Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Image Segmentation”

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 397 records · Page 22

Small target detection for search and rescue operations using distributed deep learning and synthetic data generation

It is important to find the target as soon as possible for search and rescue operations. Surveillance camera systems and unmanned aerial vehicles (UAVs) are used to support search and rescue. Automatic object detection is important because a person cannot monitor multiple surveillance screens simultaneously for 24 hours. Also, the object is often too small to be recognized by the human eye on the surveillance screen. This study used UAVs around the Port of Houston and fixed surveillance cameras to build an automatic target detection system that supports the US Coast Guard (USCG) to help find targets (e.g., person overboard). We combined image segmentation, enhancement, and convolution neural networks to reduce detection time to detect small targets. We compared the performance between the auto-detection system and the human eye. Our system detected the target within 8 seconds, but the human eye detected the target within 25 seconds. Our systems also used synthetic data generation and data augmentation techniques to improve target detection accuracy. This solution may help the search and rescue operations of the first responders in a timely manner.

Chow, Edward↗

Tomography Analysis of Orion Artemis 1 Heatshield Sample

The Orion spacecraft, under NASA's Artemis program, is an integral step in humanity's ambitions of deep space exploration, including our return to the Moon and subsequent mission to Mars. The performance of Orion's heatshield is central to ensuring the safety and success of such missions. This presentation offers a comprehensive overview of the process used in and findings derived from tomography scans of an Artemis 1 heatshield sample executed at the Lawrence Berkeley National Laboratory's Advanced Light Source. These tomography scans captured high-resolution X-Ray images of the heatshield's microstructure, allowing advanced imaging to be employed for 3D image segmentation and visualization of the sample. The Porous Media Analysis (PuMA) software stands central to our analysis, offering robust computational algorithms and methodologies to digitally compute properties of the heatshield material. The presentation discusses the following derived metrics: - Volume fractions, representing the spatial distribution and amounts of various components throughout the heatshield’s depth. - Porosity and crack distributions, offering insights into the void space within the material, critical for understanding the heatshield's structural integrity. - Fiber orientation, detailing the alignment and arrangement of fibers, significant for material orthotropy. - Permeability estimates, quantifying the passage of gas through the material, relevant for re-entry conditions and pyrolysis gasses. One distinctive feature of this study is the comparative evaluation against data obtained from tomography scans of the Exploration Flight Test-1 (EFT-1) heatshield. Such a comparison offers multiple insights, including evaluation of the consistency and repeatability of manufacturing processes as well as understanding of any evolutionary changes in heatshield design or material properties.

Micro-tomography↗

Visual-servoing optical microscopy

The present invention provides methods and devices for the knowledge-based discovery and optimization of differences between cell types. In particular, the present invention provides visual servoing optical microscopy, as well as analysis methods. The present invention provides means for the close monitoring of hundreds of individual, living cells over time; quantification of dynamic physiological responses in multiple channels; real-time digital image segmentation and analysis; intelligent, repetitive computer-applied cell stress and cell stimulation; and the ability to return to the same field of cells for long-term studies and observation. The present invention further provides means to optimize culture conditions for specific subpopulations of cells.

47 OTHER INSTRUMENTATION↗

Visual-servoing optical microscopy

The present invention provides methods and devices for the knowledge-based discovery and optimization of differences between cell types. In particular, the present invention provides visual servoing optical microscopy, as well as analysis methods. The present invention provides means for the close monitoring of hundreds of individual, living cells over time; quantification of dynamic physiological responses in multiple channels; real-time digital image segmentation and analysis; intelligent, repetitive computer-applied cell stress and cell stimulation; and the ability to return to the same field of cells for long-term studies and observation. The present invention further provides means to optimize culture conditions for specific subpopulations of cells.

47 OTHER INSTRUMENTATION↗

High-Energy X-Ray Diffraction Analysis Tool

The functionality of heRXD includes the following: distance and angular calibration and viewing flat-panel detector images used for X-ray diffraction; image (polar) rebinning or "caking"; line position fitting in powder diffraction images; image segmentation or "blob finding"; crystal orentation indesing; and lattice vector refinement. These functionalities encompass a critical set analyzing teh data for high-energy diffraction measurements that are currently performed at synchrotron sources such as the Advanced Photon Source (APS). The software design modular and open source under LGPL. The intent is to provide a common framework and graphical user interface that has the ability to utillize internal as well as external subroutines to provide various optins for performing the fuctionalities listed above. The software will initially be deployed at several national user facilities--including APS, ALS, and CHESS--and then made available for download using a hosting service such as sourceforge.

