SEARCH · Search NASA

Results for “Pattern 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 163 records · Page 9

All sources NASA NTRS DOE OSTI

NASA NTRS1994

A Decade of Neural Networks: Practical Applications and Prospects

The Jet Propulsion Laboratory Neural Network Workshop, sponsored by NASA and DOD, brings together sponsoring agencies, active researchers, and the user community to formulate a vision for the next decade of neural network research and application prospects. While the speed and computing power of microprocessors continue to grow at an ever-increasing pace, the demand to intelligently and adaptively deal with the complex, fuzzy, and often ill-defined world around us remains to a large extent unaddressed. Powerful, highly parallel computing paradigms such as neural networks promise to have a major impact in addressing these needs. Papers in the workshop proceedings highlight benefits of neural networks in real-world applications compared to conventional computing techniques. Topics include fault diagnosis, pattern recognition, and multiparameter optimization.

Kemeny, Sabrina E.↗

NASA NTRS2014

Visual Image Sensor Organ Replacement

This innovation is a system that augments human vision through a technique called "Sensing Super-position" using a Visual Instrument Sensory Organ Replacement (VISOR) device. The VISOR device translates visual and other sensors (i.e., thermal) into sounds to enable very difficult sensing tasks. Three-dimensional spatial brightness and multi-spectral maps of a sensed image are processed using real-time image processing techniques (e.g. histogram normalization) and transformed into a two-dimensional map of an audio signal as a function of frequency and time. Because the human hearing system is capable of learning to process and interpret extremely complicated and rapidly changing auditory patterns, the translation of images into sounds reduces the risk of accidentally filtering out important clues. The VISOR device was developed to augment the current state-of-the-art head-mounted (helmet) display systems. It provides the ability to sense beyond the human visible light range, to increase human sensing resolution, to use wider angle visual perception, and to improve the ability to sense distances. It also allows compensation for movement by the human or changes in the scene being viewed.

Maluf, David A.↗

NASA NTRS2008

Photorefraction Screens Millions for Vision Disorders

Who would have thought that stargazing in the 1980s would lead to hundreds of thousands of schoolchildren seeing more clearly today? Collaborating with research ophthalmologists and optometrists, Marshall Space Flight Center scientists Joe Kerr and the late John Richardson adapted optics technology for eye screening methods using a process called photorefraction. Photorefraction consists of delivering a light beam into the eyes where it bends in the ocular media, hits the retina, and then reflects as an image back to a camera. A series of refinements and formal clinical studies followed their highly successful initial tests in the 1980s. Evaluating over 5,000 subjects in field tests, Kerr and Richardson used a camera system prototype with a specifically angled telephoto lens and flash to photograph a subject s eye. They then analyzed the image, the cornea and pupil in particular, for irregular reflective patterns. Early tests of the system with 1,657 Alabama children revealed that, while only 111 failed the traditional chart test, Kerr and Richardson s screening system found 507 abnormalities.

Source record↗

NASA NTRS2000

Real Time Intelligent Target Detection and Analysis with Machine Vision

We present an algorithm for detecting a specified set of targets for an Automatic Target Recognition (ATR) application. ATR involves processing images for detecting, classifying, and tracking targets embedded in a background scene. We address the problem of discriminating between targets and nontarget objects in a scene by evaluating 40x40 image blocks belonging to an image. Each image block is first projected onto a set of templates specifically designed to separate images of targets embedded in a typical background scene from those background images without targets. These filters are found using directed principal component analysis which maximally separates the two groups. The projected images are then clustered into one of n classes based on a minimum distance to a set of n cluster prototypes. These cluster prototypes have previously been identified using a modified clustering algorithm based on prior sensed data. Each projected image pattern is then fed into the associated cluster's trained neural network for classification. A detailed description of our algorithm will be given in this paper. We outline our methodology for designing the templates, describe our modified clustering algorithm, and provide details on the neural network classifiers. Evaluation of the overall algorithm demonstrates that our detection rates approach 96% with a false positive rate of less than 0.03%.

