Date of Award
Electrical and Computer Engineering
Engineering, Electronics and Electrical.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
In this thesis, hardware and software design of a vision tracking system is presented. The whole system is a low-cost, flexible 2D device. Three algorithms are implemented in this system for position deviation detection and stretching behavior analysis. The first algorithm, which is based on the statistic approaching method, is developed in this thesis. The other two algorithms, which are based on cross correlation method and the directional flow-change (DFC) method, respectively, are existing algorithms. In this research, both algorithms are modified, implemented and tested. The experiments and the results presented in this thesis show that the first algorithm is a simple, fast, robust and accurate method to estimate the position and the size of the object. The cross correlation based algorithm is suitable for pattern recognition. But for position deviation detection, it is not reliable and need to be improved. The third algorithm is efficient for position deviation detection, and it works well for certain type of shapes. This system can be used as a platform for developing, testing and improving new algorithms. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis2002 .Y346. Source: Masters Abstracts International, Volume: 42-01, page: 0303. Adviser: Xiang Chen. Thesis (M.A.Sc.)--University of Windsor (Canada), 2002.
Yang, Jun., "Design of vision tracking system." (2002). Electronic Theses and Dissertations. 1669.