SEARCH · Engineering Papers

Results for “image recognition”

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 667 records · Page 37

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Forecast of Wildfire Potential Across California USA Using a Transformer

Wildfires are a major issue facing the United States, a matter further exacerbated by an ever-changing climate. In California alone, wildfires are responsible for billions of dollars in damages and take lives each year. Accurately predicting fire danger conditions allows preparation awareness before wildfires start. Transformers are a class of deep learning models designed to identify patterns in sequential datasets. In recent years, transformers have gained popularity through their impressive performance in natural language processing and other applications of signal recognition. This analysis demonstrates the ability of a transformer with a residual connection to forecast fire danger potential over the state of California. Wildland fire potential index (WFPI) maps collected from the US Geological Survey database from January 1st 2020 to December 31st 2023 were used to tune, train and evaluate the transformer. Meteorological inputs (provided by Daymet daily weather and climatological summaries), the normalized difference vegetation index (NDVI) (calculated from the Moderate Resolution Imaging Spectroradiometer (MODIS)), and outputs from the Scott and Burgman fire behavior fuel models (to characterize maps of fuel types), were used as inputs. Our results show that a transformer can effectively emulate the US Forest Service modeled WFPI maps of California USA for four week long forecasts over the month of July, 2023, with correlations ranging from 0.85 – 0.98.

Limber, Russell [ORNL]↗

NASA NTRS1990

Connectivity strategies for higher-order neural networks applied to pattern recognition

Different strategies for non-fully connected HONNs (higher-order neural networks) are discussed, showing that by using such strategies an input field of 128 x 128 pixels can be attained while still achieving in-plane rotation and translation-invariant recognition. These techniques allow HONNs to be used with the larger input scenes required for practical pattern-recognition applications. The number of interconnections that must be stored has been reduced by a factor of approximately 200,000 in a T/C case and about 2000 in a Space Shuttle/F-18 case by using regional connectivity. Third-order networks have been simulated using several connection strategies. The method found to work best is regional connectivity. The main advantages of this strategy are the following: (1) it considers features of various scales within the image and thus gets a better sample of what the image looks like; (2) it is invariant to shape-preserving geometric transformations, such as translation and rotation; (3) the connections are predetermined so that no extra computations are necessary during run time; and (4) it does not require any extra storage for recording which connections were formed.

Spirkovska, Lilly↗

NASA NTRS2015

International Space Station Earth Observations Working Group

The multilateral Earth Observations Working Group (EOWG) was chartered in May 2012 in order to improve coordination and collaboration of Earth observing payloads, research, and applications on the International Space Station (ISS). The EOWG derives its authority from the ISS Program Science Forum, and a NASA representative serves as a permanent co-chair. A rotating co-chair position can be occupied by any of the international partners, following concurrence by the other partners; a JAXA representative is the current co-chair. Primary functions of the EOWG include, 1) the exchange of information on plans for payloads, from science and application objectives to instrument development, data collection, distribution and research; 2) recognition and facilitation of opportunities for international collaboration in order to optimize benefits from different instruments; and 3) provide a formal ISS Program interface for collection and application of remotely sensed data collected in response to natural disasters through the International Charter, Space and Major Disasters. Recent examples of EOWG activities include coordination of bilateral data sharing protocols between NASA and TsNIIMash for use of crew time and instruments in support of ATV5 reentry imaging activities; discussion of continued use and support of the Nightpod camera mount system by NASA and ESA; and review and revision of international partner contributions on Earth observations to the ISS Program Benefits to Humanity publication.

Stefanov, William L.↗

NASA NTRS1970

Image resolution: Its significance in a wildland area

The information content of simulated space photos as a function of various levels of image resolution was determined by identifying major vegetation-terrain types in a series of images purposely degraded optically to different levels of ground resolution resolvable distance. Comparison of cumulative interpretation results with actual ground truth data indicates that although there is definite decrease in interpretability as ground resolvable distance increases, some valuable information is gained by using even the poorest aerial photography. Developed is the importance of shape and texture for correct identification of broadleaf or coniferous vegetation types and the relative unimportance of shape and texture for the recognition of grassland, water bodies, and nonvegetated areas. Imagery must have a ground resolvable distance of at least 50 feet to correctly discriminate between primary types of woody vegetation.