Howard, Ayanna↗

NASA NTRS1995

Machine learning for a Toolkit for Image Mining

A prototype user environment is described that enables a user with very limited computer skills to collaborate with a computer algorithm to develop search tools (agents) that can be used for image analysis, creating metadata for tagging images, searching for images in an image database on the basis of image content, or as a component of computer vision algorithms. Agents are learned in an ongoing, two-way dialogue between the user and the algorithm. The user points to mistakes made in classification. The algorithm, in response, attempts to discover which image attributes are discriminating between objects of interest and clutter. It then builds a candidate agent and applies it to an input image, producing an 'interest' image highlighting features that are consistent with the set of objects and clutter indicated by the user. The dialogue repeats until the user is satisfied. The prototype environment, called the Toolkit for Image Mining (TIM) is currently capable of learning spectral and textural patterns. Learning exhibits rapid convergence to reasonable levels of performance and, when thoroughly trained, Fo appears to be competitive in discrimination accuracy with other classification techniques.

Delanoy, Richard L.↗

NASA NTRS2012

The Stellar Imager (SI) - A Mission to Resolve Stellar Surfaces, Interiors, and Magnetic Activity

The Stellar Imager (SI) is a space-based, UV/Optical Interferometer (UVOI) designed to enable 0.1 milli-arcsecond (mas) spectral imaging of stellar surfaces and of the Universe in general. It will also probe via asteroseismology flows and structures in stellar interiors. SI will enable the development and testing of a predictive dynamo model for the Sun, by observing patterns of surface activity and imaging of the structure and differential rotation of stellar interiors in a population study of Sun-like stars to determine the dependence of dynamo action on mass, internal structure and flows, and time. SI's science focuses on the role of magnetism in the Universe and will revolutionize our understanding of the formation of planetary systems, of the habitability and climatology of distant planets, and of many magnetohydrodynamically controlled processes in the Universe. SI is a "LandmarklDiscovery Mission" in the 2005 Heliophysics Roadmap, an implementation of the UVOI in the 2006 Astrophysics Strategic Plan, and a NASA Vision Mission ("NASA Space Science Vision Missions" (2008), ed. M. Allen). We present here the science goals of the SI Mission, a mission architecture that could meet those goals, and the technology development needed to enable this mission

Christensen-Dalsgaard, Jorgen↗

NASA NTRS1993

Neurophysiological study on visuo-vestibular control of posture and movement in fish during adaptation to weightlessness

We can stand upright and walk smoothly without paying any particular attention to it. This is because we have established in ourselves an integration center that controls our body subconsciously in response to input from eyes, muscles, joints, foot soles, and also from the gravity sensor in the inner ear (the otolith organ). It has been shown that the cerebellum plays an important role for the establishment of the integration center and that the control pattern is comparable to that of a highly sophisticated computer system. The programming for the control, however, may well be acquired for the 1-g ground condition and does not cover the 0-g in space. Although each of the above organs function as it does on the ground, the signal pattern sent to the center must be different under 0-g and, in addition, complementary signals from the otolith organ are missing, leading to confusion in the integration center and causing a variety of symptoms similar to those of car-sickness or sea-sickness. After exposure to microgravity an immediate process of re-programming will begin and be completed in 2-4 days. There is strong supporting evidence for this sensory conflict theory as an explanation for space motion sickness (SMS) episodes. Fish were selected as test organisms for this investigation because they swim around freely in three dimensions and have well-developed organs for vision and gravity detection. They also have an innate nature to orient their back toward a light source. Actually, on the ground, the fish tilts its vertical axis toward the light when illuminated laterally, and the tilt angle is a function of the intensity of light and the magnitude of gravity, while its posture is completely light-dependent in the low-gravity environment produced by aircraft parabolic flight or when the otolith organs are removed. This implies that fish posture is entirely under visual and otolithic control. In this case, the cerebellum will also contribute to the control. In the space shuttle experiment, two fish (one with otolith-removed and the other with intact otoliths) are onboard for 7 days. The arrangement of the experiment is shown. Lamps illuminate each fish alternately from different directions at a duration of 20 seconds for 10 minutes totally, twice a day. The video images and the brain waves from the cerebellum are analyzed later. If the sensory conflict theory is acceptable, then the confusion at the onset and the following recovery process will be manifested both in the light-dependent behavior and also in the cerebellar activity. In addition, there should be some variation in response between the two fish. Even if the results are positive in the present fish experiment, they would not be extensive enough to allow us to understand the complete mechanisms of SMS. However, what is currently needed is a collection of evidence based on animal experiments on which to base future investigations. Countermeasures for SMS are mandatory since SMS-induced vomiting occurring within a space suit could be fatal for a crew member during extravehicular activities. We expect that countermeasures will be developed before the space station era starts, and that the results of these studies will be applied to improving human welfare.

