Search NASA⌕ Search

SEARCH · Search NASA

Results for “image classification”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
NASA NTRS2003

Detecting water hazards for autonomous off-road navigation

Detecting water hazards for autonomous, off-road navigation of unmanned ground vehicles is a largely unexplored problem. In this paper, we catalog environmental variables that affect the difficulty of this problem, including day vs. night operation, whether the water reflects sky or other terrain features, the size of the water body, and other factors. We briefly survey sensors that are applicable to detecting water hazards in each of these conditions. We then present analyses and results for water detection for four specific sensor cases: 1) using color image classification to recognize sky reflections in water during the day, 2) using ladar to detect the presence of water bodies and to measure their depth, 3) using short-wave infrared (SWIR) imagery to detect water bodies, as well as snow and ice, and 4) using mid-wave infrared (MWIR) imagery to recognize water bodies at night. For color imagery, we demonstrate solid results with a classifier that runs at nearly video rate on a 433 MHz processor. For ladar, we present a detailed propagation analysis that shows the limits of water body detection and depth estimation as a function of look ahead distance, water depth, and ladar wavelength. For SWIR and MWIR, we present sample imagery from a variety of data collections that illustrate the potential of these sensors. These results demonstrate significant progress on this problem.

McHenry, Mike↗
NASA NTRSDate not supplied

QuantifyML: How good is my machine learning model?

This paper presents an approach, QuantifyML, which employs model counting to assess the learnability and robustness of machine learning models. Typically the efficacy of machine learning models is determined by computing their accuracy statistically on test data sets. However, this may be misleading, if the test data is not representative of the problem that is being studied. Further, two different models may have the same accuracy on a given data set, measured statistically, but may be very different in their behavior on unseen data. Also, models with high accuracy could have poor adversarial robustness. In QuantifyML, our goal is to precisely quantify the extent to which machine learning models have learned and generalized from the given data. In QuantifyML, a trained model is translated into a C program, which is fed to the CBMC model checking tool to produce a formula in Conjunctive Normal Form (CNF), which in turn is analyzed with state-of-the-art model counters to efficiently obtain precise counts w.r.t different outputs. QuantifyML enables i) evaluating the learnability of models by comparing the counts for the outputs to ground truth, expressed as logical predicates (if available), ii) comparing the performance of different models that may be built with different machine learning algorithms (e.g., decision-trees vs. neural networks), and iii) quantifying the robustness of trained models around given inputs. Our evaluation demonstrates these applications of QuantifyML on decision trees and neural networks trained to learn relational properties of graphs, for which we know the ground truth, and to perform image classification, for which we do not have the ground truth, but we can quantify local robustness.

Deep Neural Networks↗
NASA NTRS2022

Neurosymbolic Hybrid Approach to Driver Collision Warning

There are two main algorithmic approaches to autonomous driving systems: (1) An end-to-end system in which a single deep neural network learns to map sensory input directly into appropriate warning and driving responses. (2) A mediated hybrid recognition system in which a system is created by combining independent modules that detect each semantic feature. While some researchers believe that deep learning can solve any problem, others believe that a more engineered and symbolic approach is needed to cope with complex environments with less data. Deep learning alone has achieved state-of-the-art results in many areas, from complex gameplay to predicting protein structures. In particular, in image classification and recognition, deep learning models have achieved accuracies as high as humans. But sometimes it can be very difficult to debug if the deep learning model doesn't work. Deep learning models can be vulnerable and are very sensitive to changes in data distribution. Generalization can be problematic. It's usually hard to prove why it works or doesn't. Deep learning models can also be vulnerable to adversarial attacks. Here, we combine deep learning-based object recognition and tracking with an adaptive neurosymbolic network agent, called the Non-Axiomatic Reasoning System (NARS), that can adapt to its environment by building concepts based on perceptual sequences. We achieved an improved intersection-over-union (IOU) object recognition performance of 0.65 in the adaptive retraining model compared to IOU 0.31 in the COCO data pre-trained model. We improved the object detection limits using RADAR sensors in a simulated environment, and demonstrated the weaving car detection capability by combining deep learning-based object detection and tracking with a neurosymbolic model.