Lauer, D. T.↗

NASA NTRS1989

The perception of geometrical structure from congruence

The principle function of vision is to measure the environment. As demonstrated by the coordination of motor actions with the positions and trajectories of moving objects in cluttered environments and by rapid recognition of solid objects in varying contexts from changing perspectives, vision provides real-time information about the geometrical structure and location of environmental objects and events. The geometric information provided by 2-D spatial displays is examined. It is proposed that the geometry of this information is best understood not within the traditional framework of perspective trigonometry, but in terms of the structure of qualitative relations defined by congruences among intrinsic geometric relations in images of surfaces. The basic concepts of this geometrical theory are outlined.

Lappin, Joseph S.↗

DOE OSTI2025

Electromagnetic shower reconstruction in the ICARUS liquid argon time projection chamber detector

The ICARUS-T600 liquid argon time projection chamber (LArTPC) detector is taking data at shallow depth as the far detector of the Short Baseline Neutrino (SBN) program at Fermilab, to search for a possible sterile neutrino signal at $\Delta m^{2} \approx 1~\text{eV}^{2}$ with the Booster (BNB) and Main Injector (NuMI) neutrino beams at $\GeV{\sim 0.8}$ and $\GeV{\sim 2}$ average energies respectively. The LArTPC technology, developed by the ICARUS collaboration and now a standard in neutrino physics, offers impressive charged-particle imaging capabilities with $\sim1 \ \text{mm}$ spatial resolution, enabling efficient discrimination between track-like signatures (e.g., from muons, pions, and protons) and electromagnetic showers (from electrons and photons). Moreover, electron and photon signatures can be distinguished both with the calorimetric measurement of local energy depositions at the shower start and with the cm-scale conversion gap signature of photons. This contribution discusses event reconstruction at ICARUS focusing on Pandora, a multi-algorithm pattern recognition software widely used in LArTPC experiments. Over a hundred Pandora algorithms and tools are used to reconstruct cosmic rays and neutrino interactions in the ICARUS detector. Recent developments have focused on the reconstruction of electromagnetic shower signatures, crucial to ensure a robust and efficient reconstruction of charged-current $\nu_e$ interactions, which serve as a key signature of sterile neutrino oscillations at SBN. In this contribution, recent improvements to the reconstruction are discussed, focusing on the discrimination between tracks and electromagnetic showers using neutrino simulations and data.

Triozzi, Riccardo [Padua U.; INFN, Padua] (ORCID:0↗

DOE OSTI2025

Using Eye Tracking to Elucidate the Mechanisms Underlying Stimulation-Enhanced Visual Target Detection

Transcranial direct current stimulation (tDCS) is a noninvasive form of brain stimulation that involves passing a weak electrical current between electrodes on the scalp to modulate underlying neural tissue. TDCS has been shown to modulate cognition in a variety of domains, including memory, attention, and visual processing. Prior work from our laboratory has shown positive effects of tDCS on learning to detect target objects hidden in complex naturalistic visual scenes and learn rules for categorizing images, though the mechanism for these benefits remains unknown. One possibility is that tDCS optimizes visual search by modulating visual attention or via the reduction in search errors. One method of quantifying visual attention is to use eye tracking to record search patterns to determine if and how visual search is adjusted under verum stimulation conditions. Eye tracking data allows classification of errors into error types, including sampling errors (failing to look in the relevant region), recognition errors (looking at the critical portion of a scene, but failing to recognize it as such as evidenced by visual fixation), and decision-making errors (fixating on the relevant portion of a scene, but making the wrong determination). Our results indicate that the benefit tDCS confers on visual search for targets stems from the reduction in decision-making errors when targets are present (Cohen’s d = 0.86). Also reported is a replication of previous findings showing a tDCS-dependent improvement in learning this task, learning score (Cohen’s d = 0.88); d’ (Cohen’s d = 1.00). This provides support for moving tDCS into the application space by pairing it with analysts who are concerned with the type of search error that is corrected via stimulation.

attention↗

NASA NTRS1973

Geologic and mineral and water resources investigations in western Colorado using ERTS-1 data

The author has identified the following significant results. Geologic interpretation of ERTS-1 imagery is dependent on recognition of the distribution, continuity, trend, and geometry of key surface features. In the examination of ERTS-1 imagery, lithology must be interpreted largely from the geomorphic expression of the terrain. ERTS-1 imagery is extremely useful in detecting local structures. Most mapped structures are topographically-expressed. Consequently, ERTS-1 imagery acquired during mid-winter, when the solar illumination angle is low, provides the largest amount of structural information. Stereoscopic analyses of ERTS-1 images significantly aid geologic interpretation. Positive transparencies of ERTS-1 images (1:1,000,000) commonly contain more geologic information than can be adequately annotated during geologic interpretation.