Mori, Shigeo↗

NASA NTRS1989

Plant features measurements for robotics

Initial studies of the technical feasibility of using machine vision and color image processing to measure plant health were performed. Wheat plants were grown in nutrient solutions deficient in nitrogen, potassium, and iron. An additional treatment imposed water stress on wheat plants which received a full complement of nutrients. The results for juvenile (less than 2 weeks old) wheat plants show that imaging technology can be used to detect nutrient deficiencies. The relative amount of green color in a leaf declined with increased water stress. The absolute amount of green was higher for nitrogen deficient leaves compared to the control plants. Relative greenness was lower for iron deficient leaves, but the absolute green values were higher. The data showed patterns across the leaf consistent with visual symptons. The development of additional color image processing routines to recognize these patterns would improve the performance of this sensor of plant health.

Miles, Gaines E.↗

NASA NTRS1994

The Influence of Gravito-Inertial Force on Sensorimotor Integration and Reflexive Responses

Sensorimotor responses (e.g.. eye movements, spinal reflexes, etc depend upon the interpretation of the neural signals from the sensory systems. Since neural signals from the otoliths may represent either tilt (gravity) or translation (linear inertial force), sensory signals from the otolith organs are necessarily somewhat ambiguous. Therefore. the neural responses to changing otolith signals depend upon the context of the stimulation (e.g- active vs. passive, relative orientation of gravity, etc.) as well as upon other sensory signals (e.g., vision. canals, etc.). This session will focus upon the -role -played by the sensory signals from the otolith organs in producing efficient sensorimotor and behavioral responses. Curthoys will show the influence of the peripheral anatomy and physiology. Tomko will discuss the influence of tilt and translational otolith signals on eye movements. Merfeld will demonstrate the rate otolith organs play during the interaction of sensory signals from the canals and otoliths. Watt will show the influence of the otoliths on spinal/postural responses. Guedry will discuss the contribution of vestibular information to "path of movement"' perception and to the development of a stable vertical reference. Sensorimotor responses to the ambiguous inertial force stimulation provide an important tool to investigate how the nervous system processes patterns of sensory information and yields functional sensorimotor responses.

Curthoys, Ian S.↗

NASA NTRSDate not supplied

Translational Line of Sight: a multi-omics longitudinal study of the murine retinal response to spaceflight hazard analogs