Wang, Pei↗
NASA NTRSDate not supplied

Advancement of Deep Learning and Geometric Methods for Active Terrain Relative Navigation

To enhance NASA’s precision landing capabilities, in conjunction with the development of a novel active terrain relative navigation (ATRN) and terrain mapping system, denoted SHERIF, this work performed a comparative analysis between both deep-learning (DL) based and geometric approaches to hazard detection (HD) and safe-site-identification (SSI) through hardware-in-the loop testing on the Six degree-of-freedom Tendon Actuated Robot (STAR). The Standalone Hazard Evaluation and Refinement using Instrument Findings (SHERIF) system is capable of ingesting sensor data at an asynchronous rate, stitching successive terrain scans together to yield a high-resolution digital elevation map (DEM), performing absolute and relative localization using novel 3D feature extraction and matching methods, and HD/SSI activities. The DL-based HD/SSI algorithm provides a modular alternative to classical geometric approaches which have performance times that scale with map resolution. As the adoption of AI solutions become more prevalent for autonomous system decision making, it is prudent to explore the utility of such solutions in applications where they traditionally excel, such as image classification. Along with the development of a DL-based HD system, this work performed the first comparative analysis between DL and geometric approaches to HD/SSI using real sensor data from real-time testing in a relevant environment.

Davis Adams↗
NASA NTRS2024

EdgeCortix SAKURA-I Machine-Learning, PCIe Accelerator SEE Heavy Ion Test Report

To enable autonomy in space, machine-learning and computer vision applications become invaluable for sensor processing. However, these algorithms are computationally complex and unfeasible for many embedded central processing units (CPUs) and usually require external coprocessors, such as graphics processing units (GPUs) or accelerators specific to the application, including application specific integrated circuits (ASICs). In power-constrained systems, GPUs tend to consume more power than is acceptable (>40W), so lower-power accelerators have shown promise to provide the performance needed under spacecraft constraints. For radiation engineers, developing methodologies that can properly test CPUs, GPUs, and accelerators, and enable comparisons between them remains a necessary complication to solve as the devices become more complex. The methodology in this test aims to be a start in developing a baseline single-event effect (SEE) test for client-device machine learning accelerators. This category of devices do not host their own operating system. This testing campaign is a continuation of a previous 200 MeV proton test performed in January 2024. This report covers two heavy ion tests of the SAKURA-I card: one in April 2024, and one in June 2024. Additional data was needed after the April test due to ion-range issues experienced at higher linear-energy transfers (LETs). These range issues are described in more detail in Section 8. This experiment characterizes SEEs and data error susceptibility of the EdgeCortix SAKURA-I machine-learning accelerator under heavy ions. The device was monitored for single event upsets (SEUs) and single event functional interrupts (SEFIs) at the Lawrence Berkeley National Laboratory’s 88-inch cyclotron. The SAKURA-I board accelerates machine-learning inference applications on a host computer through a PCIex16 connection. For the purposes of devising an end to end automated analysis workflow for this experiment, the YOLO-V5 and SSD300 objection-detection models, and the ResNet-50, EfficientNet, and MobileNetV2 image classification models were used as a representative suite of analytical machine-learning models.

Seth S Roffe↗
DOE OSTI2025

Two-Frequency RF Fields Induced Multipactor in Coaxial Transmission Lines

Multipactor is a nonlinear discharge phenomenon that occurs in vacuum RF systems, potentially leading to signal distortion, power loss, and even permanent damage to high-power components. This study presents a detailed investigation of two-surface multipactor in coaxial transmission lines under two-frequency excitation, using one-dimensional (1D) Monte Carlo simulations validated by three-dimensional (3D) Particle-in-Cell (PIC) results and experimental data. Introducing a second carrier mode is shown to suppress multipactor by reshaping and shrinking the susceptibility region, with the extent and location of suppression strongly dependent on the device aspect ratio and the relative phase of the second mode. Distinct suppression patterns emerge across different frequency–gap distance (fd) regimes, and in certain cases, susceptibility expansion is also observed. The study identifies and distinguishes pure and mixed multipactor modes in coaxial geometry, where analytical mode boundaries are not readily defined. Unlike planar systems, pure-mode regions in coaxial structures overlap with mixed-mode domains, complicating classification. Image charge forces are found to have minimal effect on susceptibility thresholds but do influence electron growth rates. These findings provide new insights into waveform-driven control of multipactor in high-power RF systems.

43 PARTICLE ACCELERATORS↗
NASA NTRS1992

Automating sky object classification in astronomical survey images

We describe the application of machine classification techniques to the development of an automated tool for the reduction of a large scientific data set. The 2nd Palomer Observatory Sky Survey is nearly completed. This survey provides comprehensive coverage of the northern celestial hemisphere in the form of photographic plates. The plates are being transformed into digitized images whose quality will probably not be surpassed in the next ten to twenty years. The images are expected to contain on the order of 10(exp 7) galaxies and 10(exp 8) stars. Astronomers wish to determine which of these sky objects belong to various classes of galaxies and stars. The size of this data set precludes manual analysis. Our approach is to develop a software system which integrates the functions of independently developed techniques for image processing and data classification. Digitized sky images are passed through image processing routines to identify sky objects and to extract a set of features for each object. These routines are used to help select a useful set of attributes for classifying sky objects. Then GID3* and O-BTree, two inductive learning techniques, learn classification decision trees from examples. These classifiers will be used to process the rest of the data. This paper gives an overview of the machine learning techniques used, describes the details of our specific application, and reports the initial encouraging results. The results indicate that our approach is well-suited to the problem. The primary benefits of the approach are increased data reduction throughput and consistency of classification. The classification rules which are the product of the inductive learning techniques will form an object, examinable basis for classifying sky objects. A final, not to be underestimated benefit is that astronomers will be freed from the tedium of an intensely visual task to pursue more challenging analysis and interpretation problems based on automatically cataloged data.

