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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Image-to-Image Wildfire Detection via Quantum-Compatible Variational Segmentation from Remotely-sensed Data

Over the last decade, the incidence of wildfires has surged, causing widespread destruction globally. To better comprehend and manage these incidents, remote sensing and aerial missions have been implemented in recent efforts. However, this has resulted in an exponential rise in the amount of remote sensing data utilization, leading to a need for intelligent automation of data extraction in wildfire studies. Machine learning provides an accurate automated approach for detecting these natural anomalies and facilitates decision-makers to take prompt actions. To make insightful decisions in wildfire management, it is imperative to move beyond simple detection and explore the potential of probabilistic generative machine learning for creating "what-if" scenarios for various wildfire conditions. Such models offer improved representation of the stochastic nature of wildfire events. However, the optimization of these models can be computationally expensive, especially when using classical computers. Quantum computers have recently emerged as a promising solution to reduce the computational cost of training such models and improve their performance. In this study, we aim to utilize quantum-compatible machine learning techniques to implement our probabilistic generative approach. To that end, we propose a supervised probabilistic variational model consisting of a U-NET-based image-to-image component along with encoder and decoder networks which work as a variational autoencoder (VAE) component. Additionally, we explore the type of latent distribution type in the VAE component and implement different means for modeling the prior distribution. We further investigate the quantum-compatible versions of the model compared to the classical counterpart and benchmark potential benefits of quantum compatibility over the classical model.

quantum machine learning↗
NASA NTRS2002

Experimental Validation of a Neuro-Fuzzy Approach to Phasing the SIBOA Segmented Mirror Testbed

NASA is preparing to launch the Next Generation Space Telescope (NGST). This telescope will be larger than the Hubble Space Telescope, be launched on an Atlas missile rather than the Space Shuttle, have a segmented primary mirror, and be placed in a higher orbit. All these differences pose significant challenges. This effort addresses the challenge of aligning the segments of the primary mirror during the initial deployment. The segments need to piston values aligned to within one tenth of a wavelength. The present study considers using a neuro-fuzzy model of the Fraunhofer diffraction theory. The intention of the current study was to experimentally verify the algorithm derived earlier. The experimental study was to be performed on the SIBOA (Systematic Image Based Optical Alignment) test bed. Unfortunately the hardware/software for SIBOA was not ready by the end of the study period. We did succeed in capturing several images of two stacked segments with various relative phases. These images can be used to calibrate the algorithm for future implementation. This effort is a continuation of prior work. The basic effort involves developing a closed loop control algorithm to phase a segmented mirror test bed (SIBOA). The control algorithm is based on a neuro-fuzzy model of SIBOA and incorporates nonlinear observers built from observer banks. This effort involves implementing the algorithm on the SIBOA test bed.

Philip D. Olivier↗
NASA NTRS2006

Modified Recursive Hierarchical Segmentation of Data

An algorithm and a computer program that implements the algorithm that performs recursive hierarchical segmentation (RHSEG) of data have been developed. While the current implementation is for two-dimensional data having spatial characteristics (e.g., image, spectral, or spectral-image data), the generalized algorithm also applies to three-dimensional or higher dimensional data and also to data with no spatial characteristics. The algorithm and software are modified versions of a prior RHSEG algorithm and software, the outputs of which often contain processing-window artifacts including, for example, spurious segmentation-image regions along the boundaries of processing-window edges.

Tilton, James C.↗
NASA NTRS1975

Dynamic radionuclide determination of regional left ventricular wall motion using a new digital imaging device

In 47 men with arteriographically defined coronary artery disease comparative studies of left ventricular ejection fraction and segmental wall motion were made with radionuclide data obtained from the image intensifier camera computer system and with contrast cineventriculography. The radionuclide data was digitized and the images corresponding to left ventricular end-diastole and end-systole were identified from the left ventricular time-activity curve. The left ventricular end-diastolic and end-systolic images were subtracted to form a silhouette difference image which described wall motion of the anterior and inferior left ventricular segments. The image intensifier camera allows manipulation of dynamically acquired radionuclide data because of the high count rate and consequently improved resolution of the left ventricular image.

