SEARCH · Search NASA
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.
Vision system for robotic welder looks at weld along axis of welding electrode. Gives robot view of most of weld area, including yet-unwelded joint, weld pool, and completed weld bead. Protected within welding-torch body, lens and fiber bundle give robot closeup view of weld in progress. Relayed to video camera on robot manipulator frame, weld image provides data for automatic control of robot motion and welding parameters.
Gas/tungsten-arc welding torch supports electrode at center while enabling viewing of weld area along torch axis. Gas torch accommodates lens and optical fibers, all part of vision system for welding robot. Welding torch includes spoked structure in central bore of optical body. Structure supports welding electrode, carries electric current to it, and takes heat away from it. Spokes formed by drilling six holes 60 degrees apart around center line of torch.
Problems which will be encountered by computer vision systems in Space Station operations are discussed, along with solutions be examined at Johnson Space Station. Lighting cannot be controlled in space, nor can the random presence of reflective surfaces. Task-oriented capabilities are to include docking to moving objects, identification of unexpected objects during autonomous flights to different orbits, and diagnoses of damage and repair requirements for autonomous Space Station inspection robots. The approaches being examined to provide these and other capabilities are television IR sensors, advanced pattern recognition programs feeding on data from laser probes, laser radar for robot eyesight and arrays of SMART sensors for automated location and tracking of target objects. Attention is also being given to liquid crystal light valves for optical processing of images for comparisons with on-board electronic libraries of images.
Work performed as a step toward an intelligent automatic machine vision system for 3-D imaging is discussed. The problem considered is the quantitative 3-D reconstruction of rigid objects. Motion and stereo are the two clues considered in this system. The system basically consists of three processes: the low level process to extract image features, the middle level process to establish the correspondence in the stereo (spatial) and motion (temporal) modalities, and the high level process to compute the 3-D coordinates of the corner points by integrating the spatial and temporal correspondences.
Learning control algorithms have been proposed for error compensation in repetitive robotic manipulator tasks. It is shown that the performance of such control algorithms can be seriously degraded when the feedback data they use is relatively sparse in time, such as might be provided by vision systems. It is also shown that learning control algorithms can be modified to compensate for the effects of sparse data and thereby yield performance which approaches that of systems without limitations on the sensory information available for control.
A simulator evaluation of a cockpit display format for hovering flight is described. The display format is based upon the position-velocity-acceleration representation (PVA) similar to that used in the Pilot Night Vision System in the Army AH-64 helicopter. By only varying the nature of the display law driving the 'primary' indicator in the PVA format, i.e. the acceleration symbol, three candidate displays are created and evaluated. These range from a Status display in which the primary indicator provides true acceleration information to a Command display, in which the primary indicator provides flight director information. Simulation results indicate that two of the three displays offer performance and handling qualities which make them excellent candidates for future helicopter cockpit display systems.
Conceptual robot-vision system processes data from both microwave and visible-wavelength sensors. Concept, called "fusion of sensors," yields better information on shapes of some objects than obtained from one type of sensor alone. Proposed system fuses data from television images with polarized low-resolution radar-scattering cross sections. Using iterative procedure, generates successive approximations to shape of target by minimizing differences between observed radar returns and radar returns observed if object characterized by computed scattering transfer matrix.
A simulator evaluation of a cockpit display format for hovering flight is described. The display format is based on the position-velocity-acceleration representation (PVA) similar to that used in the Pilot Night Vision System in the Army AH-64 helicopter. By only varying the nature of the display law driving the primary indicator in the PVA format, i.e., the acceleration symbol, three candidate displays are created and evaluated. These range from a Status display in which the primary indicator provides true acceleration information to a Command display, in which the primary indicator provides flight director information. Simulation results indicate that two of the three displays offer performance and handling qualities which make them excellent candidates for future helicopter cockpit display systems.
Recent developments in the theory of early vision are described which lead from the formulation of the motion problem as an ill-posed one to its solution by minimizing certain 'cost' functions. These cost or energy functions can be mapped onto simple analog and digital resistive networks. It is shown how the optical flow can be computed by injecting currents into resistive networks and recording the resulting stationary voltage distribution at each node. These networks can be implemented in cMOS VLSI circuits and represent plausible candidates for biological vision systems.