Fayyad, Usama M.↗
NASA NTRS1981

Contextual classification of multispectral image data: An unbiased estimator for the context distribution

A key input to a statistical classification algorithm, which exploits the tendency of certain ground cover classes to occur more frequently in some spatial context than in others, is a statistical characterization of the context: the context distribution. An unbiased estimator of the context distribution is discussed which, besides having the advantage of statistical unbiasedness, has the additional advantage over other estimation techniques of being amenable to an adaptive implementation in which the context distribution estimate varies according to local contextual information. Results from applying the unbiased estimator to the contextual classification of three real LANDSAT data sets are presented and contrasted with results from non-contextual classifications and from contextual classifications utilizing other context distribution estimation techniques.

Tilton, J. C.↗
NASA NTRS1995

Morphology classification of galaxies in CL 0939+4713 using a ground-based telescope image

Morphological classification is studied for galaxies in cluster CL 0939+4712 at z = 0.407 using simple photometric parameters obtained from a ground-based telescope image with seeing of 1-2 arcseconds full width at half maximim (FWHM). By ploting the galaxies in a plane of the concentration parameter versus mean surface brightness, we find a good correlation between the location on the plane and galaxy colors, which are known to correlate with morphological types from a recent Hubble Space Telescope (HST) study. Using the present method, we expect a success rate of classification into early and late types of about 70% or possibly more.

Fukugita, M.↗
NASA NTRS1982

Estimation of context for statistical classification of multispectral image data

Recent investigations have demonstrated the effectiveness of a contextual classifier that combines spatial and spectral information employing a general statistical approach. This statistical classification algorithm exploits the tendency of certain ground cover classes to occur more frequently in some spatial contexts than in others. Indeed, a key input to this algorithm is a statistical characterization of the context: the context function. An unbiased estimator of the context function is discussed which, besides having the advantage of statistical unbiasedness, has the additional advantage over other estimation techniques of being amenable to an adaptive implementation in which the context-function estimate varies according to local contextual information. Results from applying the unbiased estimator to the contextual classification of three real Landsat data sets are presented and contrasted with results from noncontextual classifications and from contextual classifications utilizing other context-function estimation techniques.

Tilton, J. C.↗
NASA NTRS1981

Contextual classification of multispectral image data - An unbiased estimator for the context distribution

Recent investigations have demonstrated the effectiveness of a contextual classifier that combines spatial and spectral information employing a general statistical approach. This statistical classification algorithm exploits the tendency of certain ground-cover classes to occur more frequently in some spatial contexts than in others. Indeed, a key input to this algorithm is a statistical characterization of the context: the context distribution. Here a discussion is given of an unbiased estimator of the context distribution which, besides having the advantage of statistical unbiasedness, has the additional advantage over other estimation techniques of being amenable to an adaptive implementation in which the context distribution estimate varies according to local contextual information. Results from applying the unbiased estimator to the contextual classification of three real Landsat data sets are presented and contrasted with results from noncontextual classifications and from contextual classifications utilizing other context distribution estimation techniques.

Tilton, J. C.↗
NASA NTRS1981

Comparison of wheat classification accuracy using different classifiers of the image-100 system

Classification results using single-cell and multi-cell signature acquisition options, a point-by-point Gaussian maximum-likelihood classifier, and K-means clustering of the Image-100 system are presented. Conclusions reached are that: a better indication of correct classification can be provided by using a test area which contains various cover types of the study area; classification accuracy should be evaluated considering both the percentages of correct classification and error of commission; supervised classification approaches are better than K-means clustering; Gaussian distribution maximum likelihood classifier is better than Single-cell and Multi-cell Signature Acquisition Options of the Image-100 system; and in order to obtain a high classification accuracy in a large and heterogeneous crop area, using Gaussian maximum-likelihood classifier, homogeneous spectral subclasses of the study crop should be created to derive training statistics.