Steele, P.↗
NASA NTRS2022

Mars Terrain Segmentation with Less Labels

Planetary rover systems need to perform terrain segmentation to identify drivable areas as well as identify specific types of soil for sample collection. The latest Martian terrain segmentation methods rely on supervised learning which is very data hungry and difficult to train where only a small number of labeled samples are available. Moreover, the semantic classes are defined differently for different applications (e.g., rover traversal vs. geological) and as a result the network has to be trained from scratch each time, which is an inefficient use of resources. This research proposes a semi-supervised learning framework for Mars terrain segmentation where a deep segmentation network trained in an unsupervised manner on unlabeled images is transferred to the task of terrain segmentation trained on few labeled images. The network incorporates a backbone module which is trained using a contrastive loss function and an output atrous convolution module which is trained using a pixel-wise cross-entropy loss function. Evaluation results using the metric of segmentation accuracy show that the proposed method with contrastive pre-training outperforms plain supervised learning by 2%-10%. Moreover, the proposed model is able to achieve a segmentation accuracy of 91.1% using only 161 training images (1% of the original dataset) compared to 81.9% with plain supervised learning.

Wilson, Brian D↗
DOE OSTI2025

Optical image analysis of WSe 2 − thresholding for layer detection

The fast and reliable layer identification of two-dimensional transition metal dichalcogenide (TMD), such as WSe 2 , is essential to investigating their thickness-dependent electronic and optical properties. This article presents efficient optical image thresholding methodology designed to segment the mono, bi, and tri-layer regions of WSe 2 flakes mechanically exfoliated onto a SiO 2 /Si substrate. The optical images were first preprocessed to exclude the background effect and analyzed using the pixel medians and interquartile ranges for fundamental color channels—red, green, and blue (RGB). The analysis of red channel pixel intensities yielded three distinct ranges, serving as thresholds for layer segmentation: monolayer (111.0–118.0), bilayer (103.0–110.0), and tri-layer (93.0–103.0). Similarly, thresholds were established for each color channel, facilitating a comparative study of the segmentation performances. Further, the intersection-over-union ($IoU$) calculations revealed that the red and green channels demonstrated greater than 99 % and 90 % accuracy in differentiating each layer, respectively. This approach yields remarkable results without substantial data calibration that utilizes time-intensive heuristic techniques. Moreover, the proposed methodology offers the flexibility to compare performances across different color channels, expanding the applicability for other 2D material systems.

2D Materials↗
NASA NTRS2004

Formation Flying: The Future of Remote Sensing from Space

Over the next two decades a revolution is likely to occur in how remote sensing of Earth, other planets or bodies, and a range of phenomena in the universe is performed from space. In particular, current launch vehicle fairing volume and mass constraints will continue to restrict the size of monolithic telescope apertures which can be launched to little or no greater size than that of the Hubble Space Telescope, the largest aperture currently flying in space. Systems under formulation today, such as the James Webb Space Telescope will be able to increase aperture size and, hence, imaging resolution, by deploying segmented optics. However, this approach is limited as well, by our ability to control such segments to optical tolerances over long distances with highly uncertain structural dynamics connecting them. Consequently, for orders of magnitude improved resolution as required for imaging black holes, imaging planets, or performing asteroseismology, the only viable approach will be to fly a collection of spacecraft in formation to synthesize a virtual segmented telescope or interferometer with very large baselines. This paper provides some basic definitions in the area of formation flying, describes some of the strategic science missions planned in the National Aeronautics and Space Administration, and identifies some of the critical technologies needed to enable some of the most challenging space missions ever conceived which have realistic hopes of flying.

Leitner, Jesse↗
NASA NTRS2004

Formation Flying: The Future of Remote Sensing from Space

Over the next two decades a revolution is likely to occur in how remote sensing of Earth, other planets or bodies, and a range of phenomena in the universe is performed from space. In particular, current launch vehicle fairing volume and mass constraints will continue to restrict the size of monolithic telescope apertures which can be launched to accommodate only slightly more performance capability than is achievable today, such as by the Hubble Space Telescope. Systems under formulation today, such as the James Webb Space Telescope will be able to increase aperture size and, hence, imaging resolution, by deploying segmented optics. However, this approach is limited as well, by ow ability to control such segments to optical tolerances over long distances with highly uncertain structural dynamics connecting them. Consequently, for orders of magnitude improved resolution as required for imaging black holes, imaging planets, or performing asteroseismology, the only viable approach will be to fly a collection of spacecraft in formation to synthesize a virtual segmented telescope or interferometer with very large baselines. This presentation describes some of the strategic science missions planned in the National Aeronautics and Space Administration, and identifies some of the critical technologies needed to enable some of the most challenging space missions ever conceived which have realistic hopes of flying.

