Engineering Papers⌕ Search

SEARCH · Engineering Papers

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.

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

At least 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

TOWARDS RAPID RESPONSE UPDATES OF POPULATIONS AT RISK

Understanding population at risks has been a focus of the LandScan program through its development of population estimates. With advancements in computer vision, deep learning technologies and access to High Performance Computing (HPC) and high resolution imagery, population estimates are now modeled at the building level. However, when those patterns are disrupted, rapid updates to population distribution estimates are needed to support humanitarian aid and response. Oak Ridge National Laboratory (ORNL) recently adapted an existing deep learning building footprint extraction model in development of a scalable approach to Building Damage Assessments (BDA). This new opportunity opens the possibility of automating BDA to support rapid population distribution estimate updates for geographic areas involved in geopolitical conflicts or natural events for humanitarian aid and response or where to focus recovery efforts. In addition, incorporate social surveys to further model human behavior under conflict or other scenarios that disrupt normal patterns of life.

Urban, Marie↗
DOE OSTI2025

AI-Driven Accelerated Inclusion Analysis for Energy Efficient Steelmaking (Final CRADA Report)

This was a collaborative effort between Lawrence Livermore National Security, LLC (LLNS) as manager and operator of Lawrence Livermore National Laboratory (LLNL) and ArcelorMittal USA Research LLC (“ArcelorMittal” as the Participant), to use scanning electron microscopy (SEM) images, computer vision and machine learning methods, and high-performance computing to accelerate the inclusion analysis process of liquid steel so that new methods can be used for near-real time process control on the shop floor.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Distilling Knowledge from Ensembles of Cluster-Constrained-Attention Multiple-Instance Learners for Whole Slide Image Classification

The peculiar nature of whole slide imaging (WSI), digitizing conventional glass slides to obtain multiple high resolution images which capture microscopic details of a patient’s histopathological features, has garnered increased interest from the computer vision research community over the last two decades. Given the unique computational space and time complexity inherent to gigapixel-size whole slide image data, researchers have proposed novel machine learning algorithms to aid in the performance of diagnostic tasks in clinical pathology. One effective algorithm represents a Whole slide image as a bag of smaller image patches, which can be represented as low-dimension image patch embeddings. Weakly supervised deep-learning methods, such as cluster-constrained-attention multiple instance learning (CLAM), have shown promising results when combined with image patch embeddings. While traditional ensemble classifiers yield improved task performance, such methods come with a steep cost in model complexity. Through knowledge distillation, it is possible to retain some performance improvements from an ensemble, while minimizing costs to model complexity. In this work, we implement a weakly supervised ensemble using clustering-constrained-attention multiple-instance learners (CLAM), which uses attention and instance-level clustering to identify task salient regions and feature extraction in whole slides. By applying logit-based and attention-based knowledge distillation, we show it is possible to retain some performance improvements resulting from the ensemble at zero cost to model complexity.

Alamudun, Folami↗
DOE OSTI2024

Automated Inspection of Criticality Control Overpacks for Surplus Plutonium Disposition: Qualification Update – 25313