Dejesusparada, N.↗
NASA NTRS1997

On the Implementation of a Land Cover Classification System for SAR Images Using Khoros

The Synthetic Aperture Radar (SAR) sensor is widely used to record data about the ground under all atmospheric conditions. The SAR acquired images have very good resolution which necessitates the development of a classification system that process the SAR images to extract useful information for different applications. In this work, a complete system for the land cover classification was designed and programmed using the Khoros, a data flow visual language environment, taking full advantages of the polymorphic data services that it provides. Image analysis was applied to SAR images to improve and automate the processes of recognition and classification of the different regions like mountains and lakes. Both unsupervised and supervised classification utilities were used. The unsupervised classification routines included the use of several Classification/Clustering algorithms like the K-means, ISO2, Weighted Minimum Distance, and the Localized Receptive Field (LRF) training/classifier. Different texture analysis approaches such as Invariant Moments, Fractal Dimension and Second Order statistics were implemented for supervised classification of the images. The results and conclusions for SAR image classification using the various unsupervised and supervised procedures are presented based on their accuracy and performance.

Medina Revera, Edwin J.↗
NASA NTRS1981

Digital image data sets for remote sensing instruction

Several sets of LANDSAT image segments and a set of simple image processing programs operating in batch mode are being used to teach an introductory course in digital image analysis and classification. The image data sets contain only a small number of pixels and can be run quickly on most university computing systems. A number of image data sets derived from the raw spectral bands (smoothed data sets, band ratios and texture data sets) allows the student to examine and include these extracted variables in the classification process. Another data set consists of three registered LANDSAT image segments for three different dates so that the student may experiment with multitemporal data processing. The three LANDSAT scenes used in the class are described and the image data sets available for class exercises are listed.

Eyton, J. R.↗
NASA NTRS1981

A comparison of unsupervised classification procedures on LANDSAT MSS data for an area of complex surface conditions in Basilicata, Southern Italy

Two unsupervised classification procedures were applied to ratioed and unratioed LANDSAT multispectral scanner data of an area of spatially complex vegetation and terrain. An objective accuracy assessment was undertaken on each classification and comparison was made of the classification accuracies. The two unsupervised procedures use the same clustering algorithm. By on procedure the entire area is clustered and by the other a representative sample of the area is clustered and the resulting statistics are extrapolated to the remaining area using a maximum likelihood classifier. Explanation is given of the major steps in the classification procedures including image preprocessing; classification; interpretation of cluster classes; and accuracy assessment. Of the four classifications undertaken, the monocluster block approach on the unratioed data gave the highest accuracy of 80% for five coarse cover classes. This accuracy was increased to 84% by applying a 3 x 3 contextual filter to the classified image. A detailed description and partial explanation is provided for the major misclassification. The classification of the unratioed data produced higher percentage accuracies than for the ratioed data and the monocluster block approach gave higher accuracies than clustering the entire area. The moncluster block approach was additionally the most economical in terms of computing time.

Justice, C.↗
NASA NTRS1991

Human Expertise Helps Computer Classify Images

Two-domain method of computational classification of images requires less computation than other methods for computational recognition, matching, or classification of images or patterns. Does not require explicit computational matching of features, and incorporates human expertise without requiring translation of mental processes of classification into language comprehensible to computer. Conceived to "train" computer to analyze photomicrographs of microscope-slide specimens of leucocytes from human peripheral blood to distinguish between specimens from healthy and specimens from traumatized patients.

Rorvig, Mark E.↗
DOE OSTI2026

Spectrometer-free quantitative vapor sensing and classification via spatiotemporal imaging of porous silicon metasurfaces

Metasurfaces offer a compact platform for optical vapor sensing, but their practical deployment has been limited by weak evanescent light–matter interactions and reliance on spectrally resolved instrumentation. Here, we report porous silicon (pSi) metasurfaces for spectrometer-free quantitative detection of volatile organic compounds (VOCs) with strongly enhanced light–matter interaction. The engineered porosity increases sensitivity by >100× relative to non-porous dielectric metasurfaces, enabling limits of detection of 1.65 ppm for methanol and 9.1 ppm for ethanol across a broad dynamic range (<10 ppm to >103 ppm). Imaging-based readout provides a lightweight, spectrometer-free pathway for real-time quantitative sensing. Beyond quantitative detection, the mesoporous architecture introduces adsorption–desorption kinetics as an additional information channel. Analysis of the resulting spatiotemporal signatures enables kinetic fingerprinting without reliance on infrared spectral features or surface functionalization, and a lightweight machine-learning classifier differentiates acetone, methanol, ethanol, and isopropanol with 91.6% accuracy. These results establish porous metasurfaces as spatiotemporal sensing elements that couple quantitative vapor detection with kinetic fingerprinting through real-time dynamical responses, enabling low-cost, high-performance optical sensors.

Dash, Tomoshree [Clemson University]↗