Leitner, Jesse↗
NASA NTRS2007

Spacecraft Formation Flying: An Overview of Missions and Technologies

Over the next two decades a revolution is likely to occur in how remote sensing of Earth, other planets or bodies, and a range of phenomena in the universe is performed from space. In particular, current launch vehicle fairing volume and mass constraints will continue to restrict the size of monolithic telescope apertures which can be launched to accommodate only slightly more performance capability than is achievable today, such as by the Hubble Space Telescope. Systems under formulation today, such as the James Webb Space Telescope, will be able to increase aperture size and, hence, imaging resolution, by deploying segmented optics. However, this approach is limited as well, by our ability to control such segments to optical tolerances over long distances with highly uncertain structural dynamics connecting them. Consequently, for orders of magnitude improved resolution as required for imaging black holes, imaging planets, or performing asteroseismology, the only viable approach will be to fly a collection of spacecraft in formation to synthesize a virtual segmented telescope or interferometer with very large baselines. This presentation highlights some of the strategic science missions planned in the National Aeronautics and Space Administration, and identifies some of the critical technologies needed to enable some of the most challenging space missions ever conceived which have realistic hopes of flying.

Leitner, Jesse↗
NASA NTRS2013

Hand-Based Biometric Analysis

Hand-based biometric analysis systems and techniques provide robust hand-based identification and verification. An image of a hand is obtained, which is then segmented into a palm region and separate finger regions. Acquisition of the image is performed without requiring particular orientation or placement restrictions. Segmentation is performed without the use of reference points on the images. Each segment is analyzed by calculating a set of Zernike moment descriptors for the segment. The feature parameters thus obtained are then fused and compared to stored sets of descriptors in enrollment templates to arrive at an identity decision. By using Zernike moments, and through additional manipulation, the biometric analysis is invariant to rotation, scale, or translation or an input image. Additionally, the analysis uses re-use of commonly seen terms in Zernike calculations to achieve additional efficiencies over traditional Zernike moment calculation.

Bebis, George↗
NASA NTRS2015

Hand-Based Biometric Analysis

Hand-based biometric analysis systems and techniques are described which provide robust hand-based identification and verification. An image of a hand is obtained, which is then segmented into a palm region and separate finger regions. Acquisition of the image is performed without requiring particular orientation or placement restrictions. Segmentation is performed without the use of reference points on the images. Each segment is analyzed by calculating a set of Zernike moment descriptors for the segment. The feature parameters thus obtained are then fused and compared to stored sets of descriptors in enrollment templates to arrive at an identity decision. By using Zernike moments, and through additional manipulation, the biometric analysis is invariant to rotation, scale, or translation or an in put image. Additionally, the analysis utilizes re-use of commonly-seen terms in Zernike calculations to achieve additional efficiencies over traditional Zernike moment calculation.

