Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Object detection”

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.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Developing a Deep Learning-Computer Vision Framework to Monitor Avian Interactions with Solar Energy Facility Infrastructure (Final Technical Report)

The project addressed an inability to monitor avian interactions with photovoltaic (PV) solar energy facilities necessary for understanding PV solar impacts on birds. In the project, machine-vision technology that continuously monitors avian activities at PV solar facilities was developed. The technology includes four machine-learning (ML) models, each of which accomplishes a specific task in detecting birds and classifying their activities in live or recorded videos—detecting and tracking moving objects, differentiating birds from other objects, detecting bird collisions with solar panels, and classifying non-collision bird activities around PV facilities. Major project outcomes include adoption by two of DOE SETO’s SolWEB projects, providing novel observational data on birds to promote co-location of PV solar development and habitat conservation, known as ecovoltaics.

14 SOLAR ENERGY↗
NASA NTRS1988

Meteorological and Environmental Inputs to Aviation Systems

Reports on aviation meteorology, most of them informal, are presented by representatives of the National Weather Service, the Bracknell (England) Meteorological Office, the NOAA Wave Propagation Lab., the Fleet Numerical Oceanography Center, and the Aircraft Owners and Pilots Association. Additional presentations are included on aircraft/lidar turbulence comparison, lightning detection and locating systems, objective detection and forecasting of clear air turbulence, comparative verification between the Generalized Exponential Markov (GEM) Model and official aviation terminal forecasts, the evaluation of the Prototype Regional Observation and Forecast System (PROFS) mesoscale weather products, and the FAA/MIT Lincoln Lab. Doppler Weather Radar Program.

Camp, Dennis W.↗
NASA NTRS1987

Knowledge-based vision for space station object motion detection, recognition, and tracking

Computer vision, especially color image analysis and understanding, has much to offer in the area of the automation of Space Station tasks such as construction, satellite servicing, rendezvous and proximity operations, inspection, experiment monitoring, data management and training. Knowledge-based techniques improve the performance of vision algorithms for unstructured environments because of their ability to deal with imprecise a priori information or inaccurately estimated feature data and still produce useful results. Conventional techniques using statistical and purely model-based approaches lack flexibility in dealing with the variabilities anticipated in the unstructured viewing environment of space. Algorithms developed under NASA sponsorship for Space Station applications to demonstrate the value of a hypothesized architecture for a Video Image Processor (VIP) are presented. Approaches to the enhancement of the performance of these algorithms with knowledge-based techniques and the potential for deployment of highly-parallel multi-processor systems for these algorithms are discussed.

Symosek, P.↗
DOE OSTI2026

INR-TEM: Robust cavity detection in multifocus TEM images via implicit neural representations

When characterizing materials using transmission electron microscopy (TEM) images, detecting and quantifying small features in microstructures, such as cavities, pose significant challenges. Off-the-shelf object detection models, including YOLOv8, show considerable performance degradation, particularly when images vary in resolution and the objects of interest possess a low percentage of the total image region of interest. In this study, we introduce a novel detection pipeline that incorporates an implicit neural representation (INR)-based detection method, INR-TEM, and two-modality imaging (e.g., under-focused and over-focused images typically acquired during materials characterization) to improve object detection performance. The INR-TEM method incorporates a pixel-wise prediction principle inspired by pixel-wise centerness weighting. INR-TEM demonstrates superior robustness to resolution variability, maintaining high detection accuracy even at low image resolutions compared to YOLOv8. To leverage INR-TEM effectively in real-world two-modality characterization applications, we further integrate a two-stage motion correction pipeline designed explicitly for aligning multifocus TEM images. The alignment process, comprising keypoint (based on scale-invariant feature transform, SIFT) and intensity matching, significantly mitigates the adverse effects of perceived motion-induced image degradation during through-focal TEM imaging, directly enhancing INR-TEM’s detection capability over conventional single-focus images. Our integrated INR-TEM cavity detection framework notably improves performance across various cavity sizes, outperforming off-the-shelf YOLOv8 detections that rely on a single image modality.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
NASA NTRS1978

