A Dual Source, Parallel Architecture for Computer Vision

Authors:
A. M. Wallace;G. J. Michaelson;N. Scaife;W. J. Austin
Affiliations:
Department of Computing and Electrical Engineering, Heriot–Watt University, Riccarton, Edinburgh EH14 4AS E-mail: andy@cee.hw.ac.uk;Department of Computing and Electrical Engineering, Heriot–Watt University, Riccarton, Edinburgh EH14 4AS E-mail: greg@cee.hw.ac.uk;Department of Computing and Electrical Engineering, Heriot–Watt University, Riccarton, Edinburgh EH14 4AS E-mail: norman@cee.hw.ac.uk;Department of Computing and Electrical Engineering, Heriot–Watt University, Riccarton, Edinburgh EH14 4AS E-mail: billa@icbl.hw.ac.uk
Venue:
The Journal of Supercomputing
Year:
1998

Citing 12
Cited 2

Invariant surface characteristics for 3D object recognition in range images

Computer Vision, Graphics, and Image Processing - Lectures notes in computer science, Vol. 201 (G. Goos and J. Hartmanis, Eds.)
A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Object recognition and localization via pose clustering

Computer Vision, Graphics, and Image Processing
Parallelism in computer vision: a review

Parallel algorithms for machine intelligence and vision
Multiprocessor 3D vision system for pick and place

Image and Vision Computing
MARVIN and TINA: a multiprocessor 3-D vision system

Concurrency: Practice and Experience
Algorithmic skeletons: structured management of parallel computation

Algorithmic skeletons: structured management of parallel computation
Dynamic Control and Prototyping of Parallel Algorithms for Intermediate- and High-Level Vision

Computer
Compilation and sufficient representation of object models for visual recognition

Pattern Recognition Letters
Which Hough transform?

CVGIP: Image Understanding
Recognition and location by parallel pose clustering

BMVC '95 Proceedings of the 6th British conference on Machine vision (Vol. 2)
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM

Comparative Cross-Platform Performance Results from a Parallelizing SML Compiler

IFL '02 Selected Papers from the 13th International Workshop on Implementation of Functional Languages
Skeleton realisations from functional prototypes

Patterns and skeletons for parallel and distributed computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a parallel architecture for object recognition andlocation based on concurrent processing of depth and intensity image data.Parallel algorithms for curvature computation and segmentation of depth datainto planar or curved surface patches, and edge detection and segmentationof intensity data into extended linear features, are described. Using thisfeature data in comparison with a CAD model, objects can be located ineither depth or intensity images by a parallel pose clustering algorithm. The architecture is based on cooperating stages for low/intermediatelevel processing and for high level matching. Here, we discuss the use ofindividual components for depth and intensity data, and their realisationand integration within each parallel stage. We then present an analysis ofthe performance of each component, and of the system as a whole,demonstrating good parallel execution from raw image data to final pose.