SEARCH · Search NASA

Results for “computer vision techniques”

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 181 records · Page 10

All sources NASA NTRS DOE OSTI

NASA NTRS1989

Implementation of an algorithm for cylindrical object identification using range data

One of the problems in 3-D object identification and localization is addressed. In robotic and navigation applications the vision system must be able to distinguish cylindrical or spherical objects as well as those of other geometric shapes. An algorithm was developed to identify cylindrical objects in an image when range data is used. The algorithm incorporates the Hough transform for line detection using edge points which emerge from a Sobel mask. Slices of the data are examined to locate arcs of circles using the normal equations of an over-determined linear system. Current efforts are devoted to testing the computer implementation of the algorithm. Refinements are expected to continue in order to accommodate cylinders in various positions. A technique is sought which is robust in the presence of noise and partial occlusions.

Bozeman, Sylvia T.↗

NASA NTRS2016

Characterization of Stereo Vision Performance for Roving at the Lunar Poles

Surface rover operations at the polar regions of airless bodies, particularly the Moon, are of particular interest to future NASA science missions such as Resource Prospector (RP). Polar optical conditions present challenges to conventional imaging techniques, with repercussions to driving, safeguarding and science. High dynamic range, long cast shadows, opposition and white out conditions are all significant factors in appearance. RP is currently undertaking an effort to characterize stereo vision performance in polar conditions through physical laboratory experimentation with regolith simulants, obstacle distributions and oblique lighting.

Sensor Characterization↗

NASA NTRS1992

Topography from shading and stereo

Methods exploiting photometric information in images that have been developed in machine vision can be applied to planetary imagery. Present techniques, however, focus on one visual cue, such as shading or binocular stereo, and produce results that are either not very accurate in an absolute sense or provide information only at few points on the surface. We plan to integrate shape from shading, binocular stereo and photometric stereo to yield a robust system for recovering detailed surface shape and surface reflectance information. Such a system will be useful in producing quantitative information from the vast volume of imagery being received, as well as in helping visualize the underlying surface. The work will be carried out on a popular computing platform so that it will be easily accessible to other workers.

Horn, Berthold P.↗

NASA NTRS1993

Topography from shading and stereo

Horn, Berthold P.↗

DOE OSTI2025

A Data-Agnostic, Continuous Machine Learning Framework for Application in High Energy Physics and Beyond: Phase 1 Final Scientific/Technical Report

This Phase 1 effort has focused on the development of continual learning frameworks for use in machine learning, specifically in the applied context of High Energy Physics (HEP). Machine learning (ML) is a transformative technology by which computers, typically through the use of neural networks, are able to perform tasks with proficiency that rivals or surpasses that of human users. Model Degradation & Catastrophic Forgetting are two undesired phenomena which can occur in ML where the performance of a model degrades when either deployed on novel data streams, or trained on novel data which are sufficiently different than the data the models were initially trained on. A natural example where these sorts of effects can be observed is in the performance of detectors in harsh environments, where the detector signature may change over the lifetime of the detector as it ages and deteriorates — precisely what occurs in the experiments conducted in HEP. Real world HEP data is therefore an excellent test-ground and use-case for Continual Learning paradigms, which are techniques used in ML to counteract these problems. Ensemble learning is one such technique, where multiple smaller models are trained on subsets of the overall data and are ensembled together during inference. The intuition behind this technique is that, although there are shifts in the distributions which govern the incoming data streams, these shifts are not expected to be homogeneous or global. If a sufficient diversity in solutions within the various sub-models has been achieved, then at least one sub-model is expected to retain its performance within the overall ensemble. One further strength of this approach is that the architectures of the various models do not need to be identical, and in fact even different modalities of data can naturally be combined in this way. This work focused on applying ensemble learning techniques to derive results using two main datasets, anomaly detection in HEP data & time-series forecasting in semiconductor manufacturing data. Semiconductor manufacturing involves data with surprising similarity to that of HEP (e.g. wafer maps look very similar to digi-occupancy maps) and Cerium Lab’s prominence within the semiconductor industry makes semiconductor manufacturing a natural opportunity for commercialization of this work. Our efforts have led to two strong results. The first is that we evaluated the proposed ensembling techniques using previously proposed machine learning architectures for use in anomaly detection, namely AutoEncoder based models and their derivatives. We also developed new architectures which have not been evaluated in this context before. In fact, this work marks the first use of Vision Transformers for anomaly detection in HEP. Second, we demonstrated that ensemble learning significantly improves model performance in scenarios prone to degradation, validating its effectiveness across both HEP and semiconductor datasets. These results further support ensemble learning as a powerful strategy for mitigating catastrophic forgetting and maintaining robust performance in evolving data environments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