Knepper, D. H., Jr.↗

NASA NTRS2010

Algorithms for Learning Preferences for Sets of Objects

A method is being developed that provides for an artificial-intelligence system to learn a user's preferences for sets of objects and to thereafter automatically select subsets of objects according to those preferences. The method was originally intended to enable automated selection, from among large sets of images acquired by instruments aboard spacecraft, of image subsets considered to be scientifically valuable enough to justify use of limited communication resources for transmission to Earth. The method is also applicable to other sets of objects: examples of sets of objects considered in the development of the method include food menus, radio-station music playlists, and assortments of colored blocks for creating mosaics. The method does not require the user to perform the often-difficult task of quantitatively specifying preferences; instead, the user provides examples of preferred sets of objects. This method goes beyond related prior artificial-intelligence methods for learning which individual items are preferred by the user: this method supports a concept of setbased preferences, which include not only preferences for individual items but also preferences regarding types and degrees of diversity of items in a set. Consideration of diversity in this method involves recognition that members of a set may interact with each other in the sense that when considered together, they may be regarded as being complementary, redundant, or incompatible to various degrees. The effects of such interactions are loosely summarized in the term portfolio effect. The learning method relies on a preference representation language, denoted DD-PREF, to express set-based preferences. In DD-PREF, a preference is represented by a tuple that includes quality (depth) functions to estimate how desired a specific value is, weights for each feature preference, the desired diversity of feature values, and the relative importance of diversity versus depth. The system applies statistical concepts to estimate quantitative measures of the user s preferences from training examples (preferred subsets) specified by the user. Once preferences have been learned, the system uses those preferences to select preferred subsets from new sets. The method was found to be viable when tested in computational experiments on menus, music playlists, and rover images. Contemplated future development efforts include further tests on more diverse sets and development of a sub-method for (a) estimating the parameter that represents the relative importance of diversity versus depth, and (b) incorporating background knowledge about the nature of quality functions, which are special functions that specify depth preferences for features.

Wagstaff, Kiri L.↗

NASA NTRS2006

Grayscale Optical Correlator Workbench

Grayscale Optical Correlator Workbench (GOCWB) is a computer program for use in automatic target recognition (ATR). GOCWB performs ATR with an accurate simulation of a hardware grayscale optical correlator (GOC). This simulation is performed to test filters that are created in GOCWB. Thus, GOCWB can be used as a stand-alone ATR software tool or in combination with GOC hardware for building (target training), testing, and optimization of filters. The software is divided into three main parts, denoted filter, testing, and training. The training part is used for assembling training images as input to a filter. The filter part is used for combining training images into a filter and optimizing that filter. The testing part is used for testing new filters and for general simulation of GOC output. The current version of GOCWB relies on the mathematical software tools from MATLAB binaries for performing matrix operations and fast Fourier transforms. Optimization of filters is based on an algorithm, known as OT-MACH, in which variables specified by the user are parameterized and the best filter is selected on the basis of an average result for correct identification of targets in multiple test images.

Hanan, Jay↗

DOE OSTI2025

Quantum Transfer Learning to Boost Dementia Detection

Dementia is a devastating condition with profound implications for individuals, families, and healthcare systems. Early and accurate detection of dementia is critical for timely intervention and improved patient outcomes. While classical machine learning and deep learning approaches have been explored extensively for dementia prediction, these solutions often struggle with high-dimensional biomedical data and large-scale datasets, quickly reaching computational and performance limitations. To address this challenge, quantum machine learning (QML) has emerged as a promising paradigm, offering faster training and advanced pattern recognition capabilities. This work aims to demonstrate the potential of quantum transfer learning (QTL) to enhance the performance of a weak classical deep learning model applied to a binary classification task for dementia detection. Besides, we show the effect of noise on the QTL-based approach, investigating the reliability and robustness of this method. Using the OASIS 2 dataset, we show how quantum techniques can transform a suboptimal classical model into a more effective solution for biomedical image classification, highlighting their potential impact on advancing healthcare technology.

