The goal of this thesis is to provide algorithm design for smart vision sensors. Two algorithms are developed in this thesis. The first one is based on the correlation analysis method for images and can be implemented to find the 2-dimensional position of a target. In particular, the problem of finding the deviations along both X and Y directions is formulated as a matching process between the saved template, which represents the reference position, and the picture of a real static target captured by a 'vision' element such as a CCD camera, through correlation analysis of the 2-D spatial shift. It is an efficient and simple method for deviation identification of target position with high noise rejection ability. Using this method, 2-D position deviation can be found very accurately with high reliability. The second algorithm, which is based on locating the critical points of a planar shape, can be applied to identifying the pattern and finding the 2-dimensional position deviation and rotation angle of a target. (Abstract shortened by UMI.)Dept. of Electrical and Computer Engineering. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis2001 .G36. Source: Masters Abstracts International, Volume: 40-06, page: 1586. Adviser: Xiang Chen. Thesis (M.A.Sc.)--University of Windsor (Canada), 2001.
Algorithm design for smart vision sensors.
2001-01-01
Electronic Theses and Dissertations
Theses
Electronic Resource
English
DDC: | 629 |
Smart sensors yield fast and robust machine vision
British Library Online Contents | 2000
|Smart laser vision sensors for tyre and rubber inspection
Automotive engineering | 2005
|Online Contents | 1994
|SAE Technical Papers | 1983
|A system approach to smart-sensors and smart-actuators design
Automotive engineering | 1988
|