NASA NTRS2005

Hubble Space Telescope Angular Velocity Estimation During the Robotic Servicing Mission

During the Hubble Robotic Servicing Mission, the Hubble Space Telescope (HST) attitude and rates are necessary to achieve the capture of HST by the Hubble Robotic Vehicle (HRV). The attitude and rates must be determined without the HST gyros or HST attitude estimates. The HRV will be equipped with vision-based sensors, capable of estimating the relative attitude between HST and HRV. The HST attitude is derived from the measured relative attitude and the HRV computed inertial attitude. However, the relative rate between HST and HRV cannot be measured directly. Therefore, the HST rate with respect to inertial space is not known. Two approaches are developed to estimate the HST rates. Both methods utilize the measured relative attitude and the HRV inertial attitude and rates. First, a nonlinear estimator is developed. The nonlinear approach estimates the HST rate through an estimation of the inertial angular momentum. Second, a linearized approach is developed. The linearized approach is based on more traditional Extended Kalman filter techniques. Simulation test results for both methods are given.

Thienel, Julie K.↗

NASA NTRS2017

Optical Flow for Flight and Wind Tunnel Background Oriented Schlieren Imaging

Background oriented Schlieren images have historically been generated by calculating the observed pixel displacement between a wind-on and wind-o image pair using normalized cross-correlation. This work uses optical flow to solve the displacement fields which generate the Schlieren images. A well established method used in the computer vision community, optical flow is the apparent motion in an image sequence due to brightness changes. The regularization method of Horn and Schunck is used to create Schlieren images using two data sets: a supersonic jet plume shock interaction from the NASA Ames Unitary Plan Wind Tunnel, and a transonic flight test of a T-38 aircraft using a naturally occurring background, performed in conjunction with NASA Ames and Armstrong Research Centers. Results are presented and contrasted with those using normalized cross-correlation. The optical flow Schlieren images are found to provided significantly more detail. We apply the method to historical data sets to demonstrate the broad applicability and limitations of the technique.

Image processing↗

NASA NTRS1993

Acting to gain information

This report is concerned with agents that act to gain information. In previous work, we developed agent models combining qualitative modeling with real-time control. That work, however, focused primarily on actions that affect physical states of the environment. The current study extends that work by explicitly considering problems of active information-gathering and by exploring specialized aspects of information-gathering in computational perception, learning, and language. In our theoretical investigations, we analyzed agents into their perceptual and action components and identified these with elements of a state-machine model of control. The mathematical properties of each was developed in isolation and interactions were then studied. We considered the complexity dimension and the uncertainty dimension and related these to intelligent-agent design issues. We also explored active information gathering in visual processing. Working within the active vision paradigm, we developed a concept of 'minimal meaningful measurements' suitable for demand-driven vision. We then developed and tested an architecture for ongoing recognition and interpretation of visual information. In the area of information gathering through learning, we explored techniques for coping with combinatorial complexity. We also explored information gathering through explicit linguistic action by considering the nature of conversational rules, coordination, and situated communication behavior.

