Redistribution in U-19Pu-10Zr Fuel as it Evolves with Local Burnup

While constituent redistribution is a known irradiation behavior in U-Pu-Zr fuel, new data have shown it is more complex than our current understanding and predictive capabilities. The size and composition of redistributed rings evolve as a function of pin composition, burnup, geometry, and irradiation temperature. In this work, we extract microstructural information from optical microscopy conducted on U-19Pu-10Zr pins (irradiated between 1.9 at. % and 11.6 at. % peak burnup). Both manual image analysis techniques and machine learning-assisted segmentation are used to quantify the thicknesses of the cladding, fuel-cladding interaction layers, and rings of fuel constituent redistribution in addition to pore distribution. These microstructural features and individual redistributed regions affect local thermomechanical properties, and identifying the relationship between burnup and constituent redistribution will improve accurate prediction of advanced reactor fuel performance.

Constituent Redistribution↗
NASA NTRS1997

High resolution magnetic resonance imaging of the calcaneus: age-related changes in trabecular structure and comparison with dual X-ray absorptiometry measurements

A high-resolution magnetic resonance imaging (MRI) protocol, together with specialized image processing techniques, was applied to the quantitative measurement of age-related changes in calcaneal trabecular structure. The reproducibility of the technique was assessed and the annual rates of change for several trabecular structure parameters were measured. The MR-derived trabecular parameters were compared with calcaneal bone mineral density (BMD), measured by dual X-ray absorptiometry (DXA) in the same subjects. Sagittal MR images were acquired at 1.5 T in 23 healthy women (mean age: 49.3 +/- 16.6 [SD]), using a three-dimensional gradient echo sequence. Image analysis procedures included internal gray-scale calibration, bone and marrow segmentation, and run-length methods. Three trabecular structure parameters, apparent bone volume (ABV/TV), intercept thickness (I.Th), and intercept separation (I.Sp) were calculated from the MR images. The short- and long-term precision errors (mean %CV) of these measured parameters were in the ranges 1-2% and 3-6%, respectively. Linear regression of the trabecular structure parameters vs. age showed significant correlation: ABV/TV (r2 = 33.7%, P < 0.0037), I.Th (r2 = 26.6%, P < 0.0118), I.Sp (r2 = 28.9%, P < 0.0081). These trends with age were also expressed as annual rates of change: ABV/TV (-0.52%/year), I.Th (-0.33%/year), and I.Sp (0.59%/year). Linear regression analysis also showed significant correlation between the MR-derived trabecular structure parameters and calcaneal BMD values. Although a larger group of subjects is needed to better define the age-related changes in trabecular structure parameters and their relation to BMD, these preliminary results demonstrate that high-resolution MRI may potentially be useful for the quantitative assessment of trabecular structure.

NASA Discipline Number 26-10↗
NASA NTRS2012

OpTIIX: An ISS-Based Testbed Paving the Roadmap Toward a Next Generation Large Aperture UV/Optical Space Telescope

The next generation large aperture UV/Optical space telescope will need a diameter substantially larger than even that of JWST in order to address some of the most compelling unanswered scientific quests. These quests include understanding the earliest phases of the Universe and detecting life on exo-planets by studying spectra of their atmospheres. Such 8-16 meter telescopes face severe challenges in terms of cost and complexity and are unlikely to be affordable unless a new paradigm is adopted for their design and construction. The conventional approach is to use monolithic or preassembled segmented mirrors requiring complicated and risky deployments and relying on future heavy-lift vehicles, large fairings and complex geometry. The new paradigm is to launch component modules on relatively small vehicles and then perform in-orbit robotic assembly of those modules. The Optical Testbed and Integration on ISS eXperiment (OpTIIX) is designed to demonstrate, at low cost by leveraging the infrastructure provided by ISS, telescope assembly technologies and end-to-end optical system technologies. The use of ISS as a testbed permits the concentration of resources on reducing the technical risks associated with robotically integrating the components. These include laser metrology and wavefront sensing and control (WFS&C) systems, an imaging instrument, lightweight, low-cost deformable primary mirror segments and the secondary mirror. These elements are then aligned to a diffraction-limited optical system in space. The capability to assemble the optical system and remove and replace components via the existing ISS robotic systems like the Special Purpose Dexterous Manipulator (SPDM), or by the ISS flight crew, allows for future experimentation, as well as repair.

Carpenter, Kenneth G.↗
NASA NTRS1978

Color enhancement of landsat agricultural imagery: JPL LACIE image processing support task

Color enhancement techniques were applied to LACIE LANDSAT segments to determine if such enhancement can assist analysis in crop identification. The procedure involved increasing the color range by removing correlation between components. First, a principal component transformation was performed, followed by contrast enhancement to equalize component variances, followed by an inverse transformation to restore familiar color relationships. Filtering was applied to lower order components to reduce color speckle in the enhanced products. Use of single acquisition and multiple acquisition statistics to control the enhancement were compared, and the effects of normalization investigated. Evaluation is left to LACIE personnel.

