Download Free Parallel Architectures And Parallel Algorithms For Integrated Vision Systems Book in PDF and EPUB Free Download. You can read online Parallel Architectures And Parallel Algorithms For Integrated Vision Systems and write the review.

Computer vision is one of the most complex and computationally intensive problem. Like any other computationally intensive problems, parallel pro cessing has been suggested as an approach to solving the problems in com puter vision. Computer vision employs algorithms from a wide range of areas such as image and signal processing, advanced mathematics, graph theory, databases and artificial intelligence. Hence, not only are the comput ing requirements for solving vision problems tremendous but they also demand computers that are efficient to solve problems exhibiting vastly dif ferent characteristics. With recent advances in VLSI design technology, Single Instruction Multiple Data (SIMD) massively parallel computers have been proposed and built. However, such architectures have been shown to be useful for solving a very limited subset of the problems in vision. Specifically, algorithms from low level vision that involve computations closely mimicking the architec ture and require simple control and computations are suitable for massively parallel SIMD computers. An Integrated Vision System (IVS) involves com putations from low to high level vision to be executed in a systematic fashion and repeatedly. The interaction between computations and information dependent nature of the computations suggests that architectural require ments for computer vision systems can not be satisfied by massively parallel SIMD computers.

Netra

National Aeronautics and Space Administration (NASA)

Published: 2018-07-09

Total Pages: 44


Get eBook

Computer vision is regarded as one of the most complex and computationally intensive problems. An integrated vision system (IVS) is considered to be a system that uses vision algorithms from all levels of processing for a high level application (such as object recognition). A model of computation is presented for parallel processing for an IVS. Using the model, desired features and capabilities of a parallel architecture suitable for IVSs are derived. Then a multiprocessor architecture (called NETRA) is presented. This architecture is highly flexible without the use of complex interconnection schemes. The topology of NETRA is recursively defined and hence is easily scalable from small to large systems. Homogeneity of NETRA permits fault tolerance and graceful degradation under faults. It is a recursively defined tree-type hierarchical architecture where each of the leaf nodes consists of a cluster of processors connected with a programmable crossbar with selective broadcast capability to provide for desired flexibility. A qualitative evaluation of NETRA is presented. Then general schemes are described to map parallel algorithms onto NETRA. Algorithms are classified according to their communication requirements for parallel processing. An extensive analysis of inter-cluster communication strategies in NETRA is presented, and parameters affecting performance of parallel algorithms when mapped on NETRA are discussed. Finally, a methodology to evaluate performance of algorithms on NETRA is described. Choudhary, Alok N. and Patel, Janak H. and Ahuja, Narendra Unspecified Center NAG1-613...
Proceedings -- Parallel Computing.
Over the last twenty years, automation and robotics have played an increasingly important role in a variety of application domains including manufacturing, hazardous environments, defense, and service industries. Space is a unique environment where power, communications, atmospheric, gravitational, and sensing conditions impose harsh constraints on the ability of both man and machines to function productively. In this environment, intelligent automation and robotics are essential complements to the capabilities of humans. In the development of the United States Space Program, robotic manipulation systems have increased in importance as the complexity of space missions has grown. Future missions will require the construction, maintenance, and repair of large structures, such as the space station. This volume presents the effords of several groups that are working on robotic solutions to this problem. Much of the work in this book is related to assembly in space, and especially in-orbit assembly of large truss structures. Many of these so-called truss structures will be assembled in orbit. It is expected that robot manipulators will be used exclusively, or at least provide partial assistance to humans. Intelligent Robotic Systems for Space Exploration provides detailed algorithms and analysis for assembly of truss structure in space. It reports on actual implementations to date done at NASA's Langley Research Center. The Johnson Space Center, and the Jet Propulsion Laboratory. Other implementations and research done at Rensselaer are also reported. Analysis of robot control problems that are unique to a zero-gravity environment are presented.
Since the late 1960s, there has been a revolution in robots and industrial automation, from the design of robots with no computing or sensorycapabilities (first-generation), to the design of robots with limited computational power and feedback capabilities (second-generation), and the design of intelligent robots (third-generation), which possess diverse sensing and decision making capabilities. The development of the theory of intelligent machines has been developed in parallel to the advances in robot design. This theory is the natural outcome of research and development in classical control (1950s), adaptive and learning control (1960s), self-organizing control (1970s) and intelligent control systems (1980s). The theory of intelligent machines involves utilization and integration of concepts and ideas from the diverse disciplines of science, engineering and mathematics, and fields like artificial intelligence, system theory and operations research. The main focus and motivation is to bridge the gap between diverse disciplines involved and bring under a common cover several generic methodologies pertaining to what has been defined as machine intelligence. Intelligent robotic systems are a specific application of intelligent machines. They are complex computer controlled robotic systems equipped with a diverse set of visual and non visual sensors and possess decision making and problem solving capabilities within their domain of operation. Their modeling and control is accomplished via analytical and heuristic methodologies and techniques pertaining to generalized system theory and artificial intelligence. Intelligent Robotic Systems: Theory, Design and Applications, presents and justifies the fundamental concepts and ideas associated with the modeling and analysis of intelligent robotic systems. Appropriate for researchers and engineers in the general area of robotics and automation, Intelligent Robotic Systems is both a solid reference as well as a text for a graduate level course in intelligent robotics/machines.
Some twenty years have elapsed since the first attempts at planning were made by researchers in artificial intelligence. These early programs concentrated on the development of plans for the solution of puzzles or toy problems, like the rearrangement of stacks of blocks. These early programs provided the foundation for the work described in this book, the automatic generation of plans for industrial assembly. As one reads about the complex and sophisticated planners in the current gen eration, it is important to keep in mind that they are addressing real-world problems. Although these systems may become the "toy" systems of tomor row, they are providing a solid foundation for future, more general and more advanced planning tools. As demonstrated by the papers in this book, the field of computer-aided mechanical assembly planning is maturing. It now may include: • geometric descriptions of parts extracted from or compatible with CAD programs; • constraints related to part interference and the use of tools; • fixtures and jigs required for the assembly; • the nature of connectors, matings and other relations between parts; • number of turnovers required during the assembly; • handling and gripping requirements for various parts; • automatic identification of subassemblies. This is not an exhaustive list, but it serves to illustrate the complexity of some of the issues which are discussed in this book. Such issues must be considered in the design of the modern planners, as they produce desirable assembly sequences and precedence relations for assembly.
Dynamic modeling is the fundamental building block for mechanism analysis, design, control and performance evaluation. One class of mechanism, legged machines, have multiple closed-chains established through intermittent ground contacts. Further, walking on natural terrain introduces nonlinear system compliance in the forms of foot sinkage and slippage. Closed-chains constrain the possible motions of a mechanism while compliances affect the redistribution of forces throughout the system. A General Model of Legged Locomotion on Natural Terrain develops a dynamic mechanism model that characterizes indeterminate interactions of a closed-chain robot with its environment. The approach is applicable to any closed-chain mechanism with sufficient contact compliance, although legged locomotion on natural terrain is chosen to illustrate the methodology. The modeling and solution procedures are general to all walking machine configurations, including bipeds, quadrupeds, beam-walkers and hopping machines. This work develops a functional model of legged locomotion that incorporates, for the first time, non-conservative foot-soil interactions in a nonlinear dynamic formulation. The model was applied to a prototype walking machine, and simulations generated significant insights into walking machine performance on natural terrain. The simulations are original and essential contributions to the design, evaluation and control of these complex robot systems. While posed in the context of walking machines, the approach has wider applicability to rolling locomotors, cooperating manipulators, multi-fingered hands, and prehensile agents.