A multiple in-camera processing system for machine vision.
Date of Award
Electrical and Computer Engineering
Jullien, G. A.
Engineering, Electronics and Electrical.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
In a typical machine vision application, a line-scan camera positioned on the production line captures images of the parts to be inspected and sends them to the machine vision computer. The computer then uses high-speed data acquisition devices and sophisticated analysis software to extract information from these cameras and generates decisions about the product and manufacturing system. As the manufacturing systems increasingly generate more fine featured and advanced products, the need for higher resolution and faster processing of these camera images is necessary to maintain quality control. To reduce the overwhelming amount of data from multiple camera systems to the analysis computer, an in-camera processing system is introduced. This system involves placing a computing system inside the camera which can perform similar operations to the analysis system, but without all of the additional overhead components. The work presented in this thesis describes an enhanced embedded system which is mounted into a DALSA line-scan camera. This system provides support for real-time one dimensional signal processing with the aid of integrated hardware and software resources.Dept. of Electrical and Computer Engineering. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis1999 .M89. Source: Masters Abstracts International, Volume: 40-03, page: 0757. Adviser: Graham A. Jullien. Thesis (M.Sc.)--University of Windsor (Canada), 1999.
Muscedere, Roberto., "A multiple in-camera processing system for machine vision." (1999). Electronic Theses and Dissertations. 675.