Search NASA⌕ Search

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.

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

At least 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
DOE OSTI2013

MultiFacet: A Faceted Interface for Browsing Large Multimedia Collections

Faceted browsing is a common technique for exploring collections where the data can be grouped into a number of pre-defined categories, most often generated from textual metadata. Historically, faceted browsing has been applied to a single data type such as text or image data. However, typical collections contain multiple data types, such as information from web pages that contain text, images, and video. Additionally, when browsing a collection of images and video, facets are often created based on the metadata which may be incomplete, inaccurate, or missing altogether instead of the actual visual content contained within those images and video. In this work we address these limitations by presenting MultiFacet, a faceted browsing interface that supports multiple data types. MultiFacet constructs facets for images and video in a collection from the visual content using computer vision techniques. These visual facets can then be browsed in conjunction with text facets within a single interface to reveal relationships and phenomena within multimedia collections. Additionally, we present a use case based on real-world data, demonstrating the utility of this approach towards browsing a large multimedia data collection.

content-based image retrieval↗
DOE OSTI2024

Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations

Signal analysis and classification is fraught with high levels of noise and perturbation. Computer-vision-based deep learning models applied to spectrograms have proven useful in the field of signal classification and detection; however, these methods aren't designed to handle the low signal-to-noise ratios inherent within non-vision signal processing tasks. While they are powerful, they are currently not the method of choice in the inherently noisy and dynamic critical infrastructure domain, such as smart-grid sensing, anomaly detection, and non-intrusive load monitoring. Currently, these models can be brittle, which makes them susceptible to noisy input. This also means they have sub-optimal stability of explanation outputs. Experts and technicians using these models to make decisions in real world scenarios need assurance that a model is performing as it is supposed to. The classification or prediction outputs it generates should be sound and grounded, not likely to change in the presence of shifting noise landscapes. In this work, we explore the idea of Neural Stochastic Differential Equations (NSDE's) to improve the robustness of models trained to classify time series data and the effect of NSDE's on the explainability of outputs. We then test the effectiveness of these approaches by applying them to a non-intrusive load monitoring (NILM) dataset that consists of simulated harmonic signals injected into a real building.

Brogan, Joel↗
DOE OSTI2023

Cycle-by-cycle Delay Estimation at Signalized Intersections by using Machine Learning and Simulated Video Detection Data

Accurate estimation of delay is crucial for efficient traffic signal operations. Estimation of delay in the real-time manner using traditional loop detectors requires advanced detectors (in addition to stop-bar detection). In cases when this detection layout is not in place, delay estimates are approximated with a lower accuracy. Video detection is one of the most frequently deployed detection systems at signalized intersections in recent years. In most cases video detection operates in the same way as traditional inductive loops. However, when coupled with computer vision algorithms, video detection systems could be used to retrieve additional information (e.g., vehicular arrivals and departures) that cannot be taken out from the conventional systems (e.g., long stop-bar loop detectors). Although present for several decades, video detection data were not frequently examined for delay estimation purposes. In this study, we proposed a novel delay estimation model which can be developed with only data from stop-bar video detectors. Relevant data were collected from a simulation model of 11 signalized intersections at downtown Chattanooga, TN and processed to create needed inputs for model development. With the use of multigene genetic programming the authors developed a delay model that outperforms accuracy of multi regression model. Furthermore, authors evaluated the developed model by comparison with the other benchmark delay models, such as HCM and approach delay model. It was found that the developed MGGP delay model outperforms benchmark models for a wide range of traffic and signal operation conditions.

Erdagi, Ismet Goksad↗
DOE OSTI2019

Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids

The availability of fine grained time series data is a pre-requisite for research in smart-grids. While data for transmission systems is relatively easily obtainable, issues related to data collection, security and privacy hinder the widespread public availability/accessibility of such datasets at the distribution system level. This has prevented the larger research community from effectively applying sophisticated machine learning algorithms to significantly improve the distribution-level accuracy of predictions and increase the efficiency of grid operations. Synthetic dataset generation has proven to be a promising solution for addressing data availability issues in various domains such as computer vision, natural language processing and medicine. However, its exploration in the smart grid context remains unsatisfactory. Previous works have tried to generate synthetic datasets by modeling the underlying system dynamics: an approach which is difficult, time consuming, error prone and often times infeasible in many problems. In this work, we propose a novel data-driven approach to synthetic dataset generation by utilizing deep generative adversarial networks (GAN) to learn the conditional probability distribution of essential features in the real dataset and generate samples based on the learned distribution. To evaluate our synthetically generated dataset, we measure the maximum mean discrepancy (MMD) between real and synthetic datasets as probability distributions, and show that their sampling distance converges. To further validate our synthetic dataset, we perform common smart grid tasks such as k-means clustering and short-term prediction on both datasets. Experimental results show the efficacy of our synthetic dataset approach: the real and synthetic datasets are indistinguishable by solely examining the output of these tasks.

