SEARCH · Engineering Papers

Results for “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 415 records · Page 23

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Ground-Based Vision Tracker for Advanced Air Mobility and Urban Air Mobility

Advanced Air Mobility (AAM) Air Mobility and Urban Air Mobility (UAM) require aircraft surveillance and monitoring for safety and security. Persistent tracking of flying objects provides Air Traffic Control (ATC) and Air Traffic Management (ATM) continuous coverage and knowledge of the national airspace (NAS). Since there are numerous more AAM and UAM aircraft than commercial aircraft, it will be challenging to utilize the same ATC/ATM architectures. A first step in creating a similar ATC/ATM architecture for AAM/UAM will require ground-based and airborne-based sensors to provide monitoring, which will be difficult in urban environments due to GPS degradation. This paper proposes a vision-based tracking method with static cameras by utilizing image subtraction and blob detection, which avoids adding additional electromagnetic interferences in the environment with sensors such as radar. The ground-based vision tracker (GBVT) outputs the detected objects' azimuth and elevation angles from unmanned aerial system (UAS) flight tests. Future and ongoing work includes sending the detected objects' azimuth and elevation angles as inputs for an extended Kalman filter (EKF) to estimate the position and velocity of the detected object.

distributed sensing↗

NASA NTRSDate not supplied

Unreal Engine Testbed for Computer Vision of Tall Lunar Tower Assembly

The Tall Lunar Tower project at the NASA Langley Research Center is focused on the design, modeling, fabrication, and testing of a supervised autonomously assembly engineering development unit for tall lunar towers. The lunar south pole environment poses many challenges for robotic assembly of the tall tower, particularly to computer vision camera systems due to a high-contrast lighting environment. This paper will present an Unreal Engine 5 video game engine Lunar South Pole Lighting Testbed to simulate realistic lunar lighting conditions for synthetic image generation. The fidelity of the simulation environment is investigated by comparing the accuracy of computer vision models trained using synthetic image data and trained from real image data collected in a lunar analog environment.

Unreal Engine↗

NASA NTRSDate not supplied

Unreal Engine Testbed for Computer Vision of Tall Lunar Tower Assembly

The Tall Lunar Tower project at the NASA Langley Research Center is focused on the design, modeling, fabrication, and testing of a supervised autonomously assembled engineering development unit for tall lunar towers. The lunar south pole environment poses many challenges for robotic assembly of the tall tower, particularly to computer vision camera systems due to a high-contrast lighting environment. This paper will present an Unreal Engine 5 video game engine Lunar South Pole Lighting Testbed to simulate realistic lunar lighting conditions for synthetic image generation. The fidelity of the simulation environment is investigated by comparing the accuracy of computer vision models trained using synthetic image data and trained from real image data collected in a lunar analog environment.

Unreal Engine↗

NASA NTRS2023

Unreal Engine Testbed for Computer Vision of Tall Lunar Tower Assembly

Unreal Engine↗

NASA NTRSDate not supplied

Ground-Based Vision Tracker for Advanced Air Mobility and Urban Air Mobility

Advanced Air Mobility (AAM) Air Mobility and Urban Air Mobility (UAM) require aircraft surveillance and monitoring for safety and security. Persistent tracking of flying objects provides Air Traffic Control (ATC) and Air Traffic Management (ATM) continuous coverage and knowledge of the national airspace system (NAS). Given the significant disparity in the number of AAM and UAM aircraft compared to commercial aircraft in the NAS, coupled with the dense AAM/UAM operations in urban environments, employing the existing ATC/ATM architectures poses considerable challenges. A first step in creating a similar ATC/ATM architecture for AAM/UAM will require ground-based and airborne-based sensors to provide monitoring, which will be difficult in urban environments due to GPS degradation. This paper proposes a vision-based tracking method with static cameras by utilizing image subtraction and blob detection, which avoids adding additional electromagnetic interferences in the environment with sensors such as radar. The ground-based vision tracker (GBVT) outputs the detected objects' azimuth and elevation angles from unmanned aerial system (UAS) flight tests. Future and ongoing work includes sending the detected objects' azimuth and elevation angles as inputs for an extended Kalman filter (EKF) to estimate the position and velocity of the detected object.

distributed sensing↗

DOE OSTI2017

System and method for controlling a vision guided robot assembly

A method includes the following steps: actuating a robotic arm to perform an action at a start position; moving the robotic arm from the start position toward a first position; determining from a vision process method if a first part from the first position will be ready to be subjected to a first action by the robotic arm once the robotic arm reaches the first position; commencing the execution of the visual processing method for determining the position deviation of the second part from the second position and the readiness of the second part to be subjected to a second action by the robotic arm once the robotic arm reaches the second position; and performing a first action on the first part using the robotic arm with the position deviation of the first part from the first position predetermined by the vision process method.

