SEARCH · Search NASA

Results for “Computer Vision”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 289 records · Page 16

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Mode-multiplexed photonic integrated vector dot-product core from inverse design

Photonic computing has the potential to harness the full degrees of freedom (DOFs) of the light field, including the wavelength, spatial mode, spatial location, phase quadrature, and polarization, to achieve a higher level of computing parallelism and scalability than digital electronic processors. While multiplexing using the wavelength and other DOFs can be readily integrated on silicon photonics platforms with compact footprints, conventional mode-division multiplexed (MDM) photonic designs occupy areas exceeding tens to hundreds of microns for a few spatial modes, significantly limiting their scalability. Here, we utilize inverse design to demonstrate an ultracompact photonic computing core that calculates vector dot products based on MDM coherent mixing. Our dot-product core integrates the functionalities of two-mode multiplexers and one multimode coherent mixer within a nominal footprint of 5 μm x 3 μm . We have experimentally demonstrated computing examples on the fabricated dot-product core, including complex number multiplication and motion estimation using optical flow. The compact dot-product core design enables large-scale on-chip integration in a parallel photonic computing primitive cluster for high-throughput scientific computing and computer vision tasks.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

The role of chromatin state in intron retention: A case study in leveraging large scale deep learning models

Complex deep learning models trained on very large datasets have become key enabling tools for current research in natural language processing and computer vision. By providing pre-trained models that can be fine-tuned for specific applications, they enable researchers to create accurate models with minimal effort and computational resources. Large scale genomics deep learning models come in two flavors: the first are large language models of DNA sequences trained in a self-supervised fashion, similar to the corresponding natural language models; the second are supervised learning models that leverage large scale genomics datasets from ENCODE and other sources. We argue that these models are the equivalent of foundation models in natural language processing in their utility, as they encode within them chromatin state in its different aspects, providing useful representations that allow quick deployment of accurate models of gene regulation. We demonstrate this premise by leveraging the recently created Sei model to develop simple, interpretable models of intron retention, and demonstrate their advantage over models based on the DNA language model DNABERT-2. Our work also demonstrates the impact of chromatin state on the regulation of intron retention. Using representations learned by Sei, our model is able to discover the involvement of transcription factors and chromatin marks in regulating intron retention, providing better accuracy than a recently published custom model developed for this purpose.

Biochemistry & Molecular Biology↗

NASA NTRS2022

Virtual Assistant for First Responders Using Natural Language Understanding and Optical Character Recognition

Commercial deep learning capabilities are available for many applications such as computer vision processing and intelligent chat bots. The Google Cloud Platform product Google Dialogflow provides lifelike conversational artificial intelligence (AI) using machine learning (ML) to generate natural conversations between computers and humans. This ML utilizes natural language understanding (NLU) to recognize a user’s intent and extracts key information into a form of entities. We have developed a user-friendly application through understanding the hazardous material database, first aid safety guidelines and observing the process of first responders who access this information in the field. We created the Trusted and Explainable Artificial Intelligence for Saving Lives (TruePAL) virtual assistant using Dialogflow1 and TensorFlow2 paired with EasyOCR.3 The chatbot supports first responders by providing voice interaction which helps limit additional steps such as browsing through multiple categories when searching for information. Using feedback from our field interviews, the voice interface has been developed to enable the first responder to focus on the immediate emergency. With less distractions, the first responder is able to engage the incident more effectively. The partial hands-free TruePAL chatbot assistant improves the accessibility to the correct guidance by an average of 1.9 seconds compared to the widely used application, NIH WISER, which requires full attention to operate. We combined this intelligent chatbot with a separate visual processing capability to produce hazardous signage analysis and generate the proper guidance for first responders. With the evolving functionality of AI tools, the use of virtual assistants in first responder technology will be an advancement, benefiting the safety of both first responders and civilians.

Chow, Edward↗

DOE OSTI2011

Error Detection, Factorization and Correction for Multi-View Scene Reconstruction from Aerial Imagery

