SEARCH · Engineering Papers

Results for “Machine vision”

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

SourceResearch connectionFrom yearThrough year

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

At least 145 records · Page 8

All sources NASA NTRS DOE OSTI

NASA NTRS1992

Topography from shading and stereo

Methods exploiting photometric information in images that have been developed in machine vision can be applied to planetary imagery. Present techniques, however, focus on one visual cue, such as shading or binocular stereo, and produce results that are either not very accurate in an absolute sense or provide information only at few points on the surface. We plan to integrate shape from shading, binocular stereo and photometric stereo to yield a robust system for recovering detailed surface shape and surface reflectance information. Such a system will be useful in producing quantitative information from the vast volume of imagery being received, as well as in helping visualize the underlying surface. The work will be carried out on a popular computing platform so that it will be easily accessible to other workers.

Horn, Berthold P.↗

NASA NTRS1992

Preliminary test results and upgrades for an automated assembly system

An automated structures assembly testbed developed by Langley Research Center to study the practical problems associated with the automated assembly of large space structures using robotic manipulators is described. Emphasis is placed on the requirements and features of system upgrades and their impact on system performance, flexibility, and reliability. The current research program is aimed at evolving the baseline assembly system into a flexible, robust, sensor-based system capable of assembling more complex truss-supported satellite systems. To achieve this objective, five system upgrades have been developed including a machine vision capability to eliminate taught robot arm positions; an on-board end-effector microprocessor to reduce communications; a second-generation end-effector to construct contoured trusses for antennas and install payloads; the installation of reflector-type panels on the truss to produce a complete and functional system, and an expert system to significantly reduce the amount of software code required for system operation and provide greater flexibility in implementing new features.

Will, Ralph W.↗

NASA NTRS1993

An operator interface design for a telerobotic inspection system

The operator interface has recently emerged as an important element for efficient and safe interactions between human operators and telerobotics. Advances in graphical user interface and graphics technologies enable us to produce very efficient operator interface designs. This paper describes an efficient graphical operator interface design newly developed for remote surface inspection at NASA-JPL. The interface, designed so that remote surface inspection can be performed by a single operator with an integrated robot control and image inspection capability, supports three inspection strategies of teleoperated human visual inspection, human visual inspection with automated scanning, and machine-vision-based automated inspection.

Kim, Won S.↗

NASA NTRS1990

Jet Propulsion Laboratory/Kennedy Space Center telerobotic inspection and manipulation demonstration

The goal of this effort is to demonstrate telerobotic inspection and mainpulation of space shuttle payloads in the presence of substantial communications time delays between the operator station and the robotic work space. The processing of space shuttle payloads provides a variety of tasks which are typical of both space shuttle ground operations and Space Station in-flight operations, and communications time delays are inevitable in space operations where the operator station will be light-seconds away from the telerobot. With this demonstration we hope to show the efficacy and safety of robotic technology for ground and space operations. Our approach is to develop an experimental telerobotic system with the remote sensing, actuation and reflex portions located at KSC in Florida, while the operator control station will be located at Jet Propulsion Laboratory (JPL) in California. The JPL portion of the system includes a high-level operator interface, intelligent spatial planning and machine vision, while the KSC portion includes the robot arm, end effectors, cameras and proximity sensors, and the necessary control and communications computers and software. The communications between JPL and KSC are over a limited-bandwidth network channel (19200 baud) with unpredictable and unrepeatable time delays. In FY89 we integrated a basic version of the robotic, communications, and computer hardware, and we developed the software to perform an operator-supervised inspection of a PAM-D satellite upper stage rocket motor and its shuttle support cradle. The demonstration, though severely limited by the bulk of the available computer arm, showed the potential of telerobotics for inspection tasks. In the future, we plan to develop additional capabilities which will allow manipulation tasks to be performed, including removal of dust covers and lens caps, insertion of connectors and batteries, and installation of payload objects.