Madura, D. P.↗
NASA NTRS1988

Parallel algorithm for determining motion vectors in ice floe images by matching edge features

A parallel algorithm is described to determine motion vectors of ice floes using time sequences of images of the Arctic ocean obtained from the Synthetic Aperture Radar (SAR) instrument flown on-board the SEASAT spacecraft. Researchers describe a parallel algorithm which is implemented on the MPP for locating corresponding objects based on their translationally and rotationally invariant features. The algorithm first approximates the edges in the images by polygons or sets of connected straight-line segments. Each such edge structure is then reduced to a seed point. Associated with each seed point are the descriptions (lengths, orientations and sequence numbers) of the lines constituting the corresponding edge structure. A parallel matching algorithm is used to match packed arrays of such descriptions to identify corresponding seed points in the two images. The matching algorithm is designed such that fragmentation and merging of ice floes are taken into account by accepting partial matches. The technique has been demonstrated to work on synthetic test patterns and real image pairs from SEASAT in times ranging from .5 to 0.7 seconds for 128 x 128 images.

Manohar, M.↗
NASA NTRS2001

Use of Yohkoh SXT in Measuring the Net Current and CME Productivity of Active Regions

In our investigation of the correlation of global nonpotentiality of active regions to their CME productivity (Falconer, D.A. 2001, JGR, in press, and Falconer, Moore, & Gary, 2000, EOS 82, 20 S323), we use Yohkoh SXT images for two purposes. The first use is to help resolve the 180 degree ambiguity in the direction of the observed transverse magnetic field. Resolution of the 180 degree ambiguity is important, since the net current, one of our measures of global nonpotentiality, is derived from integrating the dot product of the transverse field around a contour (I(sub N)=(integral)BT(raised dot)dl). The ambiguity results from the observed transverse field being determined from the linear polarization, which gives the plane of the direction, but leaves a 180 degrees ambiguity. Automated methods to resolve the ambiguity ranging from the simple acute angle rule (Falconer, D.A. 2001) to the more sophisticated annealing method (Metcalf T.R. 1994). For many active regions, especially ones that are nearly potential these methods work well. But for very nonpotential active regions where the shear angle (the angle between the observed and potential transverse field) is near 90 degrees throughout large swaths along the main neutral line, both methods can resolve the ambiguity incorrectly for long segments of the neutral line. By determining from coronal images, such as those from Yohkoh/SXT, the sense of shear along the main neutral line in the active region, these cases can be identified and corrected by a modification of the acute angle rule described here. The second use of Yohkoh/SXT in this study is to check for the cusped coronal arcades of long-duration eruptive flares. This signature is an excellent proxy for CMEs, and was used by Canfield, Hudson, and McKenzie (1999 GRL V26, 6, 627-630). This work is funded by NSF through the Space Weather Program and by NASA through the Solar Physics Supporting Research and Technology Program.

Falconer, D. A.↗
NASA NTRSDate not supplied

The Porous Microstructure Analysis (PuMA) software

The open-source Porous Microstructure Analysis (PuMA) software was implemented to offer an efficient framework for determining material characteristics from 3D microstructures. Its development was inspired by progress in X-ray microtomography, an imaging technology that captures the internal structure of materials in 3D, and even in a 4D temporal context. Over recent years, this method has transformed the domain of materials science due to its capability to non-destructively examine material microstructures while presenting digital data about their geometrical details. It has provided insights into materials relevant to several NASA missions, including heatshields, parachute fabrics, meteorites, and other advanced composites. PuMA, in its current version 3, delivers an array of features, spanning from basic geometric insights of a microstructure to intricate anisotropic thermo-elastic and chemical behavior. Specifically, the software evaluates morphological attributes (specific surface area, volume fractions, mean intercept lengths, orientation) and physical characteristics (conductivity, elasticity, permeability, and tortuosity). Additionally, it can model material degradation processes, such as oxidation and surface chemistry interactions. The software can generate synthetic microstructures, from straightforward geometrical designs to intricate woven and non-woven geometries. Coupling material generation and characterization enable parametric studies and sensitivity analysis to optimize the microstructural performance and inform design decisions and reliability assessment based on uncertainty quantification. A recent addition to PuMA includes the TomoSAM plugin, devised to incorporate the cutting-edge Segment Anything Model (SAM). SAM is a promptable deep learning model that can identify objects and create image masks in a zero-shot manner, based only on a few user clicks. The synergy between these tools aids in the segmentation of complex 3D datasets from tomography or other imaging techniques, which would otherwise require a laborious manual segmentation process.

Tomography↗
NASA NTRS1993

Direct 75 milliarcsecond images from the Multiple Mirror Telescope with adaptive optics

We report results from an adaptive optics system designed to provide imaging at the diffraction limit of resolution in the near-infrared at the Multiple Mirror Telescope (MMT). For the present experiment, the aperture consisted of five of the six primary mirrors of the MMT, operating as a coherently phased array. The largest components of the atmospherically induced wave-front aberration are the fluctuations in mean phase between the segments. These errors were derived in real time from the Fourier transform of short-exposure stellar images at 2.2 microns and corrected at an image of the telescope pupil with piston motion from a segmented adaptive mirror. At a correction rate of 43 Hz, this level of adaptive control resulted in an integrated image with a clear diffraction-limited component of 0.075 arcsec FWHM. This stabilized component is present directly in the light arriving at the detector and is not the result of postprocessing. We discuss future improvements to our adaptive wave-front control and its application to astronomical observations.

Lloyd-Hart, M.↗