SEARCH · Search NASA

Results for “Computer Vision”

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 739 records · Page 41

All sources NASA NTRS DOE OSTI

NASA NTRS2003

Synthetic Vision Enhances Situation Awareness and RNP Capabilities for Terrain-Challenged Approaches

The Synthetic Vision Systems (SVS) Project of Aviation Safety Program is striving to eliminate poor visibility as a causal factor in aircraft accidents as well as enhance operational capabilities of all aircraft through the display of computer generated imagery derived from an onboard database of terrain, obstacle, and airport information. To achieve these objectives, NASA 757 flight test research was conducted at the Eagle-Vail, Colorado airport to evaluate three SVS display types (Head-Up Display, Head-Down Size A, Head-Down Size X) and two terrain texture methods (photo-realistic, generic) in comparison to the simulated Baseline Boeing-757 Electronic Attitude Direction Indicator and Navigation / Terrain Awareness and Warning System displays. These independent variables were evaluated for situation awareness, path error, and workload while making approaches to Runway 25 and 07 and during simulated engine-out Cottonwood 2 and KREMM departures. The results of the experiment showed significantly improved situation awareness, performance, and workload for SVS concepts compared to the Baseline displays and confirmed the retrofit capability of the Head-Up Display and Size A SVS concepts. The research also demonstrated that the pathway and pursuit guidance used within the SVS concepts achieved required navigation performance (RNP) criteria.

Kramer, Lynda J.↗

NASA NTRS2004

Dynamic visual acuity using "far" and "near" targets

CONCLUSIONS: DVA may be useful for assessing the functional consequences of an impaired gaze stabilization mechanism or for testing the effectiveness of a rehabilitation paradigm. Because target distance influences the relative contributions of canal and otolith inputs, the ability to measure DVA at near and far viewing distances may also lead to tests that will independently assess canal and otolith function. OBJECTIVE: To present and test a methodology that uses dynamic visual acuity (DVA) to assess the efficacy of compensatory gaze mechanisms during a functionally relevant activity that differentially measures canal and otolith function. MATERIAL AND METHODS: The effect of treadmill walking at a velocity of 1.79 m/s on subjects' visual acuity was assessed at each of two viewing distances. A custom-written threshold determination program was used to display Landolt C optotypes on a laptop computer screen during a "far" (4 m) target condition and on a micro-display for a "near" (50 cm) target condition. The walking acuity scores for each target distance were normalized by subtracting a corresponding acuity measure obtained while standing still on the treadmill belt. RESULTS: As predicted by subjective reports of relative target motion, the decrease in visual acuity was significantly greater (p < 0.00001) for the near compared to the far condition.

Pattern Recognition, Visual/physiology↗

NASA NTRS1995

Vestibular plasticity following orbital spaceflight: recovery from postflight postural instability

Results of previous studies suggested that the vestibular mediated postural instability observed in astronauts upon return to earth from orbital spaceflight may be exacerbated by an increased weighting of visual inputs for spatial orientation and control of movement. This study was performed to better understand the roles of visual and somatosensory contributions to recovery of normal sensori-motor postural control in returning astronauts. Preflight and postflight, 23 astronaut volunteers were presented randomly with three trials of six sensory organization test (SOT) conditions in the EquiTest system test battery. Sagittal plane center-of-gravity (COG) excursions computed from ground reaction forces were significantly higher on landing day than preflight for those test conditions presenting sway-referenced visual and/or somatosensory orientation cues. The ratio of summed peak-to-peak COG sway amplitudes on the two sway-referenced vision tests (SOTs 3 + 6) compared to the two eyes closed tests (SOTs 2 + 5) was increased on landing day, indicating an increased reliance on visual orientation cues for postural control. The ratio of peak-to-peak COG excursions on sway-referenced surfaces (SOTs 4, 5 & 6) to an earth fixed support surfaces (SOTs 1, 2 & 3) increased even more after landing suggesting primary reliance on somatosensory orientation cues for recovery of postflight postural stability. Readaptation to sway-referenced support surfaces took longer than readaptation to sway-referenced vision. The increased reliance on visual and somatosensory inputs disappeared in all astronauts 4-8 days following return to earth.