Source record↗

Sandia Particle Holography Processor v. 1.0

HoloSand is a suite of MATLAB® functions for measurement of particle properties from digital holograms. Functions to read and display digital holograms are included along with scripts to extract three-dimensional particle positions, sizes, and velocities. This software is a research tool used to process experimental data. A user of this software would first record digital holograms of a particle field and then use this software to measure the three-dimensional particle information encoded in the hologram. Applications range from basic laboratory fluids research to applied particle measurements. The software has no known military applications. The software solves the diffraction integral equation to numerically refocus digital holograms and then applies the hybrid and cross-correlation methods described in the references to extract three-dimensional particle information. User input is required to read-in the hologram and select optimum settings for image segmentation.

Guildenbecher, Daniel↗

Quantitative Analysis Of Three-dimensional Branching Systems From X-ray Computed Microtomography Data

Branching structures such as lungs, blood vessels and plant roots play a critical role in life. Growth, structure, and function of these branching structures have an immense effect on our lives. Therefore, quantitative size information on such structures in their native environment is invaluable for studying their growth and the effect of the environment on them. X-ray computed tomography (XCT) has been an effective tool for in situ imaging and analysis of branching structures. We developed a costless tool that approximates the surface and volume of branching structures. Our methodology of noninvasive imaging, segmentation and extraction of quantitative information is demonstrated through the analysis of a plant root in its soil medium from 3D tomography data. XCT data collected on a grass specimen was used to visualize its root structure. A suite of open-source software was employed to segment the root from the soil and determine its isosurface, which was used to calculate its volume and surface. This methodology of processing 3D data is applicable to other branching structures even when the structure of interest is of similar x-ray attenuation to its environment and difficulties arise with sample segmentation.

Environmental Molecular Sciences Laboratory↗

DPP-PMRF: Rethinking Optimization for a Probabilistic Graphical Model Using Data-Parallel Primitives

We present a new parallel algorithm for probabilistic graphical model optimization. The algorithm relies on data-parallel primitives (DPPs), which provide portable performance over hardware architecture. We evaluate results on CPUs and GPUs for an image segmentation problem. Compared to a serial baseline, we observe runtime speedups of up to 13X (CPU) and 44X (GPU). We also compare our performance to a reference, OpenMP-based algorithm, and find speedups of up to 7X (CPU).

97 MATHEMATICS AND COMPUTING↗

Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design

In recent years, the CNNs have achieved great successes in the image processing tasks, e.g., image recognition and object detection. Unfortunately, traditional CNN's classication is found to be easily misled by increasingly complex image features due to the usage of pooling operations, hence unable to preserve accurate position and pose information of the objects. To address this challenge, a novel neural network structure called Capsule Network has been proposed, which introduces equivariance through capsules to signicantly enhance the learning ability for image segmentation and object detection. Due to its requirement of performing a high volume of matrix operations, CapsNets have been generally accelerated on modern GPU platforms that provide highly optimized software library for common deep learning tasks. However, based on our performance characterization on modern GPUs, CapsNets exhibit low effciency due to the special program and execution features of their routing procedure, including massive unshareable intermediate variables and intensive syn- chronizations, which are very dicult to optimize at software level. To address these challenges, we propose a hybrid computing architecture design named PIM-CapsNet. It preserves GPU's on-chip computing capability for accelerating CNN types of layers in CapsNet, while pipelining with an off-chip in-memory acceleration solution that effectively tackles routing procedure's ineffciency by leveraging the processing-in-memory capability of today's 3D stacked memory. Using routing procedure's inherent parallellization feature, our design enables hierarchical improvements on CapsNet inference effciency through minimizing data movement and maximizing parallel processing in memory. Evaluation results demonstrate that our proposed design can achieve substantial improvement on both performance and energy savings for CapsNet inference, with almost zero accuracy loss. The results also suggest good performance scalability in optimizing the routing procedure with increasing network size.

Zhang, Xingyao↗

A Scalable Parallel Hypergraph Generator (HyGen)

Graphs are extensively used to model real-world complex systems. An edge in a graph can model pairwise relationships. However, multiway relationships (connections between three or more vertices) are common in many complex systems such as cellular process, image segmentation, and circuit design. A graph edge cannot model multiway relationships. A hypergraph, which can connect more than two vertices, is thus a better option to model multiway relationships. A large-scale hypergraph analysis has the potential to find useful insights from a complex system and assist in knowledge discovery. Currently a limited number of hypergraphs exists that are representative of real-world datasets. Moreover, real-world hypergraph datasets are small in size and inadequate to incorporate future needs. A graph generator that can produce large-scale synthetic hypergraphs can solve the above mentioned problems. In this paper, we present a scalable parallel hypergraph generator (HyGen) based on the Message Passing Interface (MPI) standard. To generate hypergraphs, HyGen takes the following parameter values as inputs: i) number of vertices, ii) number of hyperedges, iii) number of clusters, iv) vertex distribution, v) hyperedge distribution, vi) local cluster cardinality, and vii) global cluster cardinality. We have demonstrated that HyGen can generate hypergraphs of various sizes in a scalable fashion. HyGen takes approximately four minutes to generate a hypergraph with 4.8 million vertices, 1.6 million hyperedges, and 800 clusters using 1,024 processes on a leadership class computing platform. Our strong and weak scaling experiments on supercomputers demonstrate that HyGen can quickly create large-scale hypergraphs in a parallel manner, thus providing a useful capability for hypergraph analysis.