Rosenchein, Stanley J.↗

DOE OSTI2025

Vision Foundation Models in Remote Sensing: A survey

Artificial intelligence (AI) technologies have profoundly transformed the field of remote sensing (RS), revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, RS research has been significantly enhanced by the advent of foundation models (FMs)—large-scale pretrained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency. This article provides a comprehensive survey of FMs in the RS domain. We categorize these models based on their architectures, pretraining datasets, and methodologies. Through detailed performance comparisons, we highlight emerging trends and the significant advancements achieved by those FMs. Additionally, we discuss technical challenges, practical implications, and future research directions, addressing the need for high-quality data, computational resources, and improved model generalization. Our research also finds that pretraining methods, particularly self-supervised learning (SSL) techniques like contrastive learning (CL) and masked autoencoders (MAEs), remarkably enhance the performance and robustness of FMs. This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for the continued development and application of FMs in RS.

data models↗

NASA NTRS2006

2D/3D Visual Tracker for Rover Mast

A visual-tracker computer program controls an articulated mast on a Mars rover to keep a designated feature (a target) in view while the rover drives toward the target, avoiding obstacles. Several prior visual-tracker programs have been tested on rover platforms; most require very small and well-estimated motion between consecutive image frames a requirement that is not realistic for a rover on rough terrain. The present visual-tracker program is designed to handle large image motions that lead to significant changes in feature geometry and photometry between frames. When a point is selected in one of the images acquired from stereoscopic cameras on the mast, a stereo triangulation algorithm computes a three-dimensional (3D) location for the target. As the rover moves, its body-mounted cameras feed images to a visual-odometry algorithm, which tracks two-dimensional (2D) corner features and computes their old and new 3D locations. The algorithm rejects points, the 3D motions of which are inconsistent with a rigid-world constraint, and then computes the apparent change in the rover pose (i.e., translation and rotation). The mast pan and tilt angles needed to keep the target centered in the field-of-view of the cameras (thereby minimizing the area over which the 2D-tracking algorithm must operate) are computed from the estimated change in the rover pose, the 3D position of the target feature, and a model of kinematics of the mast. If the motion between the consecutive frames is still large (i.e., 3D tracking was unsuccessful), an adaptive view-based matching technique is applied to the new image. This technique uses correlation-based template matching, in which a feature template is scaled by the ratio between the depth in the original template and the depth of pixels in the new image. This is repeated over the entire search window and the best correlation results indicate the appropriate match. The program could be a core for building application programs for systems that require coordination of vision and robotic motion.

Bajracharya, Max↗

NASA NTRS1989

Robot Acting on Moving Bodies (RAMBO): Interaction with tumbling objects

Interaction with tumbling objects will become more common as human activities in space expand. Attempting to interact with a large complex object translating and rotating in space, a human operator using only his visual and mental capacities may not be able to estimate the object motion, plan actions or control those actions. A robot system (RAMBO) equipped with a camera, which, given a sequence of simple tasks, can perform these tasks on a tumbling object, is being developed. RAMBO is given a complete geometric model of the object. A low level vision module extracts and groups characteristic features in images of the object. The positions of the object are determined in a sequence of images, and a motion estimate of the object is obtained. This motion estimate is used to plan trajectories of the robot tool to relative locations rearby the object sufficient for achieving the tasks. More specifically, low level vision uses parallel algorithms for image enhancement by symmetric nearest neighbor filtering, edge detection by local gradient operators, and corner extraction by sector filtering. The object pose estimation is a Hough transform method accumulating position hypotheses obtained by matching triples of image features (corners) to triples of model features. To maximize computing speed, the estimate of the position in space of a triple of features is obtained by decomposing its perspective view into a product of rotations and a scaled orthographic projection. This allows use of 2-D lookup tables at each stage of the decomposition. The position hypotheses for each possible match of model feature triples and image feature triples are calculated in parallel. Trajectory planning combines heuristic and dynamic programming techniques. Then trajectories are created using dynamic interpolations between initial and goal trajectories. All the parallel algorithms run on a Connection Machine CM-2 with 16K processors.