A study of the IC 5146 dark cloud complex

The IC 5146 dark cloud complex has been studied in the infrared in order to identify and study associated young stellar objects. Most of the objects detected in the survey appear to be field stars, predominantly late-type giants. Three young objects were detected in the survey: the B0 star BD +46 deg 3474, the Ae star BD +46 deg 3471, and a previously unidentified object which appears to be a heavily obscured FU Orionis star. The properties of the last two objects are examined in detail, and an attempt is made to produce reasonable models for them. It is suggested that FU Orionis stars are binaries, and some consequences of this model are described. Photometry of the brighter stars in the IC 5146 cluster has been used to establish a distance to the cluster of 900 + or - 100 pc.

Elias, J. H.↗
NASA NTRS1979

Super-resolution imaging system

The resolution of an imaging system is greatly enhanced by radiating an object with a plane wave field from a coherent source variable in either frequency, angle or distance from the object, detecting the wave field transmitted through, or reflected from, the object at some point on the image of the object, with or without heterodyne detection, and with or without a lens system. The heterodyne detected output of the detector is processed to obtain the Fourier transform as a function of the variable for a direct measurement of the amplitude and surface height structure of the object within a resolution cell centered at the corresponding point on the object. In the case of no heterodyne detection, only intensity data is obtained for a Fourier spectrum.

Jain, Atul↗
NASA NTRS2010

The HST/ACS Coma Cluster Survey. II. Data Description and Source Catalogs

The Coma cluster, Abell 1656, was the target of a HST-ACS Treasury program designed for deep imaging in the F475W and F814W passbands. Although our survey was interrupted by the ACS instrument failure in early 2007, the partially-completed survey still covers approximately 50% of the core high density region in Coma. Observations were performed for twenty-five fields with a total coverage area of 274 aremin(sup 2), and extend over a wide range of cluster-centric radii (approximately 1.75 Mpe or 1 deg). The majority of the fields are located near the core region of Coma (19/25 pointings) with six additional fields in the south-west region of the cluster. In this paper we present SEXTRACTOR source catalogs generated from the processed images, including a detailed description of the methodology used for object detection and photometry, the subtraction of bright galaxies to measure faint underlying objects, and the use of simulations to assess the photometric accuracy and completeness of our catalogs. We also use simulations to perform aperture corrections for the SEXTRACTOR Kron magnitudes based only on the measured source flux and its half-light radius. We have performed photometry for 76,000 objects that consist of roughly equal numbers of extended galaxies and unresolved objects. Approximately two-thirds of all detections are brighter than F814W=26.5 mag (AB), which corresponds to the 10sigma, point-source detection limit. We estimate that Coma members are 5-10% of the source detections, including a large population of compact objects (primarily GCs, but also cEs and UCDs), and a wide variety of extended galaxies from cD galaxies to dwarf low surface brightness galaxies. The initial data release for the HST-ACS Coma Treasury program was made available to the public in August 2008. The images and catalogs described in this study relate to our second data release.

Hammer, Derek↗
NASA NTRSDate not supplied

Tracking the Hunga Tonga-Hunga Ha’apai Eruption Stratospheric Aerosol and Trace Gas Plumes Using Machine Learning

The Hunga Tonga-Hunga Ha’apai (HTHH) submarine volcano had an explosive eruption phase on January 15, 2022, that thrusted ash, gases, and water vapor through the troposphere and into the stratosphere. The stratospheric volcanic plume included aerosol precursor gases such as SO2 and H2S as well as anomalously high water vapor concentrations due to the submarine oceanic origin. With these atmospheric constituents, the sulfuric gases and water vapor formed sulfate (SO4) particles via gas-to-particle reactions and these aerosols likely increased in size due to hygroscopic growth within anomalously humid regions. Strong easterlies and gravity waves propagated the volcanic impacts throughout the stratosphere. Orbital and suborbital passive sensor retrievals detected changes in the aerosol and trace gas characteristics within the atmospheric column for cloud-free regions over the southern hemisphere. While the CALIPSO lidar can detect aerosol layers in the stratosphere, passive sensors such as MODIS retrieved the total column aerosol abundance and characteristics. Previous studies used manual tracking methods to determine volcanic plume positions and compared them to ground observations. In this study, we examine the machine learning (ML) approaches including segmentation, object detection, and object tracking to identify and track aerosol and trace gas plumes using orbital and suborbital sensor data. This ML implementation strives to provide a more systematic approach to separate total column effects from those of the stratosphere. Similar ML tracking may be useful for stratospheric impact events observed historically by CALIPSO and in the future with EarthCare and the Atmosphere Observing System (AOS) lidar-capable missions.

