the authors present vision system based on the object-properties-relationships abstraction. It combines different approaches to knowledge representation and uses structured rules which support goal-directed as well as...
详细信息
the authors present vision system based on the object-properties-relationships abstraction. It combines different approaches to knowledge representation and uses structured rules which support goal-directed as well as data driven inferencing, and accommodates some degree of parallelprocessing. the purpose of the system is to draw a distinction between domain-independent and domain-specific structures and processes.< >
An efficient skeletonizing algorithm is presented for the hexagonal grid. the skeleton has unit width, except at crossings and in regions of the shape having even width. Otherwise the skeleton has all the properties g...
详细信息
An efficient skeletonizing algorithm is presented for the hexagonal grid. the skeleton has unit width, except at crossings and in regions of the shape having even width. Otherwise the skeleton has all the properties generally required for correct skeletons. It includes all local maxima, so complete recovery of the original shape is obtained by using the reverse distance transformation. the algorithm uses only local operations. thus it can be performed both on sequential and parallel computers. In the sequential case described only three passes through the image are necessary, two to compute the distance transform and one for the identification of skeletal pixels.< >
A novel graph-theoretic model for describing the relation between a decomposed algorithm and its execution in a multiprocessor environment is developed. Called ATAMM, the model consists of a set of Petri-net marked gr...
详细信息
A novel graph-theoretic model for describing the relation between a decomposed algorithm and its execution in a multiprocessor environment is developed. Called ATAMM, the model consists of a set of Petri-net marked graphs that incorporates the general specifications of a data-flow architecture. the model is useful for representing decision-free algorithms having large-grained, computationally complex primitive operations. Performance measures of computing speed and throughput capacity are defined. the ATAMM model is used to develop analytically lower bounds for these parameters.< >
To detect arbitrary shapes on a binary image quickly, a method is developed for performing the principle of the Hough transform by means of the raster operation (bitblt) hardware, with which a workstation is equipped....
详细信息
To detect arbitrary shapes on a binary image quickly, a method is developed for performing the principle of the Hough transform by means of the raster operation (bitblt) hardware, with which a workstation is equipped. the Boolean operations among bitmaps of images are used to search candidate patterns corresponding to a given shape. Using the bitblt hardware, those operations can be carried out rapidly. the method is applicable not only for shape recognition but also line detection.< >
Scale-space is a representation for detecting and organising intensity changes that occur at various scales in an image. A single-chip VLSI design is proposed for scale-space computation in one and two dimensions. the...
详细信息
Scale-space is a representation for detecting and organising intensity changes that occur at various scales in an image. A single-chip VLSI design is proposed for scale-space computation in one and two dimensions. the architecture of the chip is based on an algorithm that can provide speeds that are an order of magnitude higher than the speeds obtainable from the other systems proposed in the literature. the design uses the principles of modularity, expandability and parallelism, and fully utilizes the three properties of the Gaussian: symmetry, separability, and scaling. the proposed algorithm and the hardware architecture use a very high degree of pipelining and parallelism. the chip can be implemented in either nMOS or CMOS technology.< >
A method is described for the recognition of partially occluded 2-D objects. this method considers a set of corners, parallel lines, and so on as typical features of an object. Possible candidate models are estimated ...
详细信息
A method is described for the recognition of partially occluded 2-D objects. this method considers a set of corners, parallel lines, and so on as typical features of an object. Possible candidate models are estimated from these features, and structural matching is performed between these models and features obtained from a picture by checking the combinations of various features. Even if the whole structure is not obtained due to a partial occlusion, the system can infer an object if some unique features of the object are obtained. Partial shapes and extracted lines are matched in detail with model candidates when they are limited to one or a few.< >
there are numerous places within the general task framework of a computer music workstation where multiprocessing solutions are a natural way to overcome the diversity of tasks and the tight scheduling constraints of ...
详细信息
Rule-based systems appear to be capable of exploiting large amounts of parallelism, because it is possible to match each rule to the data memory in parallel. It is pointed out that in practice the speedup from paralle...
详细信息
ISBN:
(纸本)081860719X
Rule-based systems appear to be capable of exploiting large amounts of parallelism, because it is possible to match each rule to the data memory in parallel. It is pointed out that in practice the speedup from parallelism is quite limited, less than 10-fold. the reasons for the small speedup are: (1) the small number of rules relevant to each change to data memory;(2) the large variation in the processing required by the relevant rules;and (3) the small number of changes made to data memory between synchronization steps. To obtain this limited factor of 10-fold speedup, it is necessary to exploit parallelism at a very fine granularity. It is suggested that a suitable architecture to exploit such fine-grain parallelism is a bus-based shared-memory multiprocessor with 32-64 processors. Using such a multiprocessor (with individual processors working at 2 MIPS), it is possible to obtain execution speeds of about 3800 rule-firings/s. this speed is significantly higher than that obtained by other proposed parallel implementations of rule-based systems.
Approaching rapidly on the horizon is a change to parallel architecture in digital computers that has the potential for multiplying the speed of execution achieved in serial architectures. the departure from serial op...
Approaching rapidly on the horizon is a change to parallel architecture in digital computers that has the potential for multiplying the speed of execution achieved in serial architectures. the departure from serial operations provides rather obvious improvements in execution times for operations that are repetitive and that can be performed independently of each other. Such operations arise frequently in signal processing programs and in mathematical programming algorithms. Of interest to this conference is the impact of the new architectures on the practice of simulation - particularly simulations of large physical systems. A large number of questions can be raised (but few answered) on the impact of the new machines on simulation model designs, languages, data base manipulation, and other questions on the general utility of such machines for simulation problem solving. Moreover, it is likely that the new machines will influence the design of simulation experiments, random number generation, strategies for statistical iterations, sensitivity analyses, and variance reduction methods. Because of the interdisciplinary nature of these topics a dialog between simulation practitioners and computer technology developers will grow in importance. Several panelists, consisting of a mixture of simulation practitioners and computer scientists will describe their recent experiences in simulating systems on parallel computer configurations, highlighting efficiency comparisons and speculating on the general utility of such machines for simulation enterprises.
Hardwired resource allocators for TRAC-like reconfigurable architectures are described. these allocators facilitate searching for available resources in the system and allocation of a subset of these to a given reques...
详细信息
Hardwired resource allocators for TRAC-like reconfigurable architectures are described. these allocators facilitate searching for available resources in the system and allocation of a subset of these to a given request. Various algorithms can be implemented for the search and the allocation of the resources. Tree-structured allocators look particularly attractive withthe cost-delay product being of the order of M* (log M)**2 for a system with M resources of the same type. It is shown how this scheme can be extended to allocate multiple type of resources in the system.
暂无评论