14 SOLAR ENERGY↗
DOE OSTI2022

Accelerating Hydraulic Fracture Imaging by Deep Transfer Learning

Deep transfer learning has a great success story in computer vision (CV), natural language processing, and many other fields. In this communication, we are going to push forward the deep transfer learning to the hydraulic fracture imaging problem by proposing a two-step approach: 1) train a convolutional neural network (CNN) to reconstruct target geometries by a relatively large amount of approximated field patterns generated from a simplified model and 2) fine-tune the top layers of transferred CNN by a small amount of true field patterns generated through a full model. The advantages include the rapid generation of large amount of data through the simplified model and the high reconstruction accuracy through a careful design of the deep transfer learning. Here, the CNN trained through the deep transfer learning can accurately reconstruct the lateral extent and direction of fractures with unseen conductivity and white Gaussian noise, showing a notable acceleration/accuracy enhancement over the previous CNN trained by mixing a small number of true data into the approximated data as data augmentation.

02 PETROLEUM↗
DOE OSTI2022

Model Assumptions and Data Characteristics: Impacts on Domain Adaptation in Building Segmentation

Studies on domain adaptation (DA) for remote sensing (RS) imagery analysis lack consistency in selection and description of evaluation scenarios. Without properly characterizing datasets, model assumptions, and evaluation scenarios, it is difficult to objectively compare DA methods and reach conclusions about their suitability across different applications. With this motivation, this work seeks to empirically assess to which extent the interaction between data characteristics and model assumptions influences the effectiveness of DA methods. Using the widely explored task of building footprint segmentation as a case study, we perform a large-scale study across over 200 DA scenarios that include variations across view angles, areas observed, and sensors used for data acquisition. Rather than adopting different model architectures or optimization criteria, we contrast the performances of two DA methods based on adversarial learning that differ only in their assumptions about source and target domains. Informed by metadata and data characteristics unveiled using traditional computer vision (CV) techniques as well as pretrained deep models, we provide a detailed meta-analysis of experiments highlighting the importance of accurately considering data assumptions for DA in RS segmentation tasks. As demonstrated by a “cherry-picking” exercise, different claims regarding which model is best could be made by selecting different subsets of evaluation scenarios. While well-calibrated assumptions can be beneficial, mismatching assumptions can lead to negative biases in DA applications. Furthermore, this study intends to motivate the community toward more consistent evaluation protocols while providing recommendations and insights toward creating novel benchmark datasets, documenting data characteristics, application-specific knowledge, and model assumptions.

42 ENGINEERING↗
DOE OSTI2018

Towards Automated Transcription of Label Text from Pinned Insect Collections

We present a computer vision system that can transcribe the text on tiny printed labels stacked beneath pinned insects (as found in museum collections). The approach uses multiple views of each label because the labels are often occluded by the pin, the insect specimen, and other labels. Our approach handles occlusion and the extreme viewing angles required to image the stacked labels. Automated image analysis identifies the lines of text and then aligns and rectifies the images. Combining the aligned and rectified images from multiple viewpoints enables us to create a composite image that can be read using optical character recognition tools (OCR) to extract the text. We provide experimental demonstration using both museum specimens and experimental test labels

Agarwal, Nitin↗
DOE OSTI2022

Non-Blind Deblurring for Fluorescence: A Deformable Latent Space Approach with Kernel Parameterization

We report N\non-blind deblurring (NBD) is a modeling method of the image deblurring problem in computer vision, where the blurring kernel is known or can be externally estimated. In this paper, we attempt to solve a parametric NBD problem, inspired by the simultaneous acquisition of ptychography and fluorescent imaging (FI). Ptychography is an imaging method that favors larger probes, i.e. convolutional kernels, while FI relies on a small probe for high resolution. Also, the kernel can be solved during ptychographic reconstruction. With Ptycho-FI using the same larger kernel, we can perform NBD on the blurred fluorescent images to achieve high-resolution FI, and thus speed up the experiments. To this end, we design a deep latent space deformation network that is directly parameterized by the kernel. The network consists of three components: encoder, deformer, and decoder, where the deformer is specifically meant to rectify the latent space representations of blurred images to a standard latent space, regardless of the kernel. The deformation network is trained with a two-stage training scheme. We conduct extensive experiments to confirm that our parametric model can adapt to drastically different blurring kernels and perform robust deblurring.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2021