Rhys Leahy↗
NASA NTRS1977

The robot's eyes - Stereo vision system for automated scene analysis

Attention is given to the robot stereo vision system which maintains the image produced by solid-state detector television cameras in a dynamic random access memory called RAPID. The imaging hardware consists of sensors (two solid-state image arrays using a charge injection technique), a video-rate analog-to-digital converter, the RAPID memory, and various types of computer-controlled displays, and preprocessing equipment (for reflexive actions, processing aids, and object detection). The software is aimed at locating objects and transversibility. An object-tracking algorithm is discussed and it is noted that tracking speed is in the 50-75 pixels/s range.

Williams, D. S.↗
NASA NTRS2022

Robust Semantic Mapping and Localization on a Free-Flying Robot in Microgravity

We propose a system that uses semantic object detections to localize a microgravity free-flyer. Many applications require absolute localization in a known reference frame, such as the execution of waypoint trajectories defined by human operators. Classical geometric methods build a map of point features, which may not be able to be associated after lighting or environmental changes. By contrast, semantics remain invariant to changes up to the robustness of the detection algorithm and motion of the semantic objects. In this work, we describe our approaches for both offline semantic map generation as well as online localization against a semantic map, intended to run in real-time on the robot. We additionally demonstrate how our semantic localizer outperforms image-feature matching in some cases, and show the robustness of the algorithm to environmental changes. Crucially, we show in our experiments that when semantics are used to supplement point features, localization is always improved. To our knowledge, these experiments demonstrate the first use of learned semantics for localization on a free-flying robot in microgravity.

Localization↗
NASA NTRS2023

Automated Global-Scale Detection and Characterization of Anthropogenic Activity using Multi-Source Satellite-Based Remote Sensing Imagery

Satellite-based remote sensing imagery is an effective means for detecting objects and structures in support of many applications. However, detecting the spatial and temporal bounds of a specific activity in satellite imagery is inherently more complex and research in this area is nascent. One reason for this is that describing an activity implies defining both spatial and temporal bounds and while activity is inherently continuous in nature, the geospatial (imagery) time series for any particular swath of ground provided by satellite imagery is relatively sparse and discrete in comparison. The IARPA Space-Based Machine Automated Recognition Technique (SMART)1 program is the first large-scale research program to target advancing the state of the art for automatically detecting, characterizing, and monitoring large-scale anthropogenic activity in global, multispectral satellite imagery. The program has two primary research objectives: 1) the “harmonization” of multiple imagery sources and 2) automated reasoning at scale to detect, characterize, and monitor activities of interest. This paper provides details on the goals, dataset, metrics, and lessons learned of the IARPA SMART program. By releasing the annotated dataset, the program aims to foster additional research in this area by the community at large.

Hirsh R Goldberg↗
NASA NTRS2016

A Collision Avoidance Strategy for a Potential Natural Satellite around the Asteroid Bennu for the OSIRIS-REx Mission

The cadence of proximity operations for the OSIRIS-REx mission may have an extra induced challenge given the potential of the detection of a natural satellite orbiting the asteroid Bennu. Current ground radar observations for object detection orbiting Bennu show no found objects within bounds of specific size and rotation rates. If a natural satellite is detected during approach, a different proximity operation cadence will need to be implemented as well as a collision avoidance strategy for mission success. A collision avoidance strategy will be analyzed using the Wald Sequential Probability Ratio Test.

