Considerable evidence exists that visual sensory information is analyzed simultaneously along two or more independent pathways. In the past two decades, researchers have extensively used the concept of parallel visual channels as a framework to direct their explorations of human vision. More recently, basic and clinical scientists have found such a dichotomy applicable to the way we organize our knowledge of visual development, higher order perception, and visual disorders, to name just a few. This volume attempts to provide a forum for gathering these different perspectives.
This comprehensive book is primarily intended for researchers, computer vision specialists, and high-performance computing specialists who are interested in parallelizing computer vision techniques for the sake of accelerating the run-time of computer vision methods. This book covers different penalization methods on different parallel architectures such as multi-core CPUs and GPUs. It is also a valuable reference resource for researchers at all levels (e.g., undergraduate and postgraduate) who are seeking real-life examples of speeding up the computer vision methods’ run-time.
The last 20 years of research have been marked by exceptional progress in understanding the organization and functions of the primate visual system. This understanding has been based on the wide application of traditional and newly emerging methods for identifying the functionally significant subdivisions of the system, their interconnections, the
World-renowned contributors present papers concerning algorithms used on the latest generation of parallel machines (MIMD). Details key applications running the gamut from medical imaging, visualization and remote sensing to HDTV, demonstrating the large computational complexity necessary to perform these tasks.
This historical survey of parallel processing from 1980 to 2020 is a follow-up to the authors’ 1981 Tutorial on Parallel Processing, which covered the state of the art in hardware, programming languages, and applications. Here, we cover the evolution of the field since 1980 in: parallel computers, ranging from the Cyber 205 to clusters now approaching an exaflop, to multicore microprocessors, and Graphic Processing Units (GPUs) in commodity personal devices; parallel programming notations such as OpenMP, MPI message passing, and CUDA streaming notation; and seven parallel applications, such as finite element analysis and computer vision. Some things that looked like they would be major trends in 1981, such as big Single Instruction Multiple Data arrays disappeared for some time but have been revived recently in deep neural network processors. There are now major trends that did not exist in 1980, such as GPUs, distributed memory machines, and parallel processing in nearly every commodity device. This book is intended for those that already have some knowledge of parallel processing today and want to learn about the history of the three areas. In parallel hardware, every major parallel architecture type from 1980 has scaled-up in performance and scaled-out into commodity microprocessors and GPUs, so that every personal and embedded device is a parallel processor. There has been a confluence of parallel architecture types into hybrid parallel systems. Much of the impetus for change has been Moore’s Law, but as clock speed increases have stopped and feature size decreases have slowed down, there has been increased demand on parallel processing to continue performance gains. In programming notations and compilers, we observe that the roots of today’s programming notations existed before 1980. And that, through a great deal of research, the most widely used programming notations today, although the result of much broadening of these roots, remain close to target system architectures allowing the programmer to almost explicitly use the target’s parallelism to the best of their ability. The parallel versions of applications directly or indirectly impact nearly everyone, computer expert or not, and parallelism has brought about major breakthroughs in numerous application areas. Seven parallel applications are studied in this book.
This is one book that can genuinely be said to be straight from the horse’s mouth. Written by the originator of the technique, it examines parallel coordinates as the leading methodology for multidimensional visualization. Starting from geometric foundations, this is the first systematic and rigorous exposition of the methodology's mathematical and algorithmic components. It covers, among many others, the visualization of multidimensional lines, minimum distances, planes, hyperplanes, and clusters of "near" planes. The last chapter explains in a non-technical way the methodology's application to visual and automatic data mining. The principles of the latter, along with guidelines, strategies and algorithms are illustrated in detail on real high-dimensional datasets.
In the mid-sixties, John Robson and Christina Enroth-Cugell, without realizing what they were doing, set off a virtual revolution in the study of the visual system. They were trying to apply the methods of linear systems analysis (which were already being used to describe the optics of the eye and the psychophysical performance of the human visual system) to the properties of retinal ganglion cells in the cat. Their idea was to stimulate the retina with patterns of stripes and to look at the way that the signals from the center and the antagonistic surround of the respective field of each ganglion cell (first described by Stephen Kuffier) interact to generate the cell's responses. Many of the ganglion cells behaved themselves very nicely and John and Christina got into the habit (they now say) of calling them I (interesting) cells. However. to their annoyance, the majority of neurons they recorded had nasty, nonlinear properties that couldn't be predicted on the basis of simple summ4tion of light within the center and the surround. These uncoop erative ganglion cells, which Enroth-Cugell and Robson at first called D (dull) cells, produced transient bursts of impulses every time the distribution of light falling on the receptive field was changed, even if the total light flux was unaltered.
