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 955 records · Page 53
All sourcesNASA NTRSDOE OSTI
NASA NTRS2009

Hardware Implementation of a Bilateral Subtraction Filter

A bilateral subtraction filter has been implemented as a hardware module in the form of a field-programmable gate array (FPGA). In general, a bilateral subtraction filter is a key subsystem of a high-quality stereoscopic machine vision system that utilizes images that are large and/or dense. Bilateral subtraction filters have been implemented in software on general-purpose computers, but the processing speeds attainable in this way even on computers containing the fastest processors are insufficient for real-time applications. The present FPGA bilateral subtraction filter is intended to accelerate processing to real-time speed and to be a prototype of a link in a stereoscopic-machine- vision processing chain, now under development, that would process large and/or dense images in real time and would be implemented in an FPGA. In terms that are necessarily oversimplified for the sake of brevity, a bilateral subtraction filter is a smoothing, edge-preserving filter for suppressing low-frequency noise. The filter operation amounts to replacing the value for each pixel with a weighted average of the values of that pixel and the neighboring pixels in a predefined neighborhood or window (e.g., a 9 9 window). The filter weights depend partly on pixel values and partly on the window size. The present FPGA implementation of a bilateral subtraction filter utilizes a 9 9 window. This implementation was designed to take advantage of the ability to do many of the component computations in parallel pipelines to enable processing of image data at the rate at which they are generated. The filter can be considered to be divided into the following parts (see figure): a) An image pixel pipeline with a 9 9- pixel window generator, b) An array of processing elements; c) An adder tree; d) A smoothing-and-delaying unit; and e) A subtraction unit. After each 9 9 window is created, the affected pixel data are fed to the processing elements. Each processing element is fed the pixel value for its position in the window as well as the pixel value for the central pixel of the window. The absolute difference between these two pixel values is calculated and used as an address in a lookup table. Each processing element has a lookup table, unique for its position in the window, containing the weight coefficients for the Gaussian function for that position. The pixel value is multiplied by the weight, and the outputs of the processing element are the weight and pixel-value weight product. The products and weights are fed to the adder tree. The sum of the products and the sum of the weights are fed to the divider, which computes the sum of products the sum of weights. The output of the divider is denoted the bilateral smoothed image. The smoothing function is a simple weighted average computed over a 3 3 subwindow centered in the 9 9 window. After smoothing, the image is delayed by an additional amount of time needed to match the processing time for computing the bilateral smoothed image. The bilateral smoothed image is then subtracted from the 3 3 smoothed image to produce the final output. The prototype filter as implemented in a commercially available FPGA processes one pixel per clock cycle. Operation at a clock speed of 66 MHz has been demonstrated, and results of a static timing analysis have been interpreted as suggesting that the clock speed could be increased to as much as 100 MHz.

Huertas, Andres↗
NASA NTRS1971

Research and applications: Artificial intelligence

Research in the field of artificial intelligence is discussed. The focus of recent work has been the design, implementation, and integration of a completely new system for the control of a robot that plans, learns, and carries out tasks autonomously in a real laboratory environment. The computer implementation of low-level and intermediate-level actions; routines for automated vision; and the planning, generalization, and execution mechanisms are reported. A scenario that demonstrates the approximate capabilities of the current version of the entire robot system is presented.

Raphael, B.↗
NASA NTRS1991

Machine vision based teleoperation aid

When teleoperating a robot using video from a remote camera, it is difficult for the operator to gauge depth and orientation from a single view. In addition, there are situations where a camera mounted for viewing by the teleoperator during a teleoperation task may not be able to see the tool tip, or the viewing angle may not be intuitive (requiring extensive training to reduce the risk of incorrect or dangerous moves by the teleoperator). A machine vision based teleoperator aid is presented which uses the operator's camera view to compute an object's pose (position and orientation), and then overlays onto the operator's screen information on the object's current and desired positions. The operator can choose to display orientation and translation information as graphics and/or text. This aid provides easily assimilated depth and relative orientation information to the teleoperator. The camera may be mounted at any known orientation relative to the tool tip. A preliminary experiment with human operators was conducted and showed that task accuracies were significantly greater with than without this aid.

Hoff, William A.↗
NASA NTRS1995

Grayscale/resolution trade-off for text: Model predictions and psychophysical results for letter confusion and letter discrimination

In a series of papers presented in 1994, we examined the grayscale/resolution trade-off for natural images displayed on devices with discrete pixellation, such as AMLCD's. In the present paper we extend this study by examining the grayscale/resolution trade-off for text images on discrete-pixel displays. Halftoning in printing is an example of the grayscale/resolution trade-off. In printing, spatial resolution is sacrificed to produce grayscale. Another example of this trade-off is the inherent low-pass spatial filter of a CRT, caused by the point-spread function of the electron beam in the phosphor layer. On a CRT, sharp image edges are blurred by this inherent low-pass filtering, and the block noise created by spatial quantization is greatly reduced. A third example of this trade-off is text anti-aliasing, where grayscale is used to improve letter shape, size and location when rendered at a low spatial resolution. There are additional implications for display system design from the grayscale/resolution trade-off. For example, reduced grayscale can reduce system costs by requiring less complexity in the framestore, allowing the use of lower cost drivers, potentially increasing data transfer rates in the image subsystem, and simplifying the manufacturing processes that are used to construct the active matrix for AMLCD (active-matrix liquid-crystal display) or AMTFEL (active-matrix thin-film electroluminescent) devices. Therefore, the study of these trade-offs is important for display designers and manufacturing and systems engineers who wish to create the highest performance, lowest cost device possible. Our strategy for investigating this trade-off is to generate a set of simple test images, manipulate grayscale and resolution, predict discrimination performance using the ViDEOS(Sarnoff) Human Vision Model, conduct an empirical study of discrimination using psychophysical procedures, and verify the computational results using the psychophysical results.

Gille, Jennifer↗
NASA NTRS2005

Creating Communications, Computing, and Networking Technology Development Road Maps for Future NASA Human and Robotic Missions

For human and robotic exploration missions in the Vision for Exploration, roadmaps are needed for capability development and investments based on advanced technology developments. A roadmap development process was undertaken for the needed communications, and networking capabilities and technologies for the future human and robotics missions. The underlying processes are derived from work carried out during development of the future space communications architecture, an d NASA's Space Architect Office (SAO) defined formats and structures for accumulating data. Interrelationships were established among emerging requirements, the capability analysis and technology status, and performance data. After developing an architectural communications and networking framework structured around the assumed needs for human and robotic exploration, in the vicinity of Earth, Moon, along the path to Mars, and in the vicinity of Mars, information was gathered from expert participants. This information was used to identify the capabilities expected from the new infrastructure and the technological gaps in the way of obtaining them. We define realistic, long-term space communication architectures based on emerging needs and translate the needs into interfaces, functions, and computer processing that will be required. In developing our roadmapping process, we defined requirements for achieving end-to-end activities that will be carried out by future NASA human and robotic missions. This paper describes: 10 the architectural framework developed for analysis; 2) our approach to gathering and analyzing data from NASA, industry, and academia; 3) an outline of the technology research to be done, including milestones for technology research and demonstrations with timelines; and 4) the technology roadmaps themselves.

Bhasin, Kul↗
DOE OSTI2024

Employing artificial intelligence to steer exascale workflows with colmena

Computational workflows are a common class of application on supercomputers, yet the loosely coupled and heterogeneous nature of workflows often fails to take full advantage of their capabilities. We created Colmena to leverage the massive parallelism of a supercomputer by using Artificial Intelligence (AI) to learn from and adapt a workflow as it executes. Colmena allows scientists to define how their application should respond to events (e.g., task completion) as a series of cooperative agents. In this paper, we describe the design of Colmena, the challenges we overcame while deploying applications on exascale systems, and the science workflows we have enhanced through interweaving AI. The scaling challenges we discuss include developing steering strategies that maximize node utilization, introducing data fabrics that reduce communication overhead of data-intensive tasks, and implementing workflow tasks that cache costly operations between invocations. These innovations coupled with a variety of application patterns accessible through our agent-based steering model have enabled science advances in chemistry, biophysics, and materials science using different types of AI. In conclusion, our vision is that Colmena will spur creative solutions that harness AI across many domains of scientific computing.

Workflows↗
DOE OSTI2019

Real-Time Machine Learning Inferencing with Edge Computing Devices from Google and Intel

Machine Learning (ML) has been demonstrated to accelerate discovery and improve the accuracy of many measurements in astrophysics and high energy physics research. As an increasingly commonplace tool, we have reached a new set of challenges in the deployment of ML, at the forefront of which is their computational complexity. The goal of this project is to explore the viability of dedicated machine learning hardware, such as Google’s Coral/Edge TPU and Intel’s Movidius Myriad devices, in astrophysics and high energy physics applications. ML algorithms, while faster than traditional methods, can become the bottleneck in data processing pipelines --- which is a critical issue in systems that require low latency. Within the context of high energy physics and astrophysics, we test this hardware in an attempt to find if it is able to reduce the computational cost of machine learning. We have benchmarked some of these devices, specifically the Google Coral Dev Board and th e Google AIY Vision Kit (Containing Intel’s Movidius Myriad 2).This was done via a strong gravitational lens finding application and a known data set of lenses, simulating a realistic astrophysics application of machine learning, and compare their results to that of traditional computer hardware.

Hawks, Benjamin↗
NASA NTRS2000

Object Based Numerical Zooming Between the NPSS Version 1 and a 1-Dimensional Meanline High Pressure Compressor Design Analysis Code

Within NASA's High Performance Computing and Communication (HPCC) program, NASA Glenn Research Center is developing an environment for the analysis/design of propulsion systems for aircraft and space vehicles called the Numerical Propulsion System Simulation (NPSS). The NPSS focuses on the integration of multiple disciplines such as aerodynamics, structures, and heat transfer, along with the concept of numerical zooming between 0- Dimensional to 1-, 2-, and 3-dimensional component engine codes. The vision for NPSS is to create a "numerical test cell" enabling full engine simulations overnight on cost-effective computing platforms. Current "state-of-the-art" engine simulations are 0-dimensional in that there is there is no axial, radial or circumferential resolution within a given component (e.g. a compressor or turbine has no internal station designations). In these 0-dimensional cycle simulations the individual component performance characteristics typically come from a table look-up (map) with adjustments for off-design effects such as variable geometry, Reynolds effects, and clearances. Zooming one or more of the engine components to a higher order, physics-based analysis means a higher order code is executed and the results from this analysis are used to adjust the 0-dimensional component performance characteristics within the system simulation. By drawing on the results from more predictive, physics based higher order analysis codes, "cycle" simulations are refined to closely model and predict the complex physical processes inherent to engines. As part of the overall development of the NPSS, NASA and industry began the process of defining and implementing an object class structure that enables Numerical Zooming between the NPSS Version I (0-dimension) and higher order 1-, 2- and 3-dimensional analysis codes. The NPSS Version I preserves the historical cycle engineering practices but also extends these classical practices into the area of numerical zooming for use within a companies' design system. What follows here is a description of successfully zooming I-dimensional (row-by-row) high pressure compressor results back to a NPSS engine 0-dimension simulation and a discussion of the results illustrated using an advanced data visualization tool. This type of high fidelity system-level analysis, made possible by the zooming capability of the NPSS, will greatly improve the fidelity of the engine system simulation and enable the engine system to be "pre-validated" prior to commitment to engine hardware.

Follen, G.↗
DOE OSTI2018

Cancer epidemiology update, following the 2011 IARC evaluation of radiofrequency electromagnetic fields (Monograph 102)

Highlights: • Increased risk of brain, vestibular nerve and salivary gland tumors are associated with mobile phone use. • Nine studies (2011–2017) report increased risk of brain cancer from mobile phone use. • Four case-control studies (3 in 2013, 1 in 2014) report increased risk of vestibular nerve tumors. • Concern for other cancers: breast (male & female), testis, leukemia, and thyroid. • Based on the evidence reviewed it is our opinion that IARC's current categorization of RFR as a possible human carcinogen (Group 2B) should be upgraded to Carcinogenic to Humans (Group 1). Epidemiology studies (case-control, cohort, time trend and case studies) published since the International Agency for Research on Cancer (IARC) 2011 categorization of radiofrequency radiation (RFR) from mobile phones and other wireless devices as a possible human carcinogen (Group 2B) are reviewed and summarized. Glioma is an important human cancer found to be associated with RFR in 9 case-control studies conducted in Sweden and France, as well as in some other countries. Increasing glioma incidence trends have been reported in the UK and other countries. Non-malignant endpoints linked include acoustic neuroma (vestibular Schwannoma) and meningioma. Because they allow more detailed consideration of exposure, case-control studies can be superior to cohort studies or other methods in evaluating potential risks for brain cancer. When considered with recent animal experimental evidence, the recent epidemiological studies strengthen and support the conclusion that RFR should be categorized as carcinogenic to humans (IARC Group 1). Opportunistic epidemiological studies are proposed that can be carried out through cross-sectional analyses of high, medium, and low mobile phone users with respect to hearing, vision, memory, reaction time, and other indicators that can easily be assessed through standardized computer-based tests. As exposure data are not uniformly available, billing records should be used whenever available to corroborate reported exposures.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
DOE OSTI2024

Forecasting high-dimensional spatio-temporal systems from sparse measurements

This paper introduces a new neural network architecture designed to forecast high-dimensional spatio-temporal data using only sparse measurements. The architecture uses a two-stage end-to-end framework that combines neural ordinary differential equations (NODEs) with vision transformers. Initially, our approach models the underlying dynamics of complex systems within a low-dimensional space; and then it reconstructs the corresponding high-dimensional spatial fields. Many traditional methods involve decoding high-dimensional spatial fields before modeling the dynamics, while some other methods use an encoder to transition from high-dimensional observations to a latent space for dynamic modeling. In contrast, our approach directly uses sparse measurements to model the dynamics, bypassing the need for an encoder. This direct approach simplifies the modeling process, reduces computational complexity, and enhances the efficiency and scalability of the method for large datasets. We demonstrate the effectiveness of our framework through applications to various spatio-temporal systems, including fluid flows and global weather patterns. Although sparse measurements have limitations, our experiments reveal that they are sufficient to forecast system dynamics accurately over long time horizons. Our results also indicate that the performance of our proposed method remains robust across different sensor placement strategies, with further improvements as the number of sensors increases. This robustness underscores the flexibility of our architecture, particularly in real-world scenarios where sensor data is often sparse and unevenly distributed.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2010

Progress in Development of the Axel Rovers

Progress has been made in the development of a family of robotic land vehicles having modular and minimalist design features chosen to impart a combination of robustness, reliability, and versatility. These vehicles at earlier stages of development were described in two previous NASA Tech Briefs articles: "Reconfigurable Exploratory Robotic Vehicles" (NPO-20944), Vol. 25, No. 7 (July 2001), page 56; and "More About Reconfigurable Exploratory Robotic Vehicles" (NPO-30890), Vol. 33, No. 8 (August 2009), page 40. Conceived for use in exploration of the surfaces of Mars and other remote planets, these vehicles could also be adapted to terrestrial applications, including exploration of volcanic craters or other hostile terrain, military reconnaissance, inspection of hazardous sites, and searching for victims of earthquakes, landslides, avalanches, or mining accidents. In addition, simplified versions of these vehicles might be marketable as toys. The most basic module in this family of reconfigurable robots is the Axel rover, which has a cylindrical body with two main wheels and a trailing link. Inside its body are three motors and associated mechanisms for driving the two wheels and for rotating the link 360 around its symmetrical body. The actuated link serves several purposes: It is used as a lever arm to react to the wheels thrust to move Axel in multiple directions. It is used to rotate the Axel housing in order to tilt, to the desired angle, any sensors and instruments mounted on or in the Axel housing. It provides an alternative mobility mode, which is primarily used in its tethered configuration. Turn ing the link into the ground in lieu of driving the wheels causes the Axel housing and wheels to roll as a unit and thereby leads to a tumbling motion along the ground. With a tether mounted around Axel s cylindrical body, the link serves as a winch mechanism to reel and unreel the tether raising and lowering Axel over steep and vertical surfaces (Figure 1). Sensors, computation, and communication modules are also housed inside Axel s body. A pair of stereo vision cameras provides three-dimensional view for autonomous navigation and avoiding obstacles. Inertial sensors determine the tilt of the robot and are used for estimating its motion. In a fully developed version, power would be supplied by rechargeable batteries aboard Axel; at the time of reporting the information for this article, power was supplied from an external source via a cable. In and of itself, the Axel rover is fully capable of traversing and sampling terrains on planetary surfaces. By use of only the two main wheel actuators and the caster link actuator, Axel can be made to follow an arbitrary path, turn in place, and operate upside- down or right-side-up. If operated in a tethered configuration, as shown in Figure 1, it can be made to move down and up a steep crater wall, descend from an overhang to a cave, and ascend from the cave back to the overhang, all by use of the same three actuators. Such tethered operation could be useful in searching for accident victims or missing persons in mines, caves, and rubble piles. Running the tether through the caster link enhances the stability of Axel and provides a restoring force that keeps the link off the ground for the most part during operation on a steep slope. In its extended configuration, two Axel modules can dock to either side of a payload module to form the four wheeled Axel2 rover (Figure 2). Additional payload and Axel modules can dock to either side of the Axel2 to form the Axel3 rover, extending its payload capacity and its mobility capabilities.

Nesnas, Issa A.↗
NASA NTRS2006

Automated Camera Calibration

Automated Camera Calibration (ACAL) is a computer program that automates the generation of calibration data for camera models used in machine vision systems. Machine vision camera models describe the mapping between points in three-dimensional (3D) space in front of the camera and the corresponding points in two-dimensional (2D) space in the camera s image. Calibrating a camera model requires a set of calibration data containing known 3D-to-2D point correspondences for the given camera system. Generating calibration data typically involves taking images of a calibration target where the 3D locations of the target s fiducial marks are known, and then measuring the 2D locations of the fiducial marks in the images. ACAL automates the analysis of calibration target images and greatly speeds the overall calibration process.

Chen, Siqi↗
NASA NTRS2005

Video Mosaicking for Inspection of Gas Pipelines

A vision system that includes a specially designed video camera and an image-data-processing computer is under development as a prototype of robotic systems for visual inspection of the interior surfaces of pipes and especially of gas pipelines. The system is capable of providing both forward views and mosaicked radial views that can be displayed in real time or after inspection. To avoid the complexities associated with moving parts and to provide simultaneous forward and radial views, the video camera is equipped with a wide-angle (>165 ) fish-eye lens aimed along the axis of a pipe to be inspected. Nine white-light-emitting diodes (LEDs) placed just outside the field of view of the lens (see Figure 1) provide ample diffuse illumination for a high-contrast image of the interior pipe wall. The video camera contains a 2/3-in. (1.7-cm) charge-coupled-device (CCD) photodetector array and functions according to the National Television Standards Committee (NTSC) standard. The video output of the camera is sent to an off-the-shelf video capture board (frame grabber) by use of a peripheral component interconnect (PCI) interface in the computer, which is of the 400-MHz, Pentium II (or equivalent) class. Prior video-mosaicking techniques are applicable to narrow-field-of-view (low-distortion) images of evenly illuminated, relatively flat surfaces viewed along approximately perpendicular lines by cameras that do not rotate and that move approximately parallel to the viewed surfaces. One such technique for real-time creation of mosaic images of the ocean floor involves the use of visual correspondences based on area correlation, during both the acquisition of separate images of adjacent areas and the consolidation (equivalently, integration) of the separate images into a mosaic image, in order to insure that there are no gaps in the mosaic image. The data-processing technique used for mosaicking in the present system also involves area correlation, but with several notable differences: Because the wide-angle lens introduces considerable distortion, the image data must be processed to effectively unwarp the images (see Figure 2). The computer executes special software that includes an unwarping algorithm that takes explicit account of the cylindrical pipe geometry. To reduce the processing time needed for unwarping, parameters of the geometric mapping between the circular view of a fisheye lens and pipe wall are determined in advance from calibration images and compiled into an electronic lookup table. The software incorporates the assumption that the optical axis of the camera is parallel (rather than perpendicular) to the direction of motion of the camera. The software also compensates for the decrease in illumination with distance from the ring of LEDs.

Magruder, Darby↗
NASA NTRS2014

The Roots of Beowulf

The first Beowulf Linux commodity cluster was constructed at NASA's Goddard Space Flight Center in 1994 and its origins are a part of the folklore of high-end computing. In fact, the conditions within Goddard that brought the idea into being were shaped by rich historical roots, strategic pressures brought on by the ramp up of the Federal High-Performance Computing and Communications Program, growth of the open software movement, microprocessor performance trends, and the vision of key technologists. This multifaceted story is told here for the first time from the point of view of NASA project management.

Beowulf↗
NASA NTRS2015

Advanced Bayesian Method for Planetary Surface Navigation

Autonomous Exploration, Inc., has developed an advanced Bayesian statistical inference method that leverages current computing technology to produce a highly accurate surface navigation system. The method combines dense stereo vision and high-speed optical flow to implement visual odometry (VO) to track faster rover movements. The Bayesian VO technique improves performance by using all image information rather than corner features only. The method determines what can be learned from each image pixel and weighs the information accordingly. This capability improves performance in shadowed areas that yield only low-contrast images. The error characteristics of the visual processing are complementary to those of a low-cost inertial measurement unit (IMU), so the combination of the two capabilities provides highly accurate navigation. The method increases NASA mission productivity by enabling faster rover speed and accuracy. On Earth, the technology will permit operation of robots and autonomous vehicles in areas where the Global Positioning System (GPS) is degraded or unavailable.

Center, Julian↗
DOE OSTI2025

SHF: Symmetrical Hierarchical Forest with Pretrained Vision Transformer Encoder for High-Resolution Medical Segmentation

This paper presents a novel approach to addressing the long-sequence problem in high-resolution medical images for Vision Transformers (ViTs). Using smaller patches as tokens can enhance ViT performance, but quadratically increases computation and memory requirements. Therefore, the common practice for applying ViTs to high-resolution images is either to: (a) employ complex sub-quadratic attention schemes or (b) use large to medium-sized patches and rely on additional mechanisms within the model to capture the spatial hierarchy of details. We propose Symmetrical Hierarchical Forest (SHF), a lightweight approach that adaptively patches the input image to increase token information density and encode hierarchical spatial structures into the input embedding. We then apply a reverse depatching scheme to the output embeddings of the transformer encoder, eliminating the need for convolution-based decoders. Unlike previous methods that modify attention mechanisms or use a complex hierarchy of interacting models, SHF can be retrofitted to any ViT model to allow it to learn the hierarchical structure of details in high-resolution images without requiring architectural changes. Experimental results demonstrate significant gains in computational efficiency and performance: on the PAIP WSI dataset, we achieved a 3∼32×speedup or a 2.95%∼7.03% increase in accuracy (measured by Dice score) at a 64K2 resolution with the same computational budget, compared to state-of-the-art production models. On the 3D medical datasets BTCV and KiTS, training was 6×faster, with accuracy gains of 6.93% and 5.9%, respectively, compared to models without SHF.

Zhang, Enzhi [Hokkaido University, Japan]↗