Bebis, George↗
NASA NTRS1994

N2 Lyman-Birge-Hopfield dayglow from ATLAS 1

Spectral measurements of the far ultraviolet dayglow were made from the ATLAS 1 shuttle mission using an intensified charge coupled device (CCD) imaging spectrometer array. The instrument imaged relatively large (177 A) segments of the spectrum simultaneously and had the capability to image altitude in the second dimension of the two-dimensional focal plane detector when the entrance slit of the instrument was oriented perpendicular to the limb of the Earth. The far ultraviolet (FUV) channel of the instrument used a CsTe photocathode rather than the more conventionally used and more solar blind CsI photocathode material. As a result, the spectra were also measured with good sensitivity at FUV wavelengths longer than 1500 A. In this paper, data are selected of specific interest to a study of the N2 Lyman-Birge-Hopfield system using two shuttle attitudes: In the first the field of view was held at a fixed tangent ray height of approximately 140 km while scanning in wavelength, providing repeated FUV spectra over a range of latitudes and allowing comparison with our thermospheric airglow model. In the second observing sequence the line of sight of the instrument was scanned down through the atmosphere but covered about 75% of the full wavelength range. This sequence allows comparison of height dependence,including O2 absorption effects, with the thermospheric model. In all cases, relatively good agreement is obtained with the model (run strictly in a predictive mode) in comparisions in which the line of sight must be intergrated along a path that spans a considerable range of conditions (height, local time, latitude, solar zenith angle). In the case of the data sets examined in this study the vibrational population distributions show mixed results. In one case the distribution agrees well with a theoretical model based on direct electron impact excitation without a significant cascade contribution. A second case indicated a lower population in nu' = 3 and a higher population in nu' = 6 than would be expected from direct impact excitation alone. This supports previous indications that conditions resulting in the cascade mechanism may not always be operative.

Torr, Marsha R.↗
DOE OSTI2025

Effect of threshold parameters on infrared segmentation methods for porosity detection in electron beam powder bed fusion

In-situ process monitoring has seen significant interest in additive manufacturing to address qualification and certification goals. This is especially prevalent in metal powder bed fusion processes such as electron beam powder bed fusion (PBF-EB), with layer-wise infrared imaging being commonly used to detect defects. Here, this work compares two different segmentation methods (static thresholding and statistical thresholding) used for detecting porosity from in-situ infrared imaging data for PBF-EB. Samples were manufactured at a variety of focus offset values to induce porosity. Then, the segmented infrared images were compared to ex-situ X-ray computed tomography scans, which served as a ground-truth reference for objective evaluation. Through this analysis framework, the influential parameters, static threshold and N-value (number of standard deviations above the mean pixel value), respectively, for both image segmentation methods were analyzed and compared for their effects on porosity detection. With optimal parameter settings, the two methods had similar porosity detection performance, but the statistical method performed better under a larger variety of parameter settings.

Infrared imaging↗
NASA NTRS1974

Analysis of ERTS-1 linear features in New York State

The author has identified the following significant results. All ERTS-1 linears confirmed to date have topographic expression although they may appear as featureless tonal linears on the imagery. A bias is unavoidably introduced against any linears which may parallel raster lines, lithological trends, or the azimuth of solar illumination. Ground study of ERTS-1 topographic lineaments in the Adirondacks indicates: outcrops along linears are even more rare than expected, fault breccias are found along some NNE lineaments, chloritization and slickensiding without brecciation characterize one EW lineament whereas closely-spaced jointing plus a zone of plastic shear define another. Field work in the Catskills suggests that the prominent new NNE lineaments may be surface manifestations of normal faulting in the basement, and that it may become possible to map major joint sets over extensive plateau regions directly on the imagery. Fall and winter images each display some unique linears, and long linears on the fall image commonly appear as aligned segments on the winter scene. A computer-processed color composite image permitted the extraction or additional information on the shaded side of mountains.

Isachsen, Y. W.↗
NASA NTRS2023

Neural-Based Compression Scheme for Solar Image Data

Studying the solar system and especially the Sun relies on the data gathered daily from space missions. These missions are data-intensive and compressing this data to make them efficiently transferable to the ground station is a twofold decision to make. Stronger compression methods, by distorting the data, can increase data throughput at the cost of accuracy which could affect scientific analysis of the data. On the other hand, preserving subtle details in the compressed data requires a high amount of data to be transferred, reducing the desired gains from compression. In this work, we propose a neural network-based lossy compression method to be used in NASA’s data-intensive imagery missions. We chose NASA’s Solar Dynamics Observatory (SDO) mission which transmits 1.4 terabytes of data each day as a proof of concept for the proposed algorithm. In this work, we propose an adversarially trained neural network, equipped with local and non-local attention modules to capture both the local and global structure of the image resulting in a better trade-off in rate-distortion (RD) compared to conventional hand-engineered codecs. The RD variational autoencoder used in this work is jointly trained with a channel-dependent entropy model as a shared prior between the analysis and synthesis transforms to make the entropy coding of the latent code more effective. We also studied how optimizing perceptual losses could help our neural compressor to preserve high-frequency details of the data in the reconstructed compressed image. Our neural image compression algorithm outperforms currently-in-use and state-of-the-art codecs such as JPEG and JPEG-2000 in terms of the RD performance when compressing extreme-ultraviolet (EUV) data. As a proof of concept for use of this algorithm in SDO data analysis, we have performed coronal hole (CH) detection using our compressed images, and generated consistent segmentations, even at a compression rate of ∼ 0.1 bits per pixel (compared to 8 bits per pixel on the original data) using EUV data from SDO.