The space environment includes unique hazards like radiation and microgravity which adversely affect physiology and behavior of humans and rodent models. To better characterize the retinal response to spaceflight, we assessed a multi-omics NASA GeneLab dataset where 6-month-old female mice were gamma irradiated and/or hindlimb unloaded for 21 days followed by whole transcriptome shotgun sequencing (RNA-Seq) and reduced representation bisulfite sequencing (RRBS) of retina samples collected at 7 days, 1 month or 4 months post-exposure. We compared time-matched epigenomic and transcriptomic retinal profiles revealing a total of 4,178 differentially methylated loci or regions, and 457 differentially expressed genes. Highest correlation in methylation differences was seen across different conditions at the same time point (e.g., between radiation exposure and hindlimb unloaded at 7 days). Biological processes related to nucleotide metabolism were enriched in all groups with activation at 1 month and suppression at 7 days and 4 months. Genes and processes related to Notch and Wnt signaling showed alterations 4 months post-exposure. Interestingly, Notch3 and Lrg1 showed differential patterns in the NASA Twins Study in-flight samples and in response to stressors in the murine retina in the current study. A total of 23 genes were both differentially methylated and expressed, including genes involved in retinal disease or cataract development (Crybb3, Fgfr1, Pitpnm3, Sipa1l3, Sox9) and inflammatory response (B4galt6, Ppm1a, Sphk1). To our knowledge, the current multi-omics analysis is the first multi-omics study to interrogate the epigenomic and transcriptomic impacts of radiation and hindlimb unloading on the retina in isolation and in combination. The results provide an insight into the retinal response to individual spaceflight hazard analogs and their interplay at different post-exposure stages and contributes towards a mechanistic understanding of spaceflight-induced vision impairment using ground-based models.

Prachi Kothiyal↗

NASA NTRSDate not supplied

A Multi-omics Longitudinal Study of the Murine Retinal Response to Chronic Low-dose Irradiation and/or Simulated Microgravity

Prachi Kothiyal↗

NASA NTRS2014

Nutritional Status Assessment (SMO 016E)

The Nutritional Status Assessment Supplemental Medical Objective was initiated to expand nominal clinical nutrition testing of ISS astronauts, and to gain a better understanding of the time course of changes in nutritional status during flight. The primary activity of this effort was collecting blood and urine samples during flight for analysis after return to Earth. Samples were subjected to a battery of tests. The resulting data provide a comprehensive survey of how nutritional status and related systems are affected by 4-6 months of space flight. Analysis of these data has yielded many findings to date, including: Vision. Documented evidence that biochemical markers involved in one-carbon metabolism were altered in crewmembers who experienced vision-related issues during and after flight (1). Iron, Oxidative Stress, and Bone. In-flight data document a clear association of increased iron stores, markers of oxidative damage to DNA, and bone loss (2). Exercise. Documented that well-nourished crewmembers performing heavy resistance exercise returned from ISS with bone mineral densities unchanged from preflight (3). Furthermore, the response of bone to space flight and exercise countermeasures was the same in men and women (4). Body Mass. Crewmembers lose 2-5% of their body mass in the first month of flight, and maintain the lower body mass during flight (5). Additionally, the two devices to measure body mass on orbit, the SLAMMD and BMMD, provide similar results (5). Cytokines. Findings indicated that a pattern of persistent physiological adaptations occurs during space flight that includes shifts in immune and hormonal regulation (6). Fish/Bone. Documented a relationship between fish intake and bone loss in astronauts (that is, those who ate more fish lost less bone) (7). Vitamin K. Documented that in generally well-fed and otherwise healthy individuals, vitamin K status and bone vitamin K-dependent proteins are unaffected by space flight (and bed rest) (8). Testosterone. Documented that blood concentrations of testosterone were unchanged during flight, but a transient decline occurred after landing (9). Calcium. Nutrition SMO data contributed to the ISS Program by helping understand how and why the Urine Processor Assembly clogged with calcium sulfate precipitate (10). Sample Processing. Ground-based analytical testing results have also been published (11).