Effects on the Ocular Surface from Reading on Different Smartphone Screens: A Prospective Randomized Controlled Study

The purpose of this study was to investigate the influence of smartphone reading on the ocular surface and to compare the various effects of different screens and light conditions on the ocular surface. One hundred nineteen volunteers were randomly divided into: light + organic light‐emitting diode (OLED), light + electronic ink (eINK), dark + OLED, and dark + eINK. Ocular surface examinations, including noninvasive break‐up time (NIBUT), noninvasive keratograph tear meniscus height (NIKTMH), ocular redness, fluorescein break‐up time (FBUT), corneal fluorescein staining, meibomian gland assessment, Schirmer I Test, and blinking frequency, were performed before and after a reading task. Symptoms were evaluated using the Ocular Surface Disease Index (OSDI) and Computer Vision Syndrome Questionnaire (CVS‐Q). NIBUT and FBUT were decreased statistically significantly after participants read on an OLED screen for 2 hours compared with the baseline in light and dark environments, whereas no statistically significant decrease was observed on an eINK screen. NIKTMH was statistically significantly decreased after reading on an OLED screen in light and dark settings, and the eINK screen had a lesser effect on NIKTMH. An obvious increase in the ocular redness, OSDI and CVS‐Q scores was observed after reading on an OLED screen, whereas the eINK screen had a lesser effect on these indicators. Blink rate increased gradually in OLED subgroups during the reading task, whereas no statistically significant difference was observed in the eINK subgroups. Our research suggested that reading on an OLED screen can cause ocular surface disorder and obvious subjective discomfort, whereas reading on an eINK screen can minimize ocular surface disorder in both dark and light environments.

Yuan, Kelan↗
DOE OSTI2016

Scanning electron microscopy image representativeness: morphological data on nanoparticles

Summary A sample of a nanomaterial contains a distribution of nanoparticles of various shapes and/or sizes. A scanning electron microscopy image of such a sample often captures only a fragment of the morphological variety present in the sample. In order to quantitatively analyse the sample using scanning electron microscope digital images, and, in particular, to derive numerical representations of the sample morphology, image content has to be assessed. In this work, we present a framework for extracting morphological information contained in scanning electron microscopy images using computer vision algorithms, and for converting them into numerical particle descriptors. We explore the concept of image representativeness and provide a set of protocols for selecting optimal scanning electron microscopy images as well as determining the smallest representative image set for each of the morphological features. We demonstrate the practical aspects of our methodology by investigating tricalcium phosphate, Ca 3 (PO 4 ) 2 , and calcium hydroxyphosphate, Ca 5 (PO 4 ) 3 (OH), both naturally occurring minerals with a wide range of biomedical applications.

ODZIOMEK, KATARZYNA↗
DOE OSTI2025

Automated nuclear cloud feature extraction from film

Chemical, biological, radiological, nuclear, and explosives incidents require rapid detection and characterization for appropriate response. For a nuclear detonation, visible-light cameras may be used to locate the cloud and characterize fallout deposition when coupled with numerical models. Films from the United States’ nuclear testing era compose the only sizeable collection of imagery depicting high-yield detonations. These films offer unique insights into characteristics of flows involving scales that are difficult to replicate experimentally, and they are a valuable source of data for the validation of models for nuclear fallout transport, either as part of emergency response or forensic activities. In this work, we implement modern computer vision and machine learning techniques to identify and track the cloud automatically and subsequently determine the time dependence of some of its features. We trained a ResNet-18 image classifier on hundreds of images to categorize nuclear cloud morphology. Each category or cloud regime is determined by early cloud evolution and is associated to constitutive properties of the flow, such as distribution of vorticity. Next, we identified keypoint features using the KAZE algorithm and tracked these keypoints in the images, allowing us to determine the dimensions and velocities of the cloud across film frames. These measurements converted to real-world units provide valuable experimental data that can be used in the development and validation of nuclear cloud models. We compared the results of this method against manual cloud rise measurements from two different films. In one, our automated method accelerated the feature extraction process without sacrificing measurement accuracy.