Davis, Larry S.↗

NASA NTRS2007

NASA Tech Briefs, November 2007

Topics include: Wireless Measurement of Contact and Motion Between Contact Surfaces; Wireless Measurement of Rotation and Displacement Rate; Portable Microleak-Detection System; Free-to-Roll Testing of Airplane Models in Wind Tunnels; Cryogenic Shrouds for Testing Thermal-Insulation Panels; Optoelectronic System Measures Distances to Multiple Targets; Tachometers Derived From a Brushless DC Motor; Algorithm-Based Fault Tolerance for Numerical Subroutines; Computational Support for Technology- Investment Decisions; DSN Resource Scheduling; Distributed Operations Planning; Phase-Oriented Gear Systems; Freeze Tape Casting of Functionally Graded Porous Ceramics; Electrophoretic Deposition on Porous Non- Conductors; Two Devices for Removing Sludge From Bioreactor Wastewater; Portable Unit for Metabolic Analysis; Flash Diffusivity Technique Applied to Individual Fibers; System for Thermal Imaging of Hot Moving Objects; Large Solar-Rejection Filter; Improved Readout Scheme for SQUID-Based Thermometry; Error Rates and Channel Capacities in Multipulse PPM; Two Mathematical Models of Nonlinear Vibrations; Simpler Adaptive Selection of Golomb Power-of- Two Codes; VCO PLL Frequency Synthesizers for Spacecraft Transponders; Wide Tuning Capability for Spacecraft Transponders; Adaptive Deadband Synchronization for a Spacecraft Formation; Analysis of Performance of Stereoscopic-Vision Software; Estimating the Inertia Matrix of a Spacecraft; Spatial Coverage Planning for Exploration Robots; and Increasing the Life of a Xenon-Ion Spacecraft Thruster.

Source record↗

NASA NTRS1989

Robot acting on moving bodies (RAMBO): Preliminary results

A robot system called RAMBO is being developed. It is equipped with a camera, which, given a sequence of simple tasks, can perform these tasks on a moving object. RAMBO is given a complete geometric model of the object. A low level vision module extracts and groups characteristic features in images of the object. The positions of the object are determined in a sequence of images, and a motion estimate of the object is obtained. This motion estimate is used to plan trajectories of the robot tool to relative locations nearby the object sufficient for achieving the tasks. More specifically, low level vision uses parallel algorithms for image enchancement by symmetric nearest neighbor filtering, edge detection by local gradient operators, and corner extraction by sector filtering. The object pose estimation is a Hough transform method accumulating position hypotheses obtained by matching triples of image features (corners) to triples of model features. To maximize computing speed, the estimate of the position in space of a triple of features is obtained by decomposing its perspective view into a product of rotations and a scaled orthographic projection. This allows the use of 2-D lookup tables at each stage of the decomposition. The position hypotheses for each possible match of model feature triples and image feature triples are calculated in parallel. Trajectory planning combines heuristic and dynamic programming techniques. Then trajectories are created using parametric cubic splines between initial and goal trajectories. All the parallel algorithms run on a Connection Machine CM-2 with 16K processors.

Davis, Larry S.↗

NASA NTRS1990

The JPL/KSC telerobotic inspection demonstration

An ASEA IRB90 robotic manipulator with attached inspection cameras was moved through a Space Shuttle Payload Assist Module (PAM) Cradle under computer control. The Operator and Operator Control Station, including graphics simulation, gross-motion spatial planning, and machine vision processing, were located at JPL. The Safety and Support personnel, PAM Cradle, IRB90, and image acquisition system, were stationed at the Kennedy Space Center (KSC). Images captured at KSC were used both for processing by a machine vision system at JPL, and for inspection by the JPL Operator. The system found collision-free paths through the PAM Cradle, demonstrated accurate knowledge of the location of both objects of interest and obstacles, and operated with a communication delay of two seconds. Safe operation of the IRB90 near Shuttle flight hardware was obtained both through the use of a gross-motion spatial planner developed at JPL using artificial intelligence techniques, and infrared beams and pressure sensitive strips mounted to the critical surfaces of the flight hardward at KSC. The Demonstration showed that telerobotics is effective for real tasks, safe for personnel and hardware, and highly productive and reliable for Shuttle payload operations and Space Station external operations.

Mittman, David↗

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 NTRS2019

Earth Science Technology Office (ESTO) New Observing Strategies (NOS) and NOS-Testbed (NOS-T)

With the advancement of space hardware technologies such as smaller spacecraft, component and instrument miniaturization and high performance space processors, and with the advancement of software technologies in artificial intelligence, big data analysis and autonomous decision making, Earth Science is looking at novel ways to observe phenomena that previously could not have been studied or would have been too expensive to study with traditional missions. In particular, the New Observing Strategies (NOS) component of the NASA Earth Science Technology Office (ESTO) Advanced Information Systems Technology (AIST) Program aims at leveraging these novel technologies as well as low cost and easy access to space to acquire multi-temporal or simultaneous multi-angular, multi-locations, multi-resolution and multi-spectral observations that will provide better multi-source measurements and will build a more dynamic and comprehensive picture of Earth Science phenomena that need to be studied and analyzed. For applications such as water resources management, air quality monitoring, biodiversity studies or disaster management, NOS will integrate the use of small instruments, small spacecraft, constellations of spacecraft and networks of sensors to design new missions that will provide the necessary measurements to improve future forecast and science modeling systems.Measurement acquisition will therefore be approached as a system of systems rather than on a mission basis, and a system of this complexity should not be expected to work without full integration and experimental characterization. Although most of the individual technologies enabling to link and coordinate multi-source observations are more or less mature, a few technologies need to be developed and all of them need to be integrated and tested as a system. In order for this validation to occur, the AIST Program is developing the NOS Testbed that includes 3 main goals:1.Validate novel NOS technologies, independently and as a system2.Demonstrate novel distributed operations concepts3.Socialize new Distributed Spacecraft Mission (DSM) and SensorWeb (SW) technologies and concepts to the science community by significantly retiring the risk of integrating these new technologies.The NOS Testbed will consist of multiple sensing nodes, simulated or actual, representing space, air and/or ground measurements, that are interconnected by a communications fabric (infrastructure that permits nodes to transmit and receive data between one another and interact with each other). Each node will be supported by hardware capabilities required to perform nodes monitoring and command & control, as well as intelligent "onboard" computing. The nodes will work together in a collaborative manner to demonstrate optimal science capabilities. The testbed will enable to validate technologies such as inter-node communication models, techniques and protocols; inter-node coordination; real-time data fusion and understanding; planning; sensor re-targeting; etc. Additionally, the testbed will have the capability to interact with various mission design tools, OSSEs and one or several forecast models. More details about the NOS Testbed will be presented at the confererence.

Earth Science missions; Advanced information Syste↗

NASA NTRS1987

Advanced data management design for autonomous telerobotic systems in space using spaceborne symbolic processors

The use of computers in autonomous telerobots is reaching the point where advanced distributed processing concepts and techniques are needed to support the functioning of Space Station era telerobotic systems. Three major issues that have impact on the design of data management functions in a telerobot are covered. It also presents a design concept that incorporates an intelligent systems manager (ISM) running on a spaceborne symbolic processor (SSP), to address these issues. The first issue is the support of a system-wide control architecture or control philosophy. Salient features of two candidates are presented that impose constraints on data management design. The second issue is the role of data management in terms of system integration. This referes to providing shared or coordinated data processing and storage resources to a variety of telerobotic components such as vision, mechanical sensing, real-time coordinated multiple limb and end effector control, and planning and reasoning. The third issue is hardware that supports symbolic processing in conjunction with standard data I/O and numeric processing. A SSP that currently is seen to be technologically feasible and is being developed is described and used as a baseline in the design concept.

Goforth, Andre↗

NASA NTRS2005

MIT-NASA Workshop: Transformational Technologies

As a space faring nation, we are at a critical juncture in the evolution of space exploration. NASA has announced its Vision for Space Exploration, a vision of returning humans to the Moon, sending robots and eventually humans to Mars, and exploring the outer solar system via automated spacecraft. However, mission concepts have become increasingly complex, with the potential to yield a wealth of scientific knowledge. Meanwhile, there are significant resource challenges to be met. Launch costs remain a barrier to routine space flight; the ever-changing fiscal and political environments can wreak havoc on mission planning; and technologies are constantly improving, and systems that were state of the art when a program began can quickly become outmoded before a mission is even launched. This Conference Publication describes the workshop and featured presentations by world-class experts presenting leading-edge technologies and applications in the areas of power and propulsion; communications; automation, robotics, computing, and intelligent systems; and transformational techniques for space activities. Workshops such as this one provide an excellent medium for capturing the broadest possible array of insights and expertise, learning from researchers in universities, national laboratories, NASA field Centers, and industry to help better our future in space.

Mankins, J. C.↗