In an effort to reduce the amount of nuclear waste in South Carolina, the Department of Energy (DOE) tasked the Savannah River Site (SRS) with diluting and disposing of the amount of plutonium in the state. This process involves the movement and shipment of over 100,000 criticality control overpacks (CCOs) throughout the project lifespan, lending itself to the use of automation to reduce worker radiation exposure and more efficiently utilize human capital. Due to the large scope, this overarching process was broken down into several different “automation projects” to be developed. The first opportunity pursued was the receipt and inspection of empty CCO drums coming into SRS, identified as Automation Project 1 (AP1), and is the focus of this paper. AP1 was developed to unpack incoming CCOs and inspect them for unwanted foreign objects and any damage to the drum or its contents. This process is accomplished by the combination of an automated guided vehicle (AGV) that delivers CCOs to a robotic arm which uses a suite of custom tools to disassemble a CCO, inspect the inside and outside of the CCO and its inner criticality control container (CCC), reassemble the CCC and CCO, and apply a tamper indicating device (TID) to the inspected drum. In past years, the robotic work cell had been developed in a small-scale testing facility for proof-of-concept. This year, major improvements were made to the robotic work cell to perform the process, including integration into the final facility where CCOs will be inspected. Other technical improvements include the implementation of sensor feedback and safety relays into the control system to allow the state of the work cell to be better tracked, and additional development of the TID application process to complete the robotic inspection. Further enhancements were made to the robotic vision processes and robot pathing, as well as development on a computer vision inspection process to detect inspection criteria anomalies in CCOs. In addition to developmental improvements, the work cell underwent a six-month testing period to ensure the project requirements were met. Results of this testing period demonstrate the work cell’s capability to meet project throughput goals at an acceptable level, successfully document the status of each CCO inspected, and reduce the toll on technical operations’ human power by two thirds. At the time of this paper, the work cell is capable of autonomously handling up to eight CCOs with an AGV, delivering CCOs to and from the robot work cell, and having a robotic arm perform a full receipt and inspection procedure on each CCO. Moving forward, repeatability will be improved so that these CCOs can be run back-to-back seamlessly, as well as improving the system to handle more significant edge cases and failure modes.

Spivey, Nicholas↗
DOE OSTI2023

A survey of techniques for optimizing transformer inference

Recent years have seen a phenomenal rise in the performance and applications of transformer neural networks. The family of transformer networks, including Bidirectional Encoder Representations from Transformer (BERT), Generative Pretrained Transformer (GPT) and Vision Transformer (ViT), have shown their effectiveness across Natural Language Processing (NLP) and Computer Vision (CV) domains. Transformer-based networks such as ChatGPT have impacted the lives of common men. However, the quest for high predictive performance has led to an exponential increase in transformers' memory and compute footprint. Researchers have proposed techniques to optimize transformer inference at all levels of abstraction. Further, this paper presents a comprehensive survey of techniques for optimizing the inference phase of transformer networks. We survey techniques such as knowledge distillation, pruning, quantization, neural architecture search and lightweight network design at the algorithmic level. We further review hardware-level optimization techniques and the design of novel hardware accelerators for transformers. We summarize the quantitative results on the number of parameters/FLOPs and the accuracy of several models/techniques to showcase the tradeoff exercised by them. We also outline future directions in this rapidly evolving field of research. We believe that this survey will educate both novice and seasoned researchers and also spark a plethora of research efforts in this field.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Radsource Mr: Mixed Reality Planning Tool For Radioactive Recovery

The RadSource MR system leverages Meta Quest 3's advanced mixed reality capabilities to create a comprehensive spatial planning platform for end-of-life sealed radioactive source recovery operations. The application utilizes the Quest 3's high-resolution passthrough cameras and spatial mapping algorithms to generate accurate 3D environmental models. Core technical components include: (1) Real-time spatial measurement algorithms calculating distances, angles, slopes, and surface areas with sub-centimeter accuracy; (2) Virtual object placement system allowing users to position digital representations of recovery equipment (trailers, containment vessels, protective barriers) within the real environment; (3) Voice recording and annotation system for hands-free documentation in protective equipment; (4) 3D mesh capture and storage capabilities for post-operation analysis and regulatory documentation. (5) Procedure documentation is available for viewing in Mixed Reality, providing an innovative and convenient way to access the information during pre-visit and inspection activities. (6) Support for screen capture for the view for real world and virtual objects together to use it later for planning. The system integrates computer vision techniques for environmental understanding, spatial mathematics for precise measurements, and human-computer interaction principles optimized for hazardous environment operations. Data persistence allows teams to save and share planning sessions across multiple stakeholders while maintaining operational security requirements.