Wilcox, Brian↗

NASA NTRS1993

A summary of image segmentation techniques

Machine vision systems are often considered to be composed of two subsystems: low-level vision and high-level vision. Low level vision consists primarily of image processing operations performed on the input image to produce another image with more favorable characteristics. These operations may yield images with reduced noise or cause certain features of the image to be emphasized (such as edges). High-level vision includes object recognition and, at the highest level, scene interpretation. The bridge between these two subsystems is the segmentation system. Through segmentation, the enhanced input image is mapped into a description involving regions with common features which can be used by the higher level vision tasks. There is no theory on image segmentation. Instead, image segmentation techniques are basically ad hoc and differ mostly in the way they emphasize one or more of the desired properties of an ideal segmenter and in the way they balance and compromise one desired property against another. These techniques can be categorized in a number of different groups including local vs. global, parallel vs. sequential, contextual vs. noncontextual, interactive vs. automatic. In this paper, we categorize the schemes into three main groups: pixel-based, edge-based, and region-based. Pixel-based segmentation schemes classify pixels based solely on their gray levels. Edge-based schemes first detect local discontinuities (edges) and then use that information to separate the image into regions. Finally, region-based schemes start with a seed pixel (or group of pixels) and then grow or split the seed until the original image is composed of only homogeneous regions. Because there are a number of survey papers available, we will not discuss all segmentation schemes. Rather than a survey, we take the approach of a detailed overview. We focus only on the more common approaches in order to give the reader a flavor for the variety of techniques available yet present enough details to facilitate implementation and experimentation.

Spirkovska, Lilly↗

NASA NTRS1993

Nature's crucible: Manufacturing optical nonlinearities for high resolution, high sensitivity encoding in the compound eye of the fly, Musca domestica

The number of pixels per unit area sampling an image determines Nyquist resolution. Therefore, the highest pixel density is the goal. Unfortunately, as reduction in pixel size approaches the wavelength of light, sensitivity is lost and noise increases. Animals face the same problems and have achieved novel solutions. Emulating these solutions offers potentially unlimited sensitivity with detector size approaching the diffraction limit. Once an image is 'captured', cellular preprocessing of information allows extraction of high resolution information from the scene. Computer simulation of this system promises hyperacuity for machine vision.

Wilcox, Mike↗

NASA NTRS1993

Performance measures from the explorer platform berthing experiment

The Explorer Platform is a Modular Mission Spacecraft: it has several subunits that are designed to be replaced on orbit. The Goddard Space Flight Center Robotics Lab undertook an experiment to evaluate various robotic approaches to replacing one of the units; a large (approximately 1 meter by 1 meter by 0.5 meter) power box. The hardware consists of a Robotics Research Corporation K-1607 (RRC) manipulator mounted on a large gantry robot, a Kraft handcontroller for teleoperation of RRC, a Lightweight Servicing Tool (LST) mounted on the RRC, and an Explorer Platform mockup (EP) with a removable box (MMS) that has fixtures that mate with the LST. Sensors include a wrist wrench sensor on the RRC and Capaciflectors mounted on the LST and the MMS. There are also several cameras, but no machine vision is used. The control system for the RRC is entirely written by Goddard; it consists of Ada code on three Multibus I 386/387 CPU boards doing the real-time robot control, and C on a 386 PC processing Capaciflector data. The gantry is not moved during this experiment. The task is the exchange of the MMS; it is removed and replaced. This involves four basic steps: mating the LST to the MMS, demating the MMS from the EP, mating the MMS to the EP, and demating the LST form the MMS. Each of the mating steps must be preceeded by an alignment to bring the mechanical fixtures within their capture range. Two basic approaches to alignment are explored: teleoperation with the operator viewing thru cameras, and Capaciflector based autonomy. To evaluate the two alignment approaches, several runs were run with each approach and the final pose was recorded. Comparing this to the ideal alignment pose gives accuracy and repeatability data. In addition the wrenches exerted during the mating tasks were recorded; this gives information on how the alignment step affects the mating step. There are also two approaches to mating; teleoperation, and impedance based autonomy. The wrench data taken during mating using these two approaches is used to evaluate them. Section 2 describes the alignment results, section 3 describes the mating results, and finally Section 4 gives some conclusions.