Image coding↗
DOE OSTI2025

Accurate segmentation of localized corrosion in structural alloys via deep learning

This study presents a deep learning-based approach for the automated segmentation of corrosion damage in scanning electron microscopy (SEM) images. The proposed method enables rapid and accurate segmentation of corrosion features in these SEM images, making it highly suitable for real-time applications such as automated microscopy. Specifically, a dedicated corrosion segmentation database tailored for this task is constructed. The newly constructed dataset, alongside data from two public databases, are employed to jointly train a deep learning-based model modified with a texture refinement module. Compared to the same model without the texture refinement module, the refined model substantially enhances the efficacy and efficiency of corrosion segmentation. Furthermore, the methodology developed here is extendable to segmentation tasks for other materials with similar resolution, texture, and contrast characteristics, thereby paving the way for accelerated and automated analysis in corrosion science and beyond.

Artificial Intelligence↗
NASA NTRS1984

Scene segmentation through region growing

A computer algorithm to segment Landsat Thematic Mapper (TM) images into areas representing surface features is described. The algorithm is based on a region growing approach and uses edge elements and edge element orientation to define the limits of the surface features. Adjacent regions which are not separated by edges are linked to form larger regions. Some of the advantages of scene segmentation over conventional TM image extraction algorithms are discussed, including surface feature analysis on a pixel-by-pixel basis, and faster identification of the pixels in each region. A detailed flow diagram of region growing algorithm is provided.

Latty, R. S.↗
DOE OSTI2026

A Centralized AI Lakehouse Framework for Brain Tumor MRI Classification and Segmentation, University KPI Forecasting, and Water Potability Prediction

In many university and healthcare projects, models are built for very different data types such as tables, institutional time series, and medical images, but they are deployed as separate applications. In this work, that separation made testing and maintenance difficult because each module had its own pipeline and runtime requirements. This paper presents an integrated AI lakehouse-style implementation that runs three model pipelines inside one containerized backend. For medical imaging, we used MRI datasets from IEEE DataPort: a four-class classification set with 7012 images (5708 train/1304 test) and a segmentation set with 3063 image–mask pairs. The classification model (ResNet50 transfer learning) is evaluated using a proper train–validation–test protocol across multiple splits (80/10/10, 70/10/20, 60/10/30, and 10/30/60), achieving a test accuracy of 99.00% under the standard 80/10/10 split. Additionally, a patient-level evaluation is conducted using an external glioma dataset to provide a more realistic assessment without data leakage. The segmentation model (DeepLabV3-ResNet50) achieved 83.09% validation mIoU and 88.79% Dice score. For university KPI forecasting, we used annual IPEDS and NSF HERD data from 2010 to 2023 for three universities (BSU, EOU, and UAB). To examine the effect of preprocessing on forecasting performance, two case studies are conducted. In the first case, linear interpolation is applied to generate semester-level data. In the second case, the original annual data is used directly without interpolation. Random Forest regression and ARIMA models are evaluated using MAE, RMSE, MAPE, and R 2 . The results showed that interpolation improved apparent forecasting performance due to smoothing, while evaluation on the original annual data provided a more realistic assessment of model behavior. To further validate the framework on a larger dataset, an additional case study is conducted using a student dropout dataset. For water potability, we trained and compared multiple tabular classifiers on a large dataset (1,048,575 samples). A Random Forest model (100 trees, max depth 10) achieved 85.86% test accuracy and high recall for unsafe samples (0.8447). All modules are served via FastAPI and deployed together using Docker, with workflow automation routing requests to the correct endpoint. System-level benchmarking indicates that the backend maintains stable throughput and latency under concurrent requests.

97 MATHEMATICS AND COMPUTING↗