satellite↗
NASA NTRS2016

A Collision Avoidance Strategy for a Potential Natural Satellite Around the Asteroid Bennu for the OSIRIS-REx Mission

The cadence of proximity operations for the OSIRIS-REx mission may have an extra induced challenge given the potential of the detection of a natural satellite orbiting the asteroid Bennu. Current ground radar observations for object detection orbiting Bennu show no found objects within bounds of specific size and rotation rates. If a natural satellite is detected during approach, a different proximity operation cadence will need to be implemented as well as a collision avoidance strategy for mission success. A collision avoidance strategy will be analyzed using the Wald Sequential Probability Ratio Test.

bennu↗
DOE OSTI2024

Quantifying Streambed Grain Size, Uncertainty, and Hydrobiogeochemical Parameters Using Machine Learning Model YOLO

Abstract Streambed grain sizes control river hydro‐biogeochemical (HBGC) processes and functions. However, measuring their quantities, distributions, and uncertainties is challenging due to the diversity and heterogeneity of natural streams. This work presents a photo‐driven, artificial intelligence (AI)‐enabled, and theory‐based workflow for extracting the quantities, distributions, and uncertainties of streambed grain sizes from photos. Specifically, we first trained You Only Look Once, an object detection AI, using 11,977 grain labels from 36 photos collected from nine different stream environments. We demonstrated its accuracy with a coefficient of determination of 0.98, a Nash–Sutcliffe efficiency of 0.98, and a mean absolute relative error of 6.65% in predicting the median grain size of 20 ground‐truth photos representing nine typical stream environments. The AI is then used to extract the grain size distributions and determine their characteristic grain sizes, including the 10th, 50th, 60th, and 84th percentiles, for 1,999 photos taken at 66 sites within a watershed in the Northwest US. The results indicate that the 10th, median, 60th, and 84th percentiles of the grain sizes follow log‐normal distributions, with most likely values of 2.49, 6.62, 7.68, and 10.78 cm, respectively. The average uncertainties associated with these values are 9.70%, 7.33%, 9.27%, and 11.11%, respectively. These data allow for the computation of the quantities, distributions, and uncertainties of streambed HBGC parameters, including Manning's coefficient, Darcy‐Weisbach friction factor, top layer interstitial velocity magnitude, and nitrate uptake velocity. Additionally, major sources of uncertainty in grain sizes and their impact on HBGC parameters are examined.

58 GEOSCIENCES↗
NASA NTRS1991

Radar measurements of the orbital debris environment

The collection and preliminary processing of the first significant accumulation of orbital debris data collected by the Haystack radar is described. The data are collected in the 'beam park' mode of operation in which the radar stares in a fixed direction and debris randomly passes through the field of view. Haystack's processing system performed automatic real-time processing and threshold detection, and saved only data associated with a possible detection. Approximately 123 hours of data were collected with the radar beam parked at an elevation angle of 10 deg and an azimuth of 180 deg; 3.8 hours were collected at an elevation angle of 30 deg and an azimuth of 180 deg; and 33.9 hours were collected at an elevation angle of 90 deg. A computer model of the response of the Haystack radar while in beam park operation is described. The model calculates the probability of detection and collection area for all sizes and orbital inclinations of debris visible to the radar. At this time, the approximate sizes of the detected objects have not been determined. However, the observed detection rates and cumulative signal to noise ratio distributions agree well with the results of the radar response model using NASA's current orbital debris environment.

Stansbery, Eugene G.↗
NASA NTRS1991

Detection of earth-approaching asteroids in near real time

Computer software, called the Moving Object Detection Program (MODP), is described which detects earth-approaching asteroids in near real time. The software runs on a workstation linked to the output of the drift-scanning CCD camera of the Spacewatch Telescope. MOPD recognizes trailed images, detects motion, and accurately determines angular positions and rates of motion for moving objects in the scan images. The results are obtained a few seconds after the image signals are shifted out of the CCD. During 2 months of trial observations with this system, 304 asteroids were detected down to a limiting apparent magnitude for untrailed images of V = 20.5.

Rabinowitz, D. L.↗