Bhowmik, Sounak [University of Tennessee, Knoxvill↗

NASA NTRS1992

High-resolution space-shuttle polarimetry for farm crop classification

A significant advance is reported in imaging the polarimetry of a terrestrial area of earth located along the Mississippi River near New Madrid, Missouri. Color imagery was obtained with twin Hasselblad cameras with mutually perpendicular polarization analyzers. Digitization of the imagery in three colors (red, green, and blue) was accomplished at the Johnson Space Center Video Digital Analysis System Laboratory, Houston, Texas. A ground resolution of 80-90 m was achieved in the high-resolution imagery. Percent polarization was superior to photometry for recognition and characterization of farm crops such as rice, milo, cotton, and soybeans and of fallow areas. Statistical analyses of the percent-polarization data permit a unique classification of crops. Atmospheric effects may be deduced. Space-shuttle window distortion and viewing angle-sun geometry must be taken into account in analyzing the data.

Egan, Walter G.↗

NASA NTRS1989

Machine parts recognition using a trinary associative memory

The convergence mechanism of vectors in Hopfield's neural network in relation to recognition of partially known patterns is studied in terms of both inner products and Hamming distance. It has been shown that Hamming distance should not always be used in determining the convergence of vectors. Instead, inner product weighting coefficients play a more dominant role in certain data representations for determining the convergence mechanism. A trinary neuron representation for associative memory is found to be more effective for associative recall. Applications of the trinary associative memory to reconstruct machine part images that are partially missing are demonstrated by means of computer simulation as examples of the usefulness of this approach.

Awwal, Abdul Ahad S.↗

NASA NTRS2012

The International Space Station: New Capabilities for Disaster Response and Humanitarian Aid

The International Space Station (ISS) has been acquiring Earth imagery since 2000, primarily in the form of astronaut photography using hand-held film and digital cameras. Recent additions of more sophisticated multispectral and hyperspectral sensor systems have expanded both the capabilities and relevance of the ISS to basic research, applied Earth science, and development of new sensor technologies. Funding opportunities established within NASA, the US National Laboratories and the international partner organizations have generated instrument proposals that will further enhance these capabilities. With both internal and external sensor location options, and the availability of both automated and human-tended operational environments, the ISS is a unique platform within the constellation of Earth-observing satellites currently in orbit. Current progress and challenges associated with development of ISS terrestrial remote sensing capabilities in the area of disaster response and support of relief efforts will be presented. The ISS orbit allows for imaging of the Earth's surface at varying times of day and night, providing opportunities for data collection over approximately 95% of the populated regions. These opportunities are distinct from--yet augment--the data collection windows for the majority of sensors on polar-orbiting satellites. In addition to this potential for "being in the right place at the right time" to collect critical information on an evolving disaster, the presence of a human crew also allows for immediate recognition of an event from orbit, notification of relevant organizations on the ground, and re-tasking of available remote sensing resources to support humanitarian response and relief efforts. Challenges to establishing an integrated response capability are both technical (coordination of sensor targeting and data collection, rapid downlink and posting of data to a central accessible hub, timely generation and distribution of relevant data products) and operational (notification and engagement of sensor support teams, international partner agency sanction of astronaut support activities). To better collaborate on common issues and strengthen applications, including using the data to support disaster response, we established an ISS Program Science Forum Working Group for Earth Observations comprised of representatives from the international partner agencies. This international forum welcomes input and support from relevant United Nations task groups regarding our disaster response and humanitarian aid to enable development of the ISS capabilities in this area for greatest value to the international community.