Leake, Stephen↗

NASA NTRS1994

A new high-speed IR camera system

A multi-organizational team at the Goddard Space Flight Center is developing a new far infrared (FIR) camera system which furthers the state of the art for this type of instrument by the incorporating recent advances in several technological disciplines. All aspects of the camera system are optimized for operation at the high data rates required for astronomical observations in the far infrared. The instrument is built around a Blocked Impurity Band (BIB) detector array which exhibits responsivity over a broad wavelength band and which is capable of operating at 1000 frames/sec, and consists of a focal plane dewar, a compact camera head electronics package, and a Digital Signal Processor (DSP)-based data system residing in a standard 486 personal computer. In this paper we discuss the overall system architecture, the focal plane dewar, and advanced features and design considerations for the electronics. This system, or one derived from it, may prove useful for many commercial and/or industrial infrared imaging or spectroscopic applications, including thermal machine vision for robotic manufacturing, photographic observation of short-duration thermal events such as combustion or chemical reactions, and high-resolution surveillance imaging.

Travis, Jeffrey W.↗

NASA NTRS1994

The 4-D approach to visual control of autonomous systems

Development of a 4-D approach to dynamic machine vision is described. Core elements of this method are spatio-temporal models oriented towards objects and laws of perspective projection in a foward mode. Integration of multi-sensory measurement data was achieved through spatio-temporal models as invariants for object recognition. Situation assessment and long term predictions were allowed through maintenance of a symbolic 4-D image of processes involving objects. Behavioral capabilities were easily realized by state feedback and feed-foward control.

Dickmanns, Ernst D.↗

NASA NTRS1994

Topography from shading and stereo

Methods exploiting photometric information in images that have been developed in machine vision can be applied to planetary imagery. Integrating shape from shading, binocular stereo, and photometric stereo yields a robust system for recovering detailed surface shape and surface reflectance information. Such a system is useful in producing quantitative information from the vast volume of imagery being received, as well as in helping visualize the underlying surface.

Horn, Berthold K. P.↗

NASA NTRS1994

Document analysis with neural net circuits

Document analysis is one of the main applications of machine vision today and offers great opportunities for neural net circuits. Despite more and more data processing with computers, the number of paper documents is still increasing rapidly. A fast translation of data from paper into electronic format is needed almost everywhere, and when done manually, this is a time consuming process. Markets range from small scanners for personal use to high-volume document analysis systems, such as address readers for the postal service or check processing systems for banks. A major concern with present systems is the accuracy of the automatic interpretation. Today's algorithms fail miserably when noise is present, when print quality is poor, or when the layout is complex. A common approach to circumvent these problems is to restrict the variations of the documents handled by a system. In our laboratory, we had the best luck with circuits implementing basic functions, such as convolutions, that can be used in many different algorithms. To illustrate the flexibility of this approach, three applications of the NET32K circuit are described in this short viewgraph presentation: locating address blocks, cleaning document images by removing noise, and locating areas of interest in personal checks to improve image compression. Several of the ideas realized in this circuit that were inspired by neural nets, such as analog computation with a low resolution, resulted in a chip that is well suited for real-world document analysis applications and that compares favorably with alternative, 'conventional' circuits.