Khadka, Rajiv [Idaho National Laboratory (INL), Id↗
DOE OSTI2017

Managing the Performance/Error Tradeoff of Floating-point Intensive Applications

Modern embedded systems are becoming more reliant on real-valued arithmetic as they employ mathematically complex vision algorithms and sensor signal processing. Double-precision floating point is the most commonly used precision in computer vision algorithm implementations. A single-precision floating point can provide a performance boost due to less memory transfers, less cache occupancy, and relatively faster mathematical operations on some architectures. However, adopting it can result in loss of accuracy. Identifying which parts of the program can run in single-precision floating point with low impact on error is a manual and tedious process. In this paper, we propose an automatic approach to identify parts of the program that have a low impact on error using shadow-value analysis. Our approach provides the user with a performance/error tradeoff, using which the user can decide how much accuracy can be sacrificed in return for performance improvement. We illustrate the impact of the approach using a well known implementation of Apriltag detection used in robotics vision. In conclusion, we demonstrate that an average 1.3x speedup can be achieved with no impact on tag detection, and a 1.7x speedup with only 4% false negatives.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

QuGAN: A Quantum State Fidelity based Generative Adversarial Network

In the recent years, Generative Adversarial Networks (GANs) have been arguably one of the largest strides forward in Deep Learning. Many papers illustrate the use of GANs to accomplish extremely impressive goals, such as text-to-image or image augmentation. Specifically, GANs have seen this success in the computer vision domain. However, GANs are not without their own set of problems. GANs are computationally expensive, sometimes computationally prohibitive, and can suffer a multitude of convergence problems. As research on classical GANs continues to push the topic further, a branch of GANs, namely Quantum GANs, has seen research interest in the past years. In this work, we intend to push this research further with an illustration of a Quantum GAN architecture that provide stable convergence of the model and is extended onto real data sets. Furthermore, unlike many other Quantum GANs out there, our model's GAN architecture runs the discriminator and the generator primarily on Quantum hardware through the use of a Quantum-based similarity metric. When compared to the very few other Quantum GAN papers, our architecture leads to significantly better results in almost all aspects.

Stein, Samuel A.↗
DOE OSTI2023

DLIO: A DATA-CENTRIC BENCHMARK FOR DEEP LEARNING APPLICATIONS

SF-22-136 Deep learning has been shown as a successful method for various tasks, and its popularity results in numerous open-source deep learning software tools. Deep learning has been applied to a broad spectrum of scientific domains such as cosmology, particle physics, computer vision, fusion, and astrophysics. Scientists have performed a great deal of work to optimize the computational performance of deep learning frameworks. However, the same cannot be said for I/O performance. As deep learning algorithms rely on big-data volume and variety to effectively train neural networks accurately, I/O is a significant bottleneck on large-scale distributed deep learning training. DLIO, is a novel representative benchmark suite built based on the I/O profiling of the selected workloads. DLIO can be utilized to accurately emulate the I/O behavior of modern deep learning applications. Using DLIO, application developers and system software solution architects can identify potential I/O bottlenecks in their applications and guide optimizations to boost the I/O performance leading to lower training times. The storage vendor can also use DLIO as a guide for designing and optimize the storage and filesystem targeting at deep learning application.

ZHENG, HUIHUO↗
DOE OSTI2024

Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm

Inspections of concrete bridges across the United States represent a significant commitment of resources, given their biannual mandate for many structures. With a notable number of aging bridges, there is an imperative need to enhance the efficiency of these inspections. This study harnessed the power of computer vision to streamline the inspection process. Our experiment examined the efficacy of a state-of-the-art Visual Transformer (ViT) model combined with distinct image enhancement detector algorithms. We benchmarked against a deep learning Convolutional Neural Network (CNN) model. These models were applied to over 20,000 high-quality images from the Concrete Images for Classification dataset. Traditional crack detection methods often fall short due to their heavy reliance on time and resources. This research pioneers bridge inspection by integrating ViT with diverse image enhancement detectors, significantly improving concrete crack detection accuracy. Notably, a custom-built CNN achieves over 99% accuracy with substantially lower training time than ViT, making it an efficient solution for enhancing safety and resource conservation in infrastructure management. These advancements enhance safety by enabling reliable detection and timely maintenance, but they also align with Industry 4.0 objectives, automating manual inspections, reducing costs, and advancing technological integration in public infrastructure management.