Hasan, S M Shamimul↗

DNN-based Signal Processing for Liquid Argon Time Projection Chambers

We investigate a deep learning-based signal processing for liquid argon time projection chambers (LArTPCs), a leading detector technology in neutrino physics. Identifying regions of interest (ROIs) in LArTPCs is challenging due to signal cancellation from bipolar responses and various detector effects observed in real data. We approach ROI identification as an image segmentation task, and employ a U-ResNet architecture. The network is trained on samples that incorporate detector geometry information and include a range of detector variations. Our approach significantly outperforms traditional methods while maintaining robustness across diverse detector conditions. This method has been adopted for signal processing in the Short-Baseline Neutrino program and provides a valuable foundation for future experiments such as the Deep Underground Neutrino Experiment.

Bhat, Avinay [Chicago U.]↗

Density-based similarity measures for content based search

We consider the query by multiple example problem where the goal is to identify database samples whose content is similar to a coUection of query samples. To assess the similarity we use a relative content density which quantifies the relative concentration of the query distribution to the database distribution. If the database distribution is a mixture of the query distribution and a background distribution then it can be shown that database samples whose relative content density is greater than a particular threshold {rho} are more likely to have been generated by the query distribution than the background distribution. We describe an algorithm for predicting samples with relative content density greater than {rho} that is computationally efficient and possesses strong performance guarantees. We also show empirical results for applications in computer network monitoring and image segmentation.

97 MATHEMATICS AND COMPUTING↗

Visual-servoing optical microscopy

The present invention provides methods and devices for the knowledge-based discovery and optimization of differences between cell types. In particular, the present invention provides visual servoing optical microscopy, as well as analysis methods. The present invention provides means for the close monitoring of hundreds of individual, living cells over time: quantification of dynamic physiological responses in multiple channels; real-time digital image segmentation and analysis; intelligent, repetitive computer-applied cell stress and cell stimulation; and the ability to return to the same field of cells for long-term studies and observation. The present invention further provides means to optimize culture conditions for specific subpopulations of cells.

47 OTHER INSTRUMENTATION↗

SU-E-J-238: Monitoring Lymph Node Volumes During Radiotherapy Using Semi-Automatic Segmentation of MRI Images

Purpose: Identification and image-based monitoring of lymph nodes growing due to disease, could be an attractive alternative to prophylactic head and neck irradiation. We evaluated the accuracy of the user-interactive Grow Cut algorithm for volumetric segmentation of radiotherapy relevant lymph nodes from MRI taken weekly during radiotherapy. Method: The algorithm employs user drawn strokes in the image to volumetrically segment multiple structures of interest. We used a 3D T2-wturbo spin echo images with an isotropic resolution of 1 mm3 and FOV of 492×492×300 mm3 of head and neck cancer patients who underwent weekly MR imaging during the course of radiotherapy. Various lymph node (LN) levels (N2, N3, N4'5) were individually contoured on the weekly MR images by an expert physician and used as ground truth in our study. The segmentation results were compared with the physician drawn lymph nodes based on DICE similarity score. Results: Three head and neck patients with 6 weekly MR images were evaluated. Two patients had level 2 LN drawn and one patient had level N2, N3 and N4'5 drawn on each MR image. The algorithm took an average of a minute to segment the entire volume (512×512×300 mm3). The algorithm achieved an overall DICE similarity score of 0.78. The time taken for initializing and obtaining the volumetric mask was about 5 mins for cases with only N2 LN and about 15 mins for the case with N2,N3 and N4'5 level nodes. The longer initialization time for the latter case was due to the need for accurate user inputs to separate overlapping portions of the different LN. The standard deviation in segmentation accuracy at different time points was utmost 0.05. Conclusions: Our initial evaluation of the grow cut segmentation shows reasonably accurate and consistent volumetric segmentations of LN with minimal user effort and time.