Smith, S. M.↗

NASA NTRS2003

Design of a Borescope for Extravehicular Non-Destructive Applications

Anomalies such as corrosion, structural damage, misalignment, cracking, stress fiactures, pitting, or wear can be detected and monitored by the aid of a borescope. A borescope requires a source of light for proper operation. Today s current lighting technology market consists of incandescent lamps, fluorescent lamps and other types of electric arc and electric discharge vapor lamp. Recent advances in LED technology have made LEDs viable for a number of applications, including vehicle stoplights, traffic lights, machine-vision-inspection, illumination, and street signs. LEDs promise significant reduction in power consumption compared to other sources of light. This project focused on comparing images taken by the Olympus IPLEX, using two different light sources. One of the sources is the 50-W internal metal halide lamp and the other is a 1 W LED placed at the tip of the insertion tube. Images acquired using these two light sources were quantitatively compared using their histogram, intensity profile along a line segment, and edge detection. Also, images were qualitatively compared using image registration and transformation [l]. The gray-level histogram, edge detection, image profile and image registration do not offer conclusive results. The LED light source, however, produces good images for visual inspection by an operator. Analysis using pattern recognition using Eigenfaces and Gaussian Pyramid in face recognition may be more useful.

Bachnak, Rafic↗

NASA NTRS2017

A Network-Based Algorithm for Clustering Multivariate Repeated Measures Data

The National Aeronautics and Space Administration (NASA) Astronaut Corps is a unique occupational cohort for which vast amounts of measures data have been collected repeatedly in research or operational studies pre-, in-, and post-flight, as well as during multiple clinical care visits. In exploratory analyses aimed at generating hypotheses regarding physiological changes associated with spaceflight exposure, such as impaired vision, it is of interest to identify anomalies and trends across these expansive datasets. Multivariate clustering algorithms for repeated measures data may help parse the data to identify homogeneous groups of astronauts that have higher risks for a particular physiological change. However, available clustering methods may not be able to accommodate the complex data structures found in NASA data, since the methods often rely on strict model assumptions, require equally-spaced and balanced assessment times, cannot accommodate missing data or differing time scales across variables, and cannot process continuous and discrete data simultaneously. To fill this gap, we propose a network-based, multivariate clustering algorithm for repeated measures data that can be tailored to fit various research settings. Using simulated data, we demonstrate how our method can be used to identify patterns in complex data structures found in practice.

Koslovsky, Matthew↗

NASA NTRS1990

Photonic processing at NASA Ames Research Center

The Photonic Processing group is engaged in applied research on optical processors in support of the Ames vision to lead the development of autonomous intelligent systems. Optical processors, in conjunction with numeric and symbolic processors, are needed to provide the powerful processing capability that is required for many future agency missions. The research program emphasizes application of analog optical processing, where free-space propagation between components allows natural implementations of algorithms requiring a large degree of parallel computation. Special consideration is given in the Ames program to the integration of optical processors into larger, heterogeneous computational systems. Demonstration of the effective integration of optical processors within a broader knowledge-based system is essential to evaluate their potential for dependable operation in an autonomous environment such as space. The Ames Photonics program is currently addressing several areas of interest. One of the efforts is to develop an optical correlator system with two programmable spatial light modulators (SLMs) to perform distortion invariant pattern recognition. Another area of research is optical neural networks, also for use in distortion-invariant pattern recognition.

Ochoa, Ellen↗

DOE OSTI2026

ObstacleSense: Low-Power Neuromorphic Vision for Corridor Obstacle Awareness in Low-Level ADAS

