A parallel implementation of a structure-from-motion algorithm
This paper describes the implementation of a 3D vision algorithm, Droid, on the Oxford parallel vision architecture, PARADOX, and the results of experiments to gauge the algorithm's effectiveness in providing navigation data for an autonomous guided vehicle. The algorithm reconstructs 3D structure by analysing image sequences obtained from a moving camera. In this application, the architecture delivers a performance of greater than 1 frame per second — 17 times the performance of a Sun-4 alone.
KeywordsVision Algorithm Corner Detection Autonomous Vehicle Guidance Analyse Image Sequence Corner Detection Algorithm
Unable to display preview. Download preview PDF.
- 1.D Charnley and R Blisset. Surface reconstruction from outdoor image sequences. Image and Vision Computing, 7(1):10–16, 1989.Google Scholar
- 2.L. De Floriani. Surface representation based on triangular grids. The Visual Computer, 3:27–50, 1987.Google Scholar
- 3.C G Harris and J M Pike. 3D positional integration from image sequences. In Proc. 3rd Alvey Vision Conference, Cambridge, Sept. 1987.Google Scholar
- 4.J.A. Sheen. A parallel architecture for machine vision. In Colloquium on Practical applications of signal processing. Institution of the Electrical Engineers, 1988. Digest no: 1988/111.Google Scholar
- 5.H Wang and C C Bowman. The Oxford distributed machine for 3D vision system. In IEE colloquium on Parallel Architectures for Image Processing Applications, pages 1/2–5/2, London, April 1991.Google Scholar
- 6.H Wang, P M Dew, and J A Webb. Implementation of Apply on a transputer array. CONCURRENCY: Practice and Experience, 3(1):43–54, February 1991.Google Scholar
- 7.Han Wang and Mike Brady. Corner detection for 3D vision using array processors. In BARNAIMAGE 91, Barcelona, Sept. 1991. Springer-Verlag.Google Scholar