Khristy, Joel [ORNL] (ORCID:0000000209963060)↗
DOE OSTI2026

3D reconstruction and neural rendering for adversarial machine learning

While evasion attacks on computer vision systems have been widely studied, creating attacks that remain effective under significant changes in viewpoint continues to be challenging. Traditional approaches often rely on affine transformations of images, but these approaches degrade at larger perspective shifts and often produce unrealistic or ineffective perturbations. Recent methods use differentiable renderers to improve viewpoint robustness, but they typically depend on manually constructed 3D models. We introduce a semi-automated pipeline that generates physically printable and perspective-invariant adversarial patches using only a small set of 2D images. Our method integrates 3D reconstruction, neural rendering, adversarial patch optimization, and an object detection victim model into a unified workflow. We use 2D Gaussian Splatting for high fidelity mesh reconstruction and FlexPara for surface parameterization that produces texture maps suitable for patch editing. Together, these components form a fully differentiable pipeline in PyTorch3D that links texture modification to model outputs, enabling efficient optimization of patches that remain effective across many viewpoints. The complete process, from image capture to patch printing and physical evaluation, can be completed within a few hours. We demonstrate the effectiveness of the resulting patches through attacks on the YOLOv8 object detection model and discuss remaining challenges and opportunities for improving robustness and scalability.

Singhvi, Vivaan [ORNL] (ORCID:0009000586288221)↗
DOE OSTI2013

Real-time automatic fiducial marker tracking in low contrast cine-MV images

Purpose: To develop a real-time automatic method for tracking implanted radiographic markers in low-contrast cine-MV patient images used in image-guided radiation therapy (IGRT). Methods: Intrafraction motion tracking using radiotherapy beam-line MV images have gained some attention recently in IGRT because no additional imaging dose is introduced. However, MV images have much lower contrast than kV images, therefore a robust and automatic algorithm for marker detection in MV images is a prerequisite. Previous marker detection methods are all based on template matching or its derivatives. Template matching needs to match object shape that changes significantly for different implantation and projection angle. While these methods require a large number of templates to cover various situations, they are often forced to use a smaller number of templates to reduce the computation load because their methods all require exhaustive search in the region of interest. The authors solve this problem by synergetic use of modern but well-tested computer vision and artificial intelligence techniques; specifically the authors detect implanted markers utilizing discriminant analysis for initialization and use mean-shift feature space analysis for sequential tracking. This novel approach avoids exhaustive search by exploiting the temporal correlation between consecutive frames and makes it possible to perform more sophisticated detection at the beginning to improve the accuracy, followed by ultrafast sequential tracking after the initialization. The method was evaluated and validated using 1149 cine-MV images from two prostate IGRT patients and compared with manual marker detection results from six researchers. The average of the manual detection results is considered as the ground truth for comparisons. Results: The average root-mean-square errors of our real-time automatic tracking method from the ground truth are 1.9 and 2.1 pixels for the two patients (0.26 mm/pixel). The standard deviations of the results from the 6 researchers are 2.3 and 2.6 pixels. The proposed framework takes about 128 ms to detect four markers in the first MV images and about 23 ms to track these markers in each of the subsequent images. Conclusions: The unified framework for tracking of multiple markers presented here can achieve marker detection accuracy similar to manual detection even in low-contrast cine-MV images. It can cope with shape deformations of fiducial markers at different gantry angles. The fast processing speed reduces the image processing portion of the system latency, therefore can improve the performance of real-time motion compensation.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2014

WE-G-17A-03: MRIgRT: Quantification of Organ Motion

Purpose: To develop an MRI-based methodology and tools required for the quantification of organ motion on a dedicated MRI-guided radiotherapy system. A three-room facility, consisting of a TrueBeam 6X linac vault, a 1.5T MR suite and a brachytherapy interventional room, is currently under commissioning at our institution. The MR scanner can move and image in either room for diagnostic and treatment guidance purposes. Methods: A multi-imaging modality (MR, kV) phantom, featuring programmable 3D simple and complex motion trajectories, was used for the validation of several image sorting algorithms. The testing was performed on MRI (e.g. TrueFISP, TurboFLASH), 4D CT and 4D CBCT. The image sorting techniques were based on a) direct image pixel manipulation into columns or rows, b) single and aggregated pixel data tracking and c) using computer vision techniques for global pixel analysis. Subsequently, the motion phantom and sorting algorithms were utilized for commissioning of MR fast imaging techniques for 2D-cine and 4D data rendering. MR imaging protocols were optimized (e.g. readout gradient strength vs. SNR) to minimize the presence of susceptibility-induced distortions, which were reported through phantom experiments and numerical simulations. The system-related distortions were also quantified (dedicated field phantom) and treated as systematic shifts where relevant. Results: Image sorting algorithms were validated for specific MR-based applications such as quantification of organ motion, local data sampling, and 4D MRI for pre-RT delivery with accuracy better than the raw image pixel size (e.g. 1 mm). MR fast imaging sequences were commissioning and imaging strategies were developed to mitigate spatial artifacts with minimal penalty on the image spatial and temporal sampling. Workflows (e.g. liver) were optimized to include the new motion quantification tools for RT planning and daily patient setup verification. Conclusion: Comprehensive methods were developed and validated for the quantification of organ motion with applications in MRI-guided RT.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