NASA Program Space Physiology and Countermeasures↗

NASA NTRS2011

A Vision of Quantitative Imaging Technology for Validation of Advanced Flight Technologies

Flight-testing is traditionally an expensive but critical element in the development and ultimate validation and certification of technologies destined for future operational capabilities. Measurements obtained in relevant flight environments also provide unique opportunities to observe flow phenomenon that are often beyond the capabilities of ground testing facilities and computational tools to simulate or duplicate. However, the challenges of minimizing vehicle weight and internal complexity as well as instrumentation bandwidth limitations often restrict the ability to make high-density, in-situ measurements with discrete sensors. Remote imaging offers a potential opportunity to noninvasively obtain such flight data in a complementary fashion. The NASA Hypersonic Thermodynamic Infrared Measurements Project has demonstrated such a capability to obtain calibrated thermal imagery on a hypersonic vehicle in flight. Through the application of existing and accessible technologies, the acreage surface temperature of the Shuttle lower surface was measured during reentry. Future hypersonic cruise vehicles, launcher configurations and reentry vehicles will, however, challenge current remote imaging capability. As NASA embarks on the design and deployment of a new Space Launch System architecture for access beyond earth orbit (and the commercial sector focused on low earth orbit), an opportunity exists to implement an imagery system and its supporting infrastructure that provides sufficient flexibility to incorporate changing technology to address the future needs of the flight test community. A long term vision is offered that supports the application of advanced multi-waveband sensing technology to aid in the development of future aerospace systems and critical technologies to enable highly responsive vehicle operations across the aerospace continuum, spanning launch, reusable space access and global reach. Motivations for development of an Agency level imagery-based measurement capability to support cross cutting applications that span the Agency mission directorates as well as meeting potential needs of the commercial sector and national interests of the Intelligence, Surveillance and Reconnaissance community are explored. A recommendation is made for an assessment study to baseline current imaging technology including the identification of future mission requirements. Development of requirements fostered by the applications suggested in this paper would be used to identify technology gaps and direct roadmapping for implementation of an affordable and sustainable next generation sensor/platform system.

Horvath, Thomas J.↗

DOE OSTI2025

Automated Fire Detection for Industrial Settings with Pretrained Convolutional Networks

Early fire detection in industrial environments is critical to preventing equipment damage, personal injury, and operational disruptions. Traditional smoke detectors, while effective, often experience delays due to the time required for smoke to reach sensors, allowing fires to spread. Manual fire watch operations and human surveillance of camera feeds are resource-intensive and prone to human error. To address these challenges, this paper explores the application of convolutional neural networks for automated fire detection, specifically in industrial settings. By leveraging 11 different pre-trained machine vision models from TensorFlow and enhancing them with transfer learning on a custom-built industrial fire dataset, we optimized fire detection performance. Here, we analyzed each machine vision model architecture in terms of its depth, width, and input image resolution, considering both resource requirements and detection accuracy. We further explored the option of combining multiple models into an ensemble classifier to evaluate whether the performance improvements could justify the much greater computational complexity and other practical impacts. A cost-benefit analysis is presented to evaluate the trade-offs between performance and computational expense. Our findings identify that EfficientNetV2L, specifically tailored for industrial applications, provides the optimal balance between costs involved in training and using the model versus the overall fire detection performance. Additionally, we present a qualitative analysis of model performance using the technique of gradient-based class activation mapping to provide explainability by visualizing model decisions.

artificial intelligence↗

DOE OSTI2026

Toward memory-efficient melt pool monitoring: a classification framework using event-based imaging and sparse sensing technique