42 ENGINEERING↗

DOE OSTI2018

Enabling an Interactive Grid: A Strategic Vision for Interoperability

This whitepaper proposes that ecosystems of organizations integrating smart technology use such a vision to align their directions and transcend immediate challenge. It then offers a framework for developing a stakeholder roadmap for these integration ecosystems to achieve their vision, including tools to measure the state of interoperability, and a process to identify gaps and prioritize technologies, policies, and timelines.

der integration↗

DOE OSTI2018

Enabling an Interactive Grid: A Strategic Vision for Interoperability

interoperability, , grid architecture, der integra↗

DOE OSTI2021

Individual Wave Detection and Tracking within a Rotating Detonation Engine through Computer Vision Object Detection applied to High-Speed Images

Known for their simplistic design and continuous detonation, rotating detonation engines (RDEs) constitute a majority of current pressure gain combustion (PGC) research efforts. Experimental RDE operation times have been continuously extended through the use of rig cooling techniques. As the window of observable behavior is expanded, and as the technology matures toward eventual integration within gas turbines, monitoring techniques must evolve to better match industrial diagnostics. High-speed image analysis techniques prove useful to capture and evaluate the unsteady detonation behavior within the RDE. Traditional image analysis techniques, however, require extensive processing times which prohibit simultaneous monitoring. To better address this problem, a computer vision object detection methodology is proposed to quickly detect individual detonation waves within a single down-axis image. Detonation waves are detected in individual images by the implemented computer vision method You Only Look Once (YOLO) object detection network. In order to detect detonation waves, the network must first be trained using RDE images of interest, for which each required phase of network development is outlined. Detection of waves is improved through proper treatment of the collected image set, variation of Intersection over Union (IoU) and confidence thresholding, and through a parametric study of annotation dimensions. Each detected wave is described by its location and rotational direction, and locations are tracked to calculate wave velocity across each frame, leading to a timestep resolution of 20 µs. Wave velocities are also calculated through a series of frames, leading to a suitable average velocity estimation using as few as 10 frames. Uncertainty analysis accounting for variation in camera framerate, pixel width and annotation centroid locations estimates a total uncertainty of ±4.3% for velocity calculations, using the smallest annotation boxes. This method offers great reductions in processing times, as a step toward real-time monitoring of detonation waves within an RDE. Improving on previous studies, this technique is impartial to wave modes not included in the original training set and calculates wave velocities independent of high-speed pressure data. The ability to isolate waves within predicted bounding boxes will likely facilitate analysis of pixel intensity variation as an estimation of wave strength in future work.

Johnson, Kristyn↗

DOE OSTI2021

Progress Towards Goals Outlined in the 2014 Decadal Vision

The Atmospheric Radiation Measurement (ARM) user facility published its first decadal vision document in 2014 (U.S. DOE 2014a). The overarching vision described in that document was to develop an integrated observation-modeling framework to accelerate the application of ARM observations for process studies and model applications.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Elementary Particle Physics Vision for EPP2024

In the fall of 2022, the decadal survey committee on Elementary Particle Physics of the US National Academies requested 2000 word Vision Papers, giving personal interpretations of the results of the Snowmass 2021 study and the future of the field. This is my contribution, which emphasizes the central role of the Higgs boson and its associated mysteries. I encourage the authors of other Vision Papers to make them widely available on the arXiv.