Scene reconstruction from video sequences has become a prominent computer vision research area in recent years, due to its large number of applications in fields such as security, robotics and virtual reality. Despite recent progress in this field, there are still a number of issues that manifest as incomplete, incorrect or computationally-expensive reconstructions. The engine behind achieving reconstruction is the matching of features between images, where common conditions such as occlusions, lighting changes and texture-less regions can all affect matching accuracy. Subsequent processes that rely on matching accuracy, such as camera parameter estimation, structure computation and non-linear parameter optimization, are also vulnerable to additional sources of error, such as degeneracies and mathematical instability. Detection and correction of errors, along with robustness in parameter solvers, are a must in order to achieve a very accurate final scene reconstruction. However, error detection is in general difficult due to the lack of ground-truth information about the given scene, such as the absolute position of scene points or GPS/IMU coordinates for the camera(s) viewing the scene. In this dissertation, methods are presented for the detection, factorization and correction of error sources present in all stages of a scene reconstruction pipeline from video, in the absence of ground-truth knowledge. Two main applications are discussed. The first set of algorithms derive total structural error measurements after an initial scene structure computation and factorize errors into those related to the underlying feature matching process and those related to camera parameter estimation. A brute-force local correction of inaccurate feature matches is presented, as well as an improved conditioning scheme for non-linear parameter optimization which applies weights on input parameters in proportion to estimated camera parameter errors. Another application is in reconstruction pre-processing, where an algorithm detects and discards frames that would lead to inaccurate feature matching, camera pose estimation degeneracies or mathematical instability in structure computation based on a residual error comparison between two different match motion models. The presented algorithms were designed for aerial video but have been proven to work across different scene types and camera motions, and for both real and synthetic scenes.

42 ENGINEERING↗

NASA NTRS2018

The Next Wave: Humans, Computers, and Redefining Reality

The Augmented/Virtual Reality (AVR) Lab at KSC is dedicated to " exploration into the growing computer fields of Extended Reality and the Natural User Interface (it is) a proving ground for new technologies that can be integrated into future NASA projects and programs." The topics of Human Computer Interface, Human Computer Interaction, Augmented Reality, Virtual Reality, and Mixed Reality are defined; examples of work being done in these fields in the AVR Lab are given. Current new and future work in Computer Vision, Speech Recognition, and Artificial Intelligence are also outlined.

Extended Reality↗

NASA NTRS1987

Computer-aided analysis for the Mechanics of Granular Materials (MGM) experiment, part 2

Computer vision based analysis for the MGM experiment is continued and expanded into new areas. Volumetric strains of granular material triaxial test specimens have been measured from digitized images. A computer-assisted procedure is used to identify the edges of the specimen, and the edges are used in a 3-D model to estimate specimen volume. The results of this technique compare favorably to conventional measurements. A simplified model of the magnification caused by diffraction of light within the water of the test apparatus was also developed. This model yields good results when the distance between the camera and the test specimen is large compared to the specimen height. An algorithm for a more accurate 3-D magnification correction is also presented. The use of composite and RGB (red-green-blue) color cameras is discussed and potentially significant benefits from using an RGB camera are presented.

Parker, Joey K.↗

DOE OSTI2017

Parallel Asynchronous Distributed-Memory Maximal Independent Set Algorithm with Work Ordering

The maximal independent set (MIS) graph problem arises in many applications such as computer vision, information theory, molecular biology, and process scheduling. The growing scale of graph data suggests the use of distributed memory hardware as a cost-effective approach to providing necessary compute and memory resources. Existing distributed memory parallel MIS algorithms rely on synchronous communication and use techniques such as subgraph computations. In this paper, we present an asynchronous distributed-memory parallel graph algorithm that relies on a virtual directed acyclic graph (DAG) that is created during the algorithm execution. We introduce two additional algorithms that save computations by ordering generated work. The first algorithm applies ordering globally to reduce computations, and the second algorithm applies ordering locally at the level of threads to minimize the synchronization overhead. We use two different implementations of Luby’s algorithm variants as baseline to compare the performance of the presented algorithms: (1) vertex-centric Luby A and Luby B implementations, and (2) the CombBLAS linear-algebra Luby A implementation. Results show that proposed algorithms outperform both implementations of Luby algorithms, especially in distributed execution. Furthermore, we show that for low-diameter graphs the algorithm that applies global ordering scales better than other algorithms and for high diameter graphs the original asynchronous algorithm and thread-level ordering algorithm show better performance.

maximal independent set (MIS), distributed memory ↗

DOE OSTI2017

Distributed-Memory Fast Maximal Independent Set

The Maximal Independent Set (MIS) graph problem arises in many applications such as computer vision, information theory, molecular biology, and process scheduling. The growing scale of MIS problems suggests the use of distributed-memory hardware as a cost-effective approach to providing necessary compute and memory resources. Luby proposed four randomized algorithms to solve the MIS problem. All those algorithms are designed focusing on shared-memory machines and are analyzed using the PRAM model. These algorithms do not have direct efficient distributed-memory implementations. In this paper, we extend two of Luby’s seminal MIS algorithms, “Luby(A)” and “Luby(B),” to distributed-memory execution, and we evaluate their performance. We compare our results with the “Filtered MIS” implementation in the Combinatorial BLAS library for two types of synthetic graph inputs.

distributed memory parallel↗

NASA NTRS1987

Requirements and principles for the implementation and construction of large-scale geographic information systems

This paper provides a brief survey of the history, structure and functions of 'traditional' geographic information systems (GIS), and then suggests a set of requirements that large-scale GIS should satisfy, together with a set of principles for their satisfaction. These principles, which include the systematic application of techniques from several subfields of computer science to the design and implementation of GIS and the integration of techniques from computer vision and image processing into standard GIS technology, are discussed in some detail. In particular, the paper provides a detailed discussion of questions relating to appropriate data models, data structures and computational procedures for the efficient storage, retrieval and analysis of spatially-indexed data.