The automotive industry’s pursuit of Level 5 autonomy is constrained by substantial perception-compute power requirements, often reaching 1, 000 + watts in full autonomy stacks. Reducing this energy burden requires rethinking perception not only at the high-end autonomy level, but also at the foundational Advanced Driver Assistance Systems (ADAS) level where low-power, safety-critical sensing can have broad impact. Neuromorphic vision provides a promising starting point: HD Dynamic Vision Sensors (DVS) can operate below 100 mW at the sensor level by reporting only asynchronous brightness changes. However, low-power sensing alone is insufficient if downstream perception reintroduces dense, energy-intensive computation. In particular, many event-driven object-detection pipelines still rely on CNN backbones, while purely spiking alternatives often trade away accuracy or ignore deployment constraints. We introduce ObstacleSense, a highly compact, CNN-free hybrid ANN–SNN framework for Level 0–1 forward-corridor obstacle awareness. Instead of performing full-scene object detection with a convolutional feature backbone, ObstacleSense targets the safety-critical question of whether the ego corridor is occupied and how far the nearest obstacle is. The architecture combines polarity-conditioned event encoding, lightweight temporal spiking dynamics, axial spatial mixing, and coarse-to-fine range estimation within a regular fixed-grid compute pattern. This design avoids the dense CNN backbone commonly used in event-based detection while maintaining a small state footprint suitable for eventual small-FPGA deployment. Before hardware mapping, we evaluate the software implementation using a model-side power proxy derived from MACs, weight and activation traffic, and spiking state updates under shared FP16 assumptions. On simulated CARLA event corpora, the deployment-oriented model achieves 0.9464 objectness F1, 0.9978 grid-level mAP, and 0.8987 m distance Mean Absolute Error at an estimated 1.92 mW proxy cost, while maintaining performance on unseen generalization test sequences.

Johnson-Scott, Zac [ORNL]↗

NASA NTRS1995

1st- and 2nd-order motion and texture resolution in central and peripheral vision

STIMULI. The 1st-order stimuli are moving sine gratings. The 2nd-order stimuli are fields of static visual texture, whose contrasts are modulated by moving sine gratings. Neither the spatial slant (orientation) nor the direction of motion of these 2nd-order (microbalanced) stimuli can be detected by a Fourier analysis; they are invisible to Reichardt and motion-energy detectors. METHOD. For these dynamic stimuli, when presented both centrally and in an annular window extending from 8 to 10 deg in eccentricity, we measured the highest spatial frequency for which discrimination between +/- 45 deg texture slants and discrimination between opposite directions of motion were each possible. RESULTS. For sufficiently low spatial frequencies, slant and direction can be discriminated in both central and peripheral vision, for both 1st- and for 2nd-order stimuli. For both 1st- and 2nd-order stimuli, at both retinal locations, slant discrimination is possible at higher spatial frequencies than direction discrimination. For both 1st- and 2nd-order stimuli, motion resolution decreases 2-3 times more rapidly with eccentricity than does texture resolution. CONCLUSIONS. (1) 1st- and 2nd-order motion scale similarly with eccentricity. (2) 1st- and 2nd-order texture scale similarly with eccentricity. (3) The central/peripheral resolution fall-off is 2-3 times greater for motion than for texture.

Pattern Recognition, Visual/physiology↗

NASA NTRS2000

Bioelectric Control of a 757 Class High Fidelity Aircraft Simulation

This paper presents results of a recent experiment in fine grain Electromyographic (EMG) signal recognition, We demonstrate bioelectric flight control of 757 class simulation aircraft landing at San Francisco International Airport. The physical instrumentality of a pilot control stick is not used. A pilot closes a fist in empty air and performs control movements which are captured by a dry electrode array on the arm, analyzed and routed through a flight director permitting full pilot outer loop control of the simulation. A Vision Dome immersive display is used to create a VR world for the aircraft body mechanics and flight changes to pilot movements. Inner loop surfaces and differential aircraft thrust is controlled using a hybrid neural network architecture that combines a damage adaptive controller (Jorgensen 1998, Totah 1998) with a propulsion only based control system (Bull & Kaneshige 1997). Thus the 757 aircraft is not only being flown bioelectrically at the pilot level but also demonstrates damage adaptive neural network control permitting adaptation to severe changes in the physical flight characteristics of the aircraft at the inner loop level. To compensate for accident scenarios, the aircraft uses remaining control surface authority and differential thrust from the engines. To the best of our knowledge this is the first time real time bioelectric fine-grained control, differential thrust based control, and neural network damage adaptive control have been integrated into a single flight demonstration. The paper describes the EMG pattern recognition system and the bioelectric pattern recognition methodology.

Jorgensen, Charles↗