Vision sensors like CMOS and CCD cameras are often used for in-process monitoring of melt pools in laser-based additive and welding processes, but they require transferring large amounts of data and computational processing resources. Event-based neuromorphic imagery, on the other hand, detects only the change in pixel intensity, thus potentially reducing the data amount and latency. With an event imager, this study develops a framework for melt pool condition classification, including image construction, time scale selection, optimal pixel selection, and sparse classification, to achieve a highly memory-efficient scheme. These are based on sparse sensing techniques with singular value decomposition (SVD) and QR pivoting, the two fundamental matrix transformations for linear dimensionality reduction. The framework is then validated by classifying a controlled experiment by exciting various mode shapes of liquid gallium pools of varying depths (3, 6, and 8 mm). At 200 pixels, the classifier can reach overall accuracy of 75%, while at 2000 pixels (0.013% of the total possible pixels), the accuracy is nearly 90% (89.86%). At the same number of pixels, random selection can only achieve 46% and 67%, respectively. The memory savings of the sparsely sampled event data compared to a conventional imager is about 500 times. In addition to performance, implementation and limitations of the framework are also discussed.

42 ENGINEERING↗

DOE OSTI2026

Foundation models for atomistic simulation of chemistry and materials

Conventional computational methods for modeling chemical and materials systems are limited by system size and timescale, forcing a trade-off between quantum-mechanical accuracy and the sampling needed for realistic observables. Large language and vision foundation models — pre-trained on massive datasets using transformer architectures — have revolutionized many fields. It is thus interesting to ask whether a foundation model — subject to suitable data, parameter scaling and training — could enable learned simulations of chemistry and materials. Here, in this study, we review the field of machine-learned interatomic potentials (MLIPs) and posit that scaling up large and diverse chemical and materials datasets and highly expressive architectures using advanced training strategies should result in models that are: more efficient, transferable, robust to out-of-distribution scenarios, and easier to fine-tune to a variety of downstream physical observables than models trained from scratch on small datasets corresponding to specific, targeted atomistic simulation tasks. We provide specific criteria for creating such large-scale MLIP foundation models, coordinated strategies for their development, evaluation and deployment, and highlight potential emergent capabilities that could transform predictive simulations in chemistry and materials science and accelerate discovery across multiple technological domains.

Yuan, Eric C.-Y. [University of California, Berkel↗

DOE OSTI2024

Workflow Provenance in the Computing Continuum for Responsible, Trustworthy, and Energy-Efficient AI

As Artificial Intelligence (AI) becomes more pervasive in our society, it is crucial to develop, deploy, and assess Responsible and Trustworthy AI (RTAI) models, i.e., those that consider not only accuracy but also other aspects, such as explainability, fairness, and energy efficiency. Workflow provenance data have historically enabled critical capabilities towards RTAI. Provenance data derivation paths contribute to responsible workflows through transparency in tracking artifacts and resource consumption. Provenance data are well-known for their trustworthiness helping explainability, reproducibility, and accountability. However, there are complex challenges to achieve RTAI, which are further complicated by the heterogeneous infrastructure in the computing continuum (Edge-Cloud-HPC) used to develop and deploy models. As a result, a significant research and development gap remains between workflow provenance data management and RTAI. In this paper, we present a vision of the pivotal role of workflow provenance in supporting RTAI and discuss related challenges. We present a schematic view between RTAI and provenance, and highlight open research directions.

Santos Souza, Renan↗

NASA NTRS1987

Real-time model-based vision system for object acquisition and tracking

A machine vision system is described which is designed to acquire and track polyhedral objects moving and rotating in space by means of two or more cameras, programmable image-processing hardware, and a general-purpose computer for high-level functions. The image-processing hardware is capable of performing a large variety of operations on images and on image-like arrays of data. Acquisition utilizes image locations and velocities of the features extracted by the image-processing hardware to determine the three-dimensional position, orientation, velocity, and angular velocity of the object. Tracking correlates edges detected in the current image with edge locations predicted from an internal model of the object and its motion, continually updating velocity information to predict where edges should appear in future frames. With some 10 frames processed per second, real-time tracking is possible.