Orientation-dependent techniques for the identification of a three-dimensional object by a machine vision system are represented in parts. In the first part, the data consist of intensity images of polyhedral objects obtained by a single camera, while in the second part, the data consist of range images of curved objects obtained by a laser scanner. In both cases, the attributed graphic representation of the object surface is used to drive the respective algorithm. In this representation, a graph node represents a surface patch and a link represents the adjacency between two patches. The attributes assigned to nodes are moment invariants of the corresponding face for polyhedral objects. For range images, the Gaussian curvature is used as a segmentation criterion for providing symbolic shape attributes. Identification is achieved by an efficient graph-matching algorithm used to match the graph obtained from the data to a subgraph of one of the model graphs stored in the commputer memory.
Proposed remote vision system provides simultaneous viewing of front and back of workpiece while being welded. Enables human or automatic controller to monitor both weld pool on front and weld penetration on back. Nitrogen laser generates ultraviolet light, distributed to both sides of workpiece through two optical fiber cables. Image-intensifier tubes convert reflected ultraviolet light to visible light. Video cameras equipped with high-resolution charge-coupled devices convert visible outputs of image intensifiers into images for viewing on video monitors.
Arc-light reflector for through-the-torch welding vision system designed expressly for use in welding ducts of small diameter. Cylindrical reflector positioned to reflect light diffusely from welding arc onto nearby surface of workpiece for most advantageous viewing along axis of welding torch.
This research is part of the Human Interface Research Branch-Vision Group's program to develop computable models of biological solutions to general vision system problems. Two problem areas are addressed: effects of discrete sampling by receptors, and effects of visual system noise.
A telerobotic control station is described. In it, a machine vision system measures the position, orientation, and configuration of a user's hand. A robotic manipulator mirrors the status of the hand. This concept has two benefits: control actions are intuitive and easily learned, and the workstation requires little volume or mass.
An assembly problem in a non-deterministic environment, i.e., where parts to be assembled have unknown shape, size and location, is described. The only knowledge used by the robot to perform the assembly operation is given by a connectivity rule and geometrical constraints concerning parts. Once a set of geometrical features of parts has been extracted by a vision system, applying such a rule allows the dtermination of the composition sequence. A suitable sensory apparatus allows the control the whole operation.
A hyrbid real-time vision system concept is proposed for Mars lander guidance and control for the Mars Rover/Sample Return mission. The system includes digital and optical processing methods with high speed digital image warping to preprocess a video image for optical correlation. The system also includes position estimation by synthetic estimation filtering, image stabilization by joint transform optical correlation, and hazard identification from measurements of optical flow by sequential image subtraction.
Various papers on image compression and automatic target recognition are presented. Individual topics addressed include: target cluster detection in cluttered SAR imagery, model-based target recognition using laser radar imagery, Smart Sensor front-end processor for feature extraction of images, object attitude estimation and tracking from a single video sensor, symmetry detection in human vision, analysis of high resolution aerial images for object detection, obscured object recognition for an ATR application, neural networks for adaptive shape tracking, statistical mechanics and pattern recognition, detection of cylinders in aerial range images, moving object tracking using local windows, new transform method for image data compression, quad-tree product vector quantization of images, predictive trellis encoding of imagery, reduced generalized chain code for contour description, compact architecture for a real-time vision system, use of human visibility functions in segmentation coding, color texture analysis and synthesis using Gibbs random fields.
The extraction of buildings from aerial imagery is a complex problem for automated computer vision. It requires locating regions in a scene that possess properties distinguishing them as man-made objects as opposed to naturally occurring terrain features. It is reasonable to assume that no single detection method can correctly delineate or verify buildings in every scene. A cooperative-methods paradigm is useful in approaching the building extraction problem. Using this paradigm, each extraction technique provides information which can be added or assimilated into an overall interpretation of the scene. Thus, the main objective is to explore the development of computer vision system that integrates the results of various scene analysis techniques into an accurate and robust interpretation of the underlying three dimensional scene. The problem of building hypothesis fusion in aerial imagery is discussed. Building extraction techniques are briefly surveyed, including four building extraction, verification, and clustering systems. A method for fusing the symbolic data generated by these systems is described, and applied to monocular image and stereo image data sets. Evaluation methods for the fusion results are described, and the fusion results are analyzed using these methods.