Advanced

Vision Algorithms for Ball on Beam and Plate

Espersson, Magnus (2010) In MSc Theses
Department of Automatic Control
Abstract
The ball-and-beam process is one of the most famous control laboratory processes [1]. At the Department of Automatic Control at Lund Institute of Technology a light-weight ballandbeam process has been made portable by implementing the controls on a laptop with a webcam. The main contribution of this master thesis was the testing and implementation of a variety of vision-based algorithms used to localize the beam, the ball on it and calculate the angle of the beam. A soft-real-time controller was also implemented which used the camera sampling period. Identification of gestures was used to set reference points on the beam. For further testing of the algorithms a ball-on-plate process was implemented using an IRB2400 6-axis robot, using... (More)
The ball-and-beam process is one of the most famous control laboratory processes [1]. At the Department of Automatic Control at Lund Institute of Technology a light-weight ballandbeam process has been made portable by implementing the controls on a laptop with a webcam. The main contribution of this master thesis was the testing and implementation of a variety of vision-based algorithms used to localize the beam, the ball on it and calculate the angle of the beam. A soft-real-time controller was also implemented which used the camera sampling period. Identification of gestures was used to set reference points on the beam. For further testing of the algorithms a ball-on-plate process was implemented using an IRB2400 6-axis robot, using hard-real-time (Less)
Please use this url to cite or link to this publication:
author
Espersson, Magnus
supervisor
organization
year
type
H3 - Professional qualifications (4 Years - )
subject
publication/series
MSc Theses
report number
TFRT-5859
ISSN
0280-5316
language
English
id
8