Wilcox, Brian↗

NASA NTRS1990

Programmable Remapper

Input image remapped rapidly and accurately onto different coordinate grid. Analog/digital electronic image-processing system developed to warp input images onto arbitrary coordinate grids at video rates. Advantages of system include antialiasing effect of many-to-one data path and speed of lookup-table operation. Lookup tables reprogrammed easily with help of computer that generates table values from mathematical description of desired transformation. Applications include real-time corrections of distortions in input optics of image sensors, corrections for repeatable nonlinear scanning, and aiding persons of impaired vision by deliberately distorting images onto remaining functional portions of retinas.

Juday, Richard D.↗

NASA NTRS1989

Human performance models for computer-aided engineering

This report discusses a topic important to the field of computational human factors: models of human performance and their use in computer-based engineering facilities for the design of complex systems. It focuses on a particular human factors design problem -- the design of cockpit systems for advanced helicopters -- and on a particular aspect of human performance -- vision and related cognitive functions. By focusing in this way, the authors were able to address the selected topics in some depth and develop findings and recommendations that they believe have application to many other aspects of human performance and to other design domains.

Elkind, Jerome I.↗

NASA NTRS1996

Implementation of a Campuswide Distributed Mass Storage Service: the Dream Versus Reality

In 1990, a technical team at NASA Lewis Research Center, Cleveland, Ohio, began defining a Mass Storage Service to pro- wide long-term archival storage, short-term storage for very large files, distributed Network File System access, and backup services for critical data dw resides on workstations and personal computers. Because of software availability and budgets, the total service was phased in over dm years. During the process of building the service from the commercial technologies available, our Mass Storage Team refined the original vision and learned from the problems and mistakes that occurred. We also enhanced some technologies to better meet the needs of users and system administrators. This report describes our team's journey from dream to reality, outlines some of the problem areas that still exist, and suggests some solutions.

Prahst, Stephen↗

NASA NTRS2006

Implementing the President's Vision: JPL and NASA's Exploration Systems Mission Directorate

As part of the NASA team the Jet Propulsion Laboratory is involved in the Exploration Systems Mission Directorate (ESMD) work to implement the President's Vision for Space exploration. In this slide presentation the roles that are assigned to the various NASA centers to implement the vision are reviewed. The plan for JPL is to use the Constellation program to advance the combination of science an Constellation program objectives. JPL's current participation is to contribute systems engineering support, Command, Control, Computing and Information (C3I) architecture, Crew Exploration Vehicle, (CEV) Thermal Protection System (TPS) project support/CEV landing assist support, Ground support systems support at JSC and KSC, Exploration Communication and Navigation System (ECANS), Flight prototypes for cabin atmosphere instruments

Industry Day↗

NASA NTRS2011

Implementation of Pin Point Landing Vision Components in an FPGA System

Pin-point landing is required to enable missions to land close, typically within 10 meters, to scientifically important targets in generally hazardous terrain. In Pin Point Landing both high accuracy and high speed estimation of position and orientation is needed to provide input to the control system to safely choose and navigate to a safe landing site. A proposed algorithm called VISion aided Inertial NAVigation (VISINAV) has shown that the accuracy requirements can be met. [2][3] VISINAV was shown in software only, and was expected to use FPGA enhancements in the future to improve the computational speed needed for pin point landing during Entry Descent and Landing (EDL). Homography, feature detection and spatial correlation are computationally intensive parts of VISINAV. Homography aligns the map image with the descent image so that small correlation windows can be used, and feature detection provides regions that spatial correlation can track from frame to frame in order to estimate vehicle motion. On MER the image Homography, Feature Detection and Correlation would take approximately 650ms tracking 75 features between frames. We implemented Homography, Feature detection and Correlation on a Virtex 4 LX160 FPGA to run in under 25ms while tracking 500 features to improve algorithm reliability and throughput.