Stefanov, William↗

DOE OSTI2024

Self-Supervised Cloud Classification

Abstract Low-level marine clouds play a pivotal role in Earth’s weather and climate through their interactions with radiation, heat and moisture transport, and the hydrological cycle. These interactions depend on a range of dynamical and microphysical processes that result in a broad diversity of cloud types and spatial structures, and a comprehensive understanding of cloud morphology is critical for continued improvement of our atmospheric modeling and prediction capabilities moving forward. Deep learning has recently accelerated our ability to study clouds using satellite remote sensing, and machine learning classifiers have enabled detailed studies of cloud morphology. A major limitation of deep learning approaches to this problem, however, is the large number of hand-labeled samples that are required for training. This work applies a recently developed self-supervised learning scheme to train a deep convolutional neural network (CNN) to map marine cloud imagery to vector embeddings that capture information about mesoscale cloud morphology and can be used for satellite image classification. The model is evaluated against existing cloud classification datasets and several use cases are demonstrated, including training cloud classifiers with very few labeled samples, interrogation of the CNN’s learned internal feature representations, cross-instrument application, and resilience against sensor calibration drift and changing scene brightness. The self-supervised approach learns meaningful internal representations of cloud structures and achieves comparable classification accuracy to supervised deep learning methods without the expense of creating large hand-annotated training datasets. Significance Statement Marine clouds heavily influence Earth’s weather and climate, and improved understanding of marine clouds is required to improve our atmospheric modeling capabilities and physical understanding of the atmosphere. Recently, deep learning has emerged as a powerful research tool that can be used to identify and study specific marine cloud types in the vast number of images collected by Earth-observing satellites. While powerful, these approaches require hand-labeling of training data, which is prohibitively time intensive. This study evaluates a recently developed self-supervised deep learning method that does not require human-labeled training data for processing images of clouds. We show that the trained algorithm performs competitively with algorithms trained on hand-labeled data for image classification tasks. We also discuss potential downstream uses and demonstrate some exciting features of the approach including application to multiple satellite instruments, resilience against changing image brightness, and its learned internal representations of cloud types. The self-supervised technique removes one of the major hurdles for applying deep learning to very large atmospheric datasets.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS1990

Experiments in model-based matching using a relational pyramid representation

The relational pyramid representation is a hierarchical relational description of an object that can be used in recognition and pose estimation. In this representation, primitive features appear at the bottom of the pyramid, relations among primitives appear at level one, and, in general, relations among lower-level structures appear at the levels above the levels in which these structures were defined. A pose-estimation system is constructed that uses the relational pyramid representation for the view classes of a 3D object and for the description of the unknown view of an object extracted from an image. A previously described system uses summary information to rank and select view classes to which the unknown view is compared. This paper describes a best-first search procedure to find correspondences between the selected view class pyramid and the image pyramid.

Chu, Nancy T.↗

NASA NTRS1989

A knowledge-based machine vision system for space station automation

A simple knowledge-based approach to the recognition of objects in man-made scenes is being developed. Specifically, the system under development is a proposed enhancement to a robot arm for use in the space station laboratory module. The system will take a request from a user to find a specific object, and locate that object by using its camera input and information from a knowledge base describing the scene layout and attributes of the object types included in the scene. In order to use realistic test images in developing the system, researchers are using photographs of actual NASA simulator panels, which provide similar types of scenes to those expected in the space station environment. Figure 1 shows one of these photographs. In traditional approaches to image analysis, the image is transformed step by step into a symbolic representation of the scene. Often the first steps of the transformation are done without any reference to knowledge of the scene or objects. Segmentation of an image into regions generally produces a counterintuitive result in which regions do not correspond to objects in the image. After segmentation, a merging procedure attempts to group regions into meaningful units that will more nearly correspond to objects. Here, researchers avoid segmenting the image as a whole, and instead use a knowledge-directed approach to locate objects in the scene. The knowledge-based approach to scene analysis is described and the categories of knowledge used in the system are discussed.

Chipman, Laure J.↗

NASA NTRS2002

Classification image weights and internal noise level estimation

For the linear discrimination of two stimuli in white Gaussian noise in the presence of internal noise, a method is described for estimating linear classification weights from the sum of noise images segregated by stimulus and response. The recommended method for combining the two response images for the same stimulus is to difference the average images. Weights are derived for combining images over stimuli and observers. Methods for estimating the level of internal noise are described with emphasis on the case of repeated presentations of the same noise sample. Simple tests for particular hypotheses about the weights are shown based on observer agreement with a noiseless version of the hypothesis.

Pattern Recognition, Visual/physiology↗