We describe the implementation of a biologically motivated model of the human visual system (HVS) on the Paragon XP/S. The approach involves the simulation of the two major pathways (magno-(M), and par-vocellular (P)) of processing visual stimuli including (i) retinal sampling, (ii) active foveation and (iii) object recognition. Theory suggests a vision model based on the competition of active ...

This paper presents an efficient adaptation and application of the Dempster-Shafer theory of evidence, one that can be used effectively in a massively parallel hierarchical system for visual pattern perception. It describes the techniques used, and shows in an extended example how they serve to improve the system's performance as it applies a multiple-level set of processes.

An approach for designing a hybrid parallel system that can perform di erent levels of parallelism adaptively is presented. An adaptive parallel computer vision system (APVIS) is proposed to attain this goal. The APVIS is constructed by integrating two di erent types of parallel architectures, i.e., a multiprocessor based system (MBS) and a memory based processor array (MPA), tightly into a sin...

This paper proposes a parallel matching algorithm for feature-based stereo vision. Features are zero-crossing (ZC) points detected with various sizes of Laplacian-Gaussian filters. In order to obtain candidate intervals of disparity, the disparity histogram is computed all over the image. The image is, then, divided into small areas and the disparity histogram in each local area is computed wit...

This paper describes current research on neural networks within the collaborative project "Vision by Associative Reasoning" 1. The major aim of the work is the matching of vector descriptions of maps to airbourne IR imagery. The primary application of the work is in the guidance of airbourne vehicles. The paper describes how neural networks are being used to identify urban and field areas and f...

ions a n d customized communication protocols accessible f rom every parallel-programming model. Tab le 2 shows t h e relatively small amoun t of coding w e had t o d o t o in tegra te t h e various Checkers subsystems. O u r ability t o build t h e stylized da ta abstractions a n d communication proto-ions a n d communication protocols used in Checkers suggests that w e will have little diffic...

The computational model on which the algorithms are developed is the arrays with reconfigurable optical buses (abbreviated to AROB). It integrates the advantages of both optical transmission and electronic computation. In this paper, instead of using the radix-2 system, a radix-x system can be used to represent the numbers of the intermediate results of algorithms. We first design two Oð1Þ time...

Sparse arrays are arrays in which the number of non-zero elements is a small fraction of the total number of array elements. This paper presents computer vision algorithms using sparse representations for arrays. The parallel architecture considered is a hypercube. The algorithms can be easily modified for other architectures like the mesh. We assume that the architecture is SIMD, i.e., all PEs...

In the last one hundred years, colour vision has been demonstrated in bees and many other insects. But the underlying neural wiring remained elusive. A new study on Drosophila melanogaster combining behavioural and genetic tools yields surprising insights.