42 ENGINEERING↗
DOE OSTI2020

Machine Vision-based Robot Manipulators for Nuclear Applications - 20370

Decommissioning and dismantling of nuclear facilities are major challenges facing the nuclear industry. Robot manipulators with capabilities of restoring nuclear structures and significantly prolonging nuclear power generation in addition to their applications in decommissioning and dismantling (D and D) would immensely ease the above-mentioned challenge. Ability to remotely sense/monitor and analyze dangerous and hazardous environments such as nuclear reactors as well as performing reparatory tasks in such environments using robot manipulators require additional information from vision sensors. Structural sample collection and inspection as well as restoration require object and position information. Computer vision is used to obtain precise 3D position information. The current work uses the Sawyer robot with the integrated Cognex camera. The research presents an approach to facilitate and improve operations in a nuclear reactor using robotic vision control. The vision control system is modeled with Augmented Image Space-based visual servoing approach. Results showing accurate robot control. Object recognition is used to recognize the image and calculate it poses. To transform coordinates of the object's pose from the camera frame to the robotic frame transformation matrices are employed. Future work will employ a 3D camera (with depth information) using Denso robot. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2022

Development of an end state vision to implement digital monitoring in nuclear plants

Transitioning from an onsite Maintenance & Diagnostics Center to cloud-based services offers many new opportunities with computing power and storage, but also new challenges in terms of networking and security. This report will cover everything required for that transition including data processing and uploading to cloud services, feature selection, model creation, and result visualization for decision making. Although there are several other cloud-based services (e.g. Amazon Web Services and Google Cloud), this report explores Microsoft Azure to simplify nomenclature and maintain a consistent focus. Many of the services offered by Microsoft Azure are also available in the other cloud-based services, and their differences have been recorded in other literature. The Azure services most important to a nuclear power plant including networking & security, storage & databases, and Artificial Intelligence (AI) are reviewed here. Networking covers all aspects related to communication to Azure resources including security, privacy, and redundancy. Storage & databases includes data storage, upgrading, patching, backups, and monitoring. The AI services allows the user access to the machine learning (ML) techniques developed with Azure including automated ML, anomaly detection, computer vision, and natural language processing. This report summaries the features, capabilities, and challenges when using cloud-based services in a user-friendly manner.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Neural Architecture Search Benchmarks: Insights and Survey

Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset. NAS methods have been very successful in discovering efficient models for various Computer Vision, Natural Language Processing, etc. The major obstacles to the advancement of NAS techniques are the demand for large computation resources and fair evaluation of various search methods. The differences in training pipeline and setting make it challenging to compare the efficiency of two NAS algorithms. A large number of NAS Benchmarks to simulate the architecture evaluation in seconds have been released over the last few years to ease the computation burden of training neural networks and can aid in the unbiased assessment of different search methods. This paper provides an extensive review of several publicly available NAS Benchmarks in the literature. We provide technical details and a deeper understanding of each benchmark and point out future directions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Development of an Energy Efficient and Cost Effective Autonomous Vehicle Research Platform

Commercialization of autonomous vehicle technology is a major goal of the automotive industry, thus research in this space is rapidly expanding across the world. However, despite this high level of research activity, literature detailing a straightforward and cost-effective approach to the development of an AV research platform is sparse. To address this need, we present the methodology and results regarding the AV instrumentation and controls of a 2019 Kia Niro which was developed for a local AV pilot program. This platform includes a drive-by-wire actuation kit, Aptiv electronically scanning radar, stereo camera, MobilEye computer vision system, LiDAR, inertial measurement unit, two global positioning system receivers to provide heading information, and an in-vehicle computer for driving environment perception and path planning. Robotic Operating System software is used as the system middleware between the instruments and the autonomous application algorithms. After selection, installation, and integration of these components, our results show successful utilization of all sensors, drive-by-wire functionality, a total additional power* consumption of 242.8 Watts (*Typical), and an overall cost of $118,189 USD, which is a significant saving compared to other commercially available systems with similar functionality. This vehicle continues to serve as our primary AV research and development platform.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