aircraft landing guidance↗

NASA NTRS2017

COBALT: Development of a Platform to Flight Test Lander GN&C Technologies on Suborbital Rockets

The NASA COBALT Project (CoOperative Blending of Autonomous Landing Technologies) is developing and integrating new precision-landing Guidance, Navigation and Control (GN&C) technologies, along with developing a terrestrial fight-test platform for Technology Readiness Level (TRL) maturation. The current technologies include a third- generation Navigation Doppler Lidar (NDL) sensor for ultra-precise velocity and line- of-site (LOS) range measurements, and the Lander Vision System (LVS) that provides passive-optical Terrain Relative Navigation (TRN) estimates of map-relative position. The COBALT platform is self contained and includes the NDL and LVS sensors, blending filter, a custom compute element, power unit, and communication system. The platform incorporates a structural frame that has been designed to integrate with the payload frame onboard the new Masten Xodiac vertical take-o, vertical landing (VTVL) terrestrial rocket vehicle. Ground integration and testing is underway, and terrestrial fight testing onboard Xodiac is planned for 2017 with two flight campaigns: one open-loop and one closed-loop.

Carson, John M., III↗

NASA NTRS1991

Automated site characterization for robotic sample acquisition systems

A mobile, semi-autonomous vehicle with multiple sensors and on-board intelligence is proposed for performing preliminary scientific investigations on extraterrestrial bodies prior to human exploration. Two technologies, a hybrid optical-digital computer system based on optical correlator technology and an image and instrument data analysis system, provide complementary capabilities which might be part of an instrument package for an intelligent robotic vehicle. The hybrid digital-optical vision system could perform real-time image classification tasks using an optical correlator with programmable matched filters under control of a digital microcomputer. The data analysis system would analyze visible and multiband imagery to extract mineral composition and textural information for geologic characterization. Together these technologies would support the site characterization needs of a robotic vehicle for both navigational and scientific purposes.

Scholl, Marija S.↗

NASA NTRS2003

Surface color perception under two illuminants: the second illuminant reduces color constancy

This study investigates color perception in a scene with two different illuminants. The two illuminants, in opposite corners, simultaneously shine on a (simulated) scene with an opaque dividing wall, which controls how much of the scene is illuminated by each source. In the first experiment, the height of the dividing wall was varied. This changed the amount of each illuminant reaching objects on the opposite side of the wall. Results showed that the degree of color constancy decreased when a region on one side of the wall had cues to both illuminants, suggesting that cues from the second illuminant are detrimental to color constancy. In a later experiment, color constancy was found to improve when the specular highlight cues from the second illuminant were altered to be consistent with the first illuminant. This corroborates the influence of specular highlights in surface color perception, and suggests that the reduced color constancy in the first experiment is due to the inconsistent, though physically correct, cues from the two illuminants.

Contrast Sensitivity/physiology↗

NASA NTRS2018

Initial Flight Testing of an eXternal Vision System (XVS) for the Low Boom Flight Demonstrator (LBFD)

NASA will design an eXternal Vision System (XVS) that, with other aircraft systems and subsystems, will ensure safe and efficient operations in all phases of flight for its Low Boom Flight Demonstrator vehicle. XVS is a combination of display, sensor, and computing technologies, creating an electronic means of forward visibility for the pilot. A flight test was performed evaluating a preliminary design of an XVS to quantify, by direct comparison, the ability of a pilot using an XVS to see and recognize airborne traffic compared to that of a pilot using forward-facing windows during challenging see-and-avoid scenarios. The data showed that the XVS and forward-facing windows were essentially equivalent in detecting and recognizing incurring traffic aircraft. The data also showed that the pilot using the XVS could see and recognize the incurring traffic at no less than 0.7 nm prior to the pilot using the forward-facing windows. The performance of the XVS was dependent upon the application of image contrast enhancement. Recommendations for future improvements were captured from evaluation pilot commentary.

Kramer, Lynda J↗