TU-H-CAMPUS-TeP2-01: A Comparison of Noninvasive Techniques to Assess Radiation-Induced Lung Damage in Mice

Purpose: To evaluate the use of post-irradiation changes in respiratory rate and CBCT-based morphology as predictors of survival in mice. Methods: C57L/J mice underwent whole-thorax irradiation with a Co-60 beam to four different doses [0Gy (n=3), 9Gy (n=5), 11Gy (n=7), and 13Gy (n=5)] in order to induce varying levels of pneumonitis. Respiratory rate measurements, breath-hold CBCTs, and free-breathing CBCTs were acquired pre-irradiation and at six time points between two and seven months post-irradiation. For respiratory rate measurements, we developed a novel computer-vision-based technique. We recorded mice sleeping in standard laboratory cages with a 30 fps, 1080p webcam (Logitech C920). We calculated respiratory rate using corner detection and optical flow to track cyclical motion in the fur in the recorded video. Breath-hold and free-breathing CBCTs were acquired on the X-RAD225Cx system. For breathhold imaging, the mice were intubated and their breath was held at full-inhale for 20 seconds. Healthy lung tissue was delineated in the scans using auto-threshold contouring (0–0.7 g/cm{sup 3}). The volume of healthy lung was measured in each of the scans. Next, lung density was measured in a 6-mm{sup 2} ROI in a fixed anatomic location in each of the scans. Results: Day-to-day variability in respiratory rate with our technique was 13%. All metrics except for breath-hold lung volume were correlated with survival: lung density on free-breathing (r=−0.7482,p<0.01) and breath-hold images (r=−0.5864,p<0.01), free-breathing lung volume (r=0.7179,p<0.01), and respiratory rate (r= 0.6953,p<0.01). Lung density on free-breathing scans was correlated with respiratory rate (r=0.7142,p<0.01) and lung density on breath-hold scans (r=0.5543,p<0.01). One significant practical hurdle in the CBCT measurements was that at least one lobe of the lung was collapsed in 36% of free-breathing scans and 45% of breath-hold scans. Conclusion: Lung density and lung volume on free-breathing CBCTs and respiratory rate outperform breath-hold CBCT measurements as indicators for survival from radiation-induced pneumonitis. This work was partially funded by Elekta.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Dynamic STEM-EELS for single-atom and defect measurement during electron beam transformations

This study introduces the integration of dynamic computer vision–enabled imaging with electron energy loss spectroscopy (EELS) in scanning transmission electron microscopy (STEM). This approach involves real-time discovery and analysis of atomic structures as they form, allowing us to observe the evolution of material properties at the atomic level, capturing transient states traditional techniques often miss. Rapid object detection and action system enhances the efficiency and accuracy of STEM-EELS by autonomously identifying and targeting only areas of interest. This machine learning (ML)–based approach differs from classical ML in that it must be executed on the fly, not using static data. We apply this technology to V-doped MoS 2 , uncovering insights into defect formation and evolution under electron beam exposure. This approach opens uncharted avenues for exploring and characterizing materials in dynamic states, offering a pathway to increase our understanding of dynamic phenomena in materials under thermal, chemical, and beam stimuli.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Femtojoule optical nonlinearity for deep learning with incoherent illumination

Optical neural networks (ONNs) are a promising computational alternative for deep learning due to their inherent massive parallelism for linear operations. However, the development of energy-efficient and highly parallel optical nonlinearities, a critical component in ONNs, remains an outstanding challenge. Here, we introduce a nonlinear optical microdevice array (NOMA) compatible with incoherent illumination by integrating the liquid crystal cell with silicon photodiodes at the single-pixel level. We fabricate NOMA with more than half a million pixels, each functioning as an optical analog of the rectified linear unit at ultralow switching energy down to 100 femtojoules per pixel. With NOMA, we demonstrate an optical multilayer neural network. Our work holds promise for large-scale and low-power deep ONNs, computer vision, and real-time optical image processing.

36 MATERIALS SCIENCE↗