Pretraining Billion-Scale Geospatial Foundational Models on Frontier

As AI workloads increase in scope, generalization capability becomes challenging for small task-specific models and their demand for large amounts of labeled training samples increases. On the contrary, Foundation Models (FMs) are trained with internet-scale unlabeled data via self-supervised learning and have been shown to adapt to various tasks with minimal fine-tuning. Although large FMs have demonstrated significant impact in natural language processing and computer vision, efforts toward FMs for geospatial applications have been restricted to smaller size models, as pretraining larger models requires very large computing resources equipped with state-of-the-art hardware accelerators. Current satellite constellations collect 100+TBs of data a day, resulting in images that are billions of pixels and multimodal in nature. Such geospatial data poses unique challenges opening up new opportunities to develop FMs. We investigate billion scale FMs and HPC training profiles for geospatial applications by pretraining on publicly available data. We studied from end-to-end the performance and impact in the solution by scaling the model size. Our larger 3B parameter size model achieves up to 30% improvement in top1 scene classification accuracy when comparing a 100M parameter model. Moreover, we detail performance experiments on the Frontier supercomputer, America's first exascale system, where we study different model and data parallel approaches using PyTorch's Fully Sharded Data Parallel library. Specifically, we study variants of the Vision Transformer architecture (ViT), conducting performance analysis for ViT models with size up to 15B parameters. By discussing throughput and performance bottlenecks under different parallelism configurations, we offer insights on how to leverage such leadership-class HPC resources when developing large models for geospatial imagery applications.

Tsaris, Aristeidis (aris)↗
DOE OSTI2017

Genten: Software for Generalized Tensor Decompositions v. 1.0.0

Tensors, or multidimensional arrays, are a powerful mathematical means of describing multiway data. This software provides computational means for decomposing or approximating a given tensor in terms of smaller tensors of lower dimension, focusing on decomposition of large, sparse tensors. These techniques have applications in many scientific areas, including signal processing, linear algebra, computer vision, numerical analysis, data mining, graph analysis, neuroscience and more. The software is designed to take advantage of parallelism present emerging computer architectures such has multi-core CPUs, many-core accelerators such as the Intel Xeon Phi, and computation-oriented GPUs to enable efficient processing of large tensors.

Phipps, EricT.↗
DOE OSTI2025

Pulsed Infrared Thermography Nondestructive Imaging of SiC-SiC f Composite Cladding Architectures; Understanding the Performance of SiC-SiC f Composite Cladding Architectures with Cr Coating in Normal Operating and Accident Conditions in LWRs and Advanced Reactors

SiC-SiC f composites, consisting of silicon carbide fibers embedded in a silicon carbide matrix, are advanced materials with high thermal conductivity, temperature stability, and resistance to radiation damage. Traditional methods for quality control of fabricated SiC-SiC f composites involve nondestructive evaluation (NDE) with X-ray computed tomography (XCT). However, XCT imaging of typical SiC-SiC f structures for cladding applications can involve several hours. In this project, we investigate an alternative approach to NDE of SiC-SiC f composites that involves rapid (on the order of seconds) imaging with Pulsed infrared thermography (PIT). PIT images of a planar SiC-SiC f specimen show the structure of the surface monolith layer and internal SiC f structures. The capability of PIT imaging in visualizing SiC f structures is qualitatively confirmed by observing similarity in the PIT and X-ray transmission images of the same specimen. Computer vision analysis of defects in the PIT image of the monolith was performed with thresholding followed by topological structural analysis that computed geometric descriptors, including major/minor axes of fitted ellipses, area, perimeter, Feret diameter, circularity, roundness, and solidity.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2019

GeoAI: spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond

Recent progress in Artificial Intelligence (AI) techniques, the large-scale availability of high-quality data, as well as advances in both hardware and software to efficiently process these data, are transforming a range of fields from computer vision and natural language processing to autonomous driving and healthcare. For example, the availability of high-resolution geographic data and high-performance computing techniques together with deep learning fuel progress in fast and accurate object detection. Recent examples of GeoAI work include the detections of terrain features and densely-distributed building footprints, information extraction from scanned historical maps, semantic classification (e.g. LiDAR point clouds), novel methods for spatial interpolation, and advances in traffic forecasting. Similarly, machine learning and natural language processing are facilitating the extraction of geographic information from unstructured (textual) data, such as news articles and Wikipedia as well as the matching of natural features in multiple gazetteers.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