Smith, Terence R.↗

DOE OSTI2021

Watch and learn—a generalized approach for transferrable learning in deep neural networks via physical principles

Transfer learning refers to the use of knowledge gained while solving a machine learning task and applying it to the solution of a closely related problem. Such an approach has enabled scientific breakthroughs in computer vision and natural language processing where the weights learned in state-of-the-art models can be used to initialize models for other tasks which dramatically improve their performance and save computational time. Here we demonstrate an unsupervised learning approach augmented with basic physical principles that achieves fully transferrable learning for problems in statistical physics across different physical regimes. By coupling a sequence model based on a recurrent neural network to an extensive deep neural network, we are able to learn the equilibrium probability distributions and inter-particle interaction models of classical statistical mechanical systems. Our approach, distribution-consistent learning, DCL, is a general strategy that works for a variety of canonical statistical mechanical models (Ising and Potts) as well as disordered interaction potentials. Using data collected from a single set of observation conditions, DCL successfully extrapolates across all temperatures, thermodynamic phases, and can be applied to different length-scales. This constitutes a fully transferrable physics-based learning in a generalizable approach.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2005

An estimation algorithm for vision-based exploration of small bodies in space

This paper summarizes a methodology for designing on-board state estimators in support of spacecraft exploration of small bodies such as asteroids and comets. This paper will focus on an estimation algorithm that incorporates two basic computer-vision measurement types: a Landmark Table and a Paired Feature Table. Several innovations are developed to incorporate these measurement types into the onboard state estimation algorithm. Simulations are provided to demonstrate the feasibility of the approach.

Brugarolas, Paul B.↗

NASA NTRS2002

Flexible Wing Base Micro Aerial Vehicles: Vision-Guided Flight Stability and Autonomy for Micro Air Vehicles

Substantial progress has been made recently towards design building and test-flying remotely piloted Micro Air Vehicle's (MAVs). We seek to complement this progress in overcoming the aerodynamic obstacles to.flight at very small scales with a vision stability and autonomy system. The developed system based on a robust horizon detection algorithm which we discuss in greater detail in a companion paper. In this paper, we first motivate the use of computer vision for MAV autonomy arguing that given current sensor technology, vision may he the only practical approach to the problem. We then briefly review our statistical vision-based horizon detection algorithm, which has been demonstrated at 30Hz with over 99.9% correct horizon identification. Next we develop robust schemes for the detection of extreme MAV attitudes, where no horizon is visible, and for the detection of horizon estimation errors, due to external factors such as video transmission noise. Finally, we discuss our feed-back controller for self-stabilized flight, and report results on vision autonomous flights of duration exceeding ten minutes.

Ettinger, Scott M.↗

DOE OSTI2025

An AI-Based 3D Bat Movement Tracking System at Wind Energy Facilities Using Multi-Thermal Video Cameras

The talk at the NAWEA Wind Tech 2024 conference discusses how to leverage the potential of real-time thermal-imaging methodologies in quantifying nocturnal bat activities at wind turbines, using 3D computer vision techniques within a deep learning framework. This innovation enables the automatic detection and classification of bats, birds, and insects in thermal-imaging videos captured at wind turbine sites, facilitating efficient and accurate data analysis for enhanced understanding and mitigation of bat-wind turbine interactions.

AI↗

DOE OSTI2016

SU-F-I-45: An Automated Technique to Measure Image Contrast in Clinical CT Images