60 APPLIED LIFE SCIENCES↗

Scene segmentation of natural images using texture measures and back-propagation

Knowledge of the three-dimensional world is essential for many guidance and navigation applications. A sequence of images from an electro-optical sensor can be processed using optical flow algorithms to provide a sparse set of ranges as a function of azimuth and elevation. A natural way to enhance the range map is by interpolation. However, this should be undertaken with care since interpolation assumes continuity of range. The range is continuous in certain parts of the image and can jump at object boundaries. In such situations, the ability to detect homogeneous object regions by scene segmentation can be used to determine regions in the range map that can be enhanced by interpolation. The use of scalar features derived from the spatial gray-level dependence matrix for texture segmentation is explored. Thresholding of histograms of scalar texture features is done for several images to select scalar features which result in a meaningful segmentation of the images. Next, the selected scalar features are used with a neural net to automate the segmentation procedure. Back-propagation is used to train the feed forward neural network. The generalization of the network approach to subsequent images in the sequence is examined. It is shown that the use of multiple scalar features as input to the neural network result in a superior segmentation when compared with a single scalar feature. It is also shown that the scalar features, which are not useful individually, result in a good segmentation when used together. The methodology is applied to both indoor and outdoor images.

Sridhar, Banavar↗

Mapping biomass for a northern forest ecosystem using multi-frequency SAR data

Image processing methods for mapping standing biomass for a forest in Maine, using NASA/JPL airborne synthetic aperture radar (AIRSAR) polarimeter data, are presented. By examining the dependence of backscattering on standing biomass, it is determined that the ratio of HV backscattering from a longer wavelength (P- or L-band) to a shorter wavelength (C) is a good combination for mapping total biomass. This ratio enhances the correlation of the image signature to the standing biomass and compensates for a major part of the variations in backscattering attributed to radar incidence angle. The image processing methods used include image calibration, ratioing, filtering, and segmentation. The image segmentation algorithm uses both means and variances of the image, and it is combined with the image filtering process. Preliminary assessment of the resultant biomass maps suggests that this is a promising method.

Ranson, K. J.↗

Paw-Net: Stacking ensemble deep learning for segmenting scanning electron microscopy images of fine-grained shale samples

Segmentation of scanning electron microscopy (SEM) images is critical yet time-consuming for geological analyses, as it needs to differentiate the boundaries for different mineral objects to facilitate subsequent analyses, such as porosity calculation. Recently, various machine learning methods, especially convolutional neural networks (CNNs), have been explored to segment SEM images of fine-grained shale samples. However, we found that general CNNs do not yield optimal performance due to insufficient training data and imbalanced objects in SEM images. This work has revised the U-Net architecture, a popular approach for biomedical image analyses, by incorporating a loss function that addresses the imbalance issue. Furthermore, we used the ensemble learning method to train multiple models and combined the results to improve the overall performance of segmentation. We prepared 2162 sub-images from raw SEM images in our experiments and divided them into training, validation, and testing datasets. The overall results show that our method improves the average Intersection over Union (IOU) of mineral objects from 0.49 to 0.58, compared to the original U-Net model. Our method can clearly distinguish each object from others with boundaries, even in highly imbalanced images. Training our models takes less than three minutes using a single GPU, while manual labeling can take up to three hours for each image. Furthermore, the method helps geoscientists gain insights quickly and effectively by building neural network models from a small dataset of SEM images.

58 GEOSCIENCES↗

SU-E-J-131: Augmenting Atlas-Based Segmentation by Incorporating Image Features Proximal to the Atlas Contours

Purpose: For facilitating the current automatic segmentation, in this work we propose a narrow-shell strategy to enhance the information of each contour in the library and to improve the accuracy of the exiting atlas-based approach. Methods: In setting up an atlas-based library, we include not only the coordinates of contour points, but also the image features adjacent to the contour. 139 planning CT scans with normal appearing livers obtained during their radiotherapy treatment planning were used to construct the library. The CT images within the library were registered each other using affine registration. A nonlinear narrow shell with the regional thickness determined by the distance between two vertices alongside the contour. The narrow shell was automatically constructed both inside and outside of the liver contours. The common image features within narrow shell between a new case and a library case were first selected by a Speed-up Robust Features (SURF) strategy. A deformable registration was then performed using a thin plate splines (TPS) technique. The contour associated with the library case was propagated automatically onto the images of the new patient by exploiting the deformation field vectors. The liver contour was finally obtained by employing level set based energy function within the narrow shell. The performance of the proposed method was evaluated by comparing quantitatively the auto-segmentation results with that delineated by a physician. Results: Application of the technique to 30 liver cases suggested that the technique was capable of reliably segment organs such as the liver with little human intervention. Compared with the manual segmentation results by a physician, the average and discrepancies of the volumetric overlap percentage (VOP) was found to be 92.43%+2.14%. Conclusion: Incorporation of image features into the library contours improves the currently available atlas-based auto-contouring techniques and provides a clinically practical solution for auto-segmentation. This work is supported by NIH/NIBIB (1R01-EB016777), National Natural Science Foundation of China (No.61471226 and No.61201441), Research funding from Shandong Province (No.BS2012DX038 and No.J12LN23), and Research funding from Jinan City (No.201401221 and No.20120109)

60 APPLIED LIFE SCIENCES↗