Peskin, Michael↗

DOE OSTI2018

Achieving the Vision: An Update on Cleanup, Closure, and Reindustrialization of the East Tennessee Technology Park - 18401

URS-CH2M Oak Ridge LLC (UCOR) is responsible for cleanup of the U.S. Department of Energy's (DOE) East Tennessee Technology Park (ETTP) in Oak Ridge, Tennessee. Formerly known as the K-25 site, the facility enriched uranium for major defense nd energy programs for more than 40 years. The site's industrial processes - largely the gaseous diffusion method used for enriching uranium - left behind radioactive, chemical and industrial contaminants in soils and structures. Cleanup of the environmental legacies enables DOE's goal for converting ETTP into a private sector industrial park. Return of the restored site to the community will attract new industries to the region, creating jobs and growing the economy. The central elements to achieve DOE's vision for the site are 1) Cleanup, 2) Closure, and 3) Reindustrialization. Cleanup entails completion of all demolition activities and remedial actions consistent with the Comprehensive Environmental Response, Compensation and Liability Act of 1980 (CERCLA) agreements. Closure leaves facilities and infrastructure in a condition that enables transfer of the site to non-federal entities and reduces DOE's long-term stewardship costs. Closure activities include: - Infrastructure stabilization (site utilities, roads, stormwater, etc.); - Disposal or transfer of government property; - Relocation of most DOE contractors and support functions offsite; - Transfer of the majority of the site property to non-federal entities for redevelopment. Reindustrialization enables DOE's vision for the site as a multi-use private sector industrial park, reducing DOE's costs and enhancing the local economy. Transfer to the private sector will be accomplished through the Community Reuse Organization of East Tennessee (CROET), which will serve as the Park Manager. (author)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2019

Robotic Non-destructive Test of Concrete Structures with GPR, Impact Echo and 3D Vision - 19540

Structural members come across with various internal defects that cannot be evaluated visually. Instead, hand-held nondestructive sensors are used to detect such defects. In many situations, the hand-held NDT is not possible in high-risk structures because of limited access or safety issues. Therefore, Robotic NDT plays major role in assessing such structures. Robot Operating Systems (ROS) is a powerful open source tool, which is used to program and control robots and other devices enabling one to use sensors, devices and new functionalities such as autonomous navigation, visual perception. For the research presented, ROS is used to program the Sawyer robot arm manufactured by Rethink Robotics. The control system for the robot ensures the ability to adapt to different weights of integrated measuring devices and measured force applied against the wall with a wheeled measuring device while making a remote sweep. Twelve reinforced concrete (RC) beams built with characterized defects are evaluated with the robotic arm integrated with the measuring devices. The RC beams are characterized by voids, corrosion and debonding problems of rebars. The Impact Echo and Ground Penetrating Radar (GPR) devices attached to the robot arm are used to measure the material properties of the concrete beams. The robot arm ensures consistency and uniformity of measurement even in obscure locations. Infrared cameras are used to obtain 3D images of the surfaces of the concrete structures. Roughness is analyzed using computer vision techniques prior to the use of other sensors that are in touch with the surfaces. The computer vision is also used to handle the images collected from GPR sensor. Hand-held NDE is also performed to verify the results obtained by robotic examination. (authors)

42 ENGINEERING↗

DOE OSTI2026

Selective Amnesia using Contrastive Subnet Erasure for Class Level Unlearning in Vision Models

We study concept-level forgetting in pretrained vision models: removing an entire semantic category so the system no longer recognizes that object in unseen images and contexts, rather than merely forgetting specific training examples. Prior work either applies blunt global projections or fine-tunes parameters, which can introduce collateral damage to unrelated features, add compute, and become unstable as forgetting strength increases. We introduce Contrastive Subnet Erasure (CSE), a training-free, encoder-centric edit that targets a compact set of channels most responsible for the class and attenuates them in a calibrated manner. The modification is algebraically folded into the subsequent layer, yielding no inference-time overhead and leaving task heads unchanged. To evaluate whether forgetting generalizes beyond the data used to specify the class, we introduce a cross dataset protocol in which the class is defined on a source dataset and performance is measured on a disjoint target dataset drawn from a different distribution with no shared images. This setup tests whether the model still fails to recognize the object when it looks different or appears in new scenes, and it helps avoid overfitting to patterns in the source dataset. Across CIFAR 10, CIFAR 100, and ImageNet under this protocol, CSE achieves stronger forgetting of the target class while better preserving non target utility than existing baselines in both single class and multi class settings. Overall, CSE provides a simple, stable, and deployment-ready mechanism for class-level unlearning in vision.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗

DOE OSTI2018

Optimizing colormaps with consideration for color vision deficiency to enable accurate interpretation of scientific data

Color vision deficiency (CVD) affects more than 4% of the population and leads to a different visual perception of colors. Though this has been known for decades, colormaps with many colors across the visual spectra are often used to represent data, leading to the potential for misinterpretation or difficulty with interpretation by someone with this deficiency. Until the creation of the module presented here, there were no colormaps mathematically optimized for CVD using modern color appearance models. While there have been some attempts to make aesthetically pleasing or subjectively tolerable colormaps for those with CVD, our goal was to make optimized colormaps for the most accurate perception of scientific data by as many viewers as possible. We developed a Python module, cmaputil , to create CVD-optimized colormaps, which imports colormaps and modifies them to be perceptually uniform in CVD-safe colorspace while linearizing and maximizing the brightness range. The module is made available to the science community to enable others to easily create their own CVD-optimized colormaps. In this paper, we present an example CVD-optimized colormap created with this module that is optimized for viewing by those without a CVD as well as those with red-green colorblindness. This colormap, cividis, enables nearly-identical visual-data interpretation to both groups, is perceptually uniform in hue and brightness, and increases in brightness linearly.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS1999

Machine Vision for Autonomous Small Body Navigation

This paper describes machine vision algorithms that enable precision guidance and hazard avoidance during small body exploration through onboard visual feature tracking and landmark recognition.

Estimation Landmark Recognition↗

DOE OSTI2025

Computer Vision Pipeline for Image Analysis for Freeze‐Fracture Electron Microscopy: Rosette Cellulose Synthase Complexes Case

In materials science, plant biology, agriculture, and environmental research, the automated analysis of high-magnification, complex microscopy images, such as those generated by freeze-fracture electron microscopy (FF-TEM), remains a critical challenge that limits the scalability of data interpretation. We present a deep learning computer vision pipeline for high-throughput detection and morphological characterization analysis of cellulose synthase complexes (CSCs, or rosettes) in FF-TEM images. The pipeline integrates preprocessing, detection, human-in-the-loop verification, and semantic segmentation to quantify features such as rosette diameter and inter-lobe spacing. The approach was trained and tested on a curated dataset of high-resolution FF-TEM micrographs of Physcomitrium patens, expanded via strategic tiling and augmentation to over 650 images. We compare YOLOv8 and YOLOv9 architectures and demonstrate that YOLOv9 achieves superior performance in both localization accuracy (mAP50-95 = 0.854) and inference speed. The resulting distributions revealed biological variability consistent with prior manual studies, validating the approach for high-throughput applications. Our results show that the pipeline achieves human-expert level accuracy while dramatically reducing analysis time, enabling scalable, reproducible structural characterization of intramembrane protein complexes. The pipeline is broadly applicable to other domains requiring precise interpretation of complex microscopy data and establishes a foundation for future artificial intelligence (AI)-assisted workflows in biological imaging.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

The role of driver head pose dynamics and instantaneous driving in safety critical events: Application of computer vision in naturalistic driving

This paper investigates the role of driver behavior especially head pose dynamics in safety–critical events (SCEs). Using a large dataset collected in a naturalistic driving study, this paper analyzes the head pose dynamics and driving behavior in moments leading up to crashes or near-crashes. The study uses advanced computer vision and mixed logit modeling techniques to identify patterns and relationships between drivers’ head pose dynamics and crash involvement. The results suggest that driver-head pose dynamics, especially poses that indicate distraction and movement volatility, are important factors that can contribute to undesirable safety outcomes. Marginal effects show that angular deviation for head pose dynamics indicated by yaw, pitch and roll increase the likelihood of crash intensity by 4.56%, 4.92% and 8.26% respectively. Furthermore, traffic flow and lane changing also contribute to increase in likelihood of crash intensity. These findings provide new insights into pre-crash factors, especially human factors and safety–critical events. The study highlights the importance of considering human factors in designing driver assistance systems and developing safer vehicles. This research contributes by examining naturalistic driving data at the microscopic level with early detection of behaviors that lead to SCEs and provides a basis for future research on automation.

33 ADVANCED PROPULSION SYSTEMS↗