Purpose: To develop and validate an automated technique for measuring image contrast in chest computed tomography (CT) exams. Methods: An automated computer algorithm was developed to measure the distribution of Hounsfield units (HUs) inside four major organs: the lungs, liver, aorta, and bones. These organs were first segmented or identified using computer vision and image processing techniques. Regions of interest (ROIs) were automatically placed inside the lungs, liver, and aorta and histograms of the HUs inside the ROIs were constructed. The mean and standard deviation of each histogram were computed for each CT dataset. Comparison of the mean and standard deviation of the HUs in the different organs provides different contrast values. The ROI for the bones is simply the segmentation mask of the bones. Since the histogram for bones does not follow a Gaussian distribution, the 25th and 75th percentile were computed instead of the mean. The sensitivity and accuracy of the algorithm was investigated by comparing the automated measurements with manual measurements. Fifteen contrast enhanced and fifteen non-contrast enhanced chest CT clinical datasets were examined in the validation procedure. Results: The algorithm successfully measured the histograms of the four organs in both contrast and non-contrast enhanced chest CT exams. The automated measurements were in agreement with manual measurements. The algorithm has sufficient sensitivity as indicated by the near unity slope of the automated versus manual measurement plots. Furthermore, the algorithm has sufficient accuracy as indicated by the high coefficient of determination, R2, values ranging from 0.879 to 0.998. Conclusion: Patient-specific image contrast can be measured from clinical datasets. The algorithm can be run on both contrast enhanced and non-enhanced clinical datasets. The method can be applied to automatically assess the contrast characteristics of clinical chest CT images and quantify dependencies that may not be captured in phantom data.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2012

Edge Detection and Shape Recognition in Neutron Transmission Images

Neutron transmission measurements are a valuable tool for nondestructively imaging special nuclear materials. Analysis of these images, however, tends to require significant user interaction to determine the sizes, shapes, and likely compositions of measured objects. Computer vision (CV) techniques can be a useful approach to automatically extracting important information from either neutron transmission images or fission-site-mapping images. An automatable approach has been developed that processes an input image and, through recursive application of CV techniques, produces a set of basic shapes that define surfaces observed in the image. These shapes can then be compared to a library of known shape configurations to determine if the measured object matches its expected configuration, as could be done behind an information barrier for arms control treaty verification inspections.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2023

Providing Geospatial Intelligence through a Scalable Imagery Pipeline

This chapter describes ORNL’s (Oak Ridge National Laboratory’s) contributions to imagery preprocessing for geospatial intelligence research and development (R&D) in four sections. First, we discuss challenges involved in building an effective imagery preprocessing workflow and the world-class high-performance computing (HPC) resources at ORNL available to process petabytes of imagery data. Second, we highlight how we developed imagery preprocessing tools over three decades while paving the way for our current cutting-edge machine learning and computer vision algorithms that are impacting humanitarian and disaster response efforts. Third, we discuss how PIPE modules work together to turn raw images into analysis-ready datasets. Fourth, we look toward the future and discuss planned advancements to PIPE and computing trends that will affect geospatial intelligence R&D.

Reith, Andrew↗

DOE OSTI2016

Nonlocal atlas-guided multi-channel forest learning for human brain labeling

Purpose: It is important for many quantitative brain studies to label meaningful anatomical regions in MR brain images. However, due to high complexity of brain structures and ambiguous boundaries between different anatomical regions, the anatomical labeling of MR brain images is still quite a challenging task. In many existing label fusion methods, appearance information is widely used. However, since local anatomy in the human brain is often complex, the appearance information alone is limited in characterizing each image point, especially for identifying the same anatomical structure across different subjects. Recent progress in computer vision suggests that the context features can be very useful in identifying an object from a complex scene. In light of this, the authors propose a novel learning-based label fusion method by using both low-level appearance features (computed from the target image) and high-level context features (computed from warped atlases or tentative labeling maps of the target image). Methods: In particular, the authors employ a multi-channel random forest to learn the nonlinear relationship between these hybrid features and target labels (i.e., corresponding to certain anatomical structures). Specifically, at each of the iterations, the random forest will output tentative labeling maps of the target image, from which the authors compute spatial label context features and then use in combination with original appearance features of the target image to refine the labeling. Moreover, to accommodate the high inter-subject variations, the authors further extend their learning-based label fusion to a multi-atlas scenario, i.e., they train a random forest for each atlas and then obtain the final labeling result according to the consensus of results from all atlases. Results: The authors have comprehensively evaluated their method on both public LONI-LBPA40 and IXI datasets. To quantitatively evaluate the labeling accuracy, the authors use the dice similarity coefficient to measure the overlap degree. Their method achieves average overlaps of 82.56% on 54 regions of interest (ROIs) and 79.78% on 80 ROIs, respectively, which significantly outperform the baseline method (random forests), with the average overlaps of 72.48% on 54 ROIs and 72.09% on 80 ROIs, respectively. Conclusions: The proposed methods have achieved the highest labeling accuracy, compared to several state-of-the-art methods in the literature.

61 RADIATION PROTECTION AND DOSIMETRY↗

NASA NTRSDate not supplied

Imagery Analysis for Space Operations

The purpose of this project is to build a prototype camera system that utilizes artificial intelligence/machine learning and computer vision to track an object in 2D and recreate it in 3D.The goal is to improve image analysis and photogrammetry function for Pad 39B operations.

Computer Programming↗