Graf, Hans Peter↗

NASA NTRS1993

Topography from shading and stereo

Horn, Berthold P.↗

NASA NTRS1995

Verification Test of Automated Robotic Assembly of Space Truss Structures

A multidisciplinary program has been conducted at the Langley Research Center to develop operational procedures for supervised autonomous assembly of truss structures suitable for large-aperture antennas. The hardware and operations required to assemble a 102-member tetrahedral truss and attach 12 hexagonal panels were developed and evaluated. A brute-force automation approach was used to develop baseline assembly hardware and software techniques. However, as the system matured and operations were proven, upgrades were incorporated and assessed against the baseline test results. These upgrades included the use of distributed microprocessors to control dedicated end-effector operations, machine vision guidance for strut installation, and the use of an expert system-based executive-control program. This paper summarizes the developmental phases of the program, the results of several assembly tests, and a series of proposed enhancements. No problems that would preclude automated in-space assembly or truss structures have been encountered. The test system was developed at a breadboard level and continued development at an enhanced level is warranted.

Rhodes, Marvin D.↗

NASA NTRS1998

Three Dimensional Urban Characterization by IFSAR Measurements

In this paper a machine vision approach is applied to Interferometric Synthetic Aperture Radars (IFSAR) data to extract the most relevant built structures in a dense urban environment. The algorithm tries to cluster primitives (line segments) into more complex surfaces (planes) to approximate the 3D shape of these objects. Very interesting results starting from TOPSAR data recorded over S, Monica are presented.

Gamba, P.↗

NASA NTRS2000

Tera-Ops Processing for ATR

A three-dimensional microelectronic device (3DANN-R) capable of performing general image convolution at the speed of 1012 operations/second (ops) in a volume of less than 1.5 cubic centimeter has been successfully built under the BMDO/JPL VIGILANTE program. 3DANN-R was developed in partnership with Irvine Sensors Corp., Costa Mesa, California. 3DANN-R is a sugar-cube-sized, low power image convolution engine that in its core computation circuitry is capable of performing 64 image convolutions with large (64x64) windows at video frame rates. This paper explores potential applications of 3DANN-R such as target recognition, SAR and hyperspectral data processing, and general machine vision using real data and discuss technical challenges for providing deployable systems for BMDO surveillance and interceptor programs.

Udomkesmalee, Suraphol↗

NASA NTRS1998

VR for Mars Pathfinder

Virtual reality (VR) technology has played an integral role for Mars Pathfinder mission, operations Using an automated machine vision algorithm, the 3d topography of the Martian surface was rapidly recovered fro -a the stereo images captured. by the Tender camera to produce photo-realistic 3d models, An advanced, interface was developed for visualization and interaction with. the virtual environment of the Pathfinder landing site for mission scientists at the Space Flight Operations Facility of the Jet Propulsion Laboratory. The VR aspect of the display allowed mission scientists to navigate on Mars in Bud while remaining here on Earth, thus improving their spatial awareness of the rock field that surrounds the lenders Measurements of positions, distances and angles could be easily extracted from the topographic models, providing valuable information for science analysis and mission. planning. Moreover, the VR map of Mars has also been used to assist with the archiving and planning of activities for the Sojourner rover.

Blackmon, Theodore↗

NASA NTRS1998

Back in Time

Under a Jet Propulsion Laboratory SBIR (Small Business Innovative Research), Cambridge Research and Instrumentation Inc., developed a new class of filters for the construction of small, low-cost multispectral imagers. The VariSpec liquid crystal enables users to obtain multi-spectral, ultra-high resolution images using a monochrome CCD (charge coupled device) camera. Application areas include biomedical imaging, remote sensing, and machine vision.

Source record↗

NASA NTRS1992

Controllable Mirror Devices

A deformable Mirror Device (DMD) is a type of spatial light modulator in which mirrors fabricated monolithically on a silicon chip are deformed, or tilted, under electronic control to change the direction of light that falls upon the mirror. NASA and Texas Instruments (TI) have worked to develop this technology, which has subsequently been commercialized by TI. Initial application is the DMD 2000 Travel Information Printer for high speed, high volume printing of airline tickets and boarding passes. Other possible applications range from real-time object tracking to advanced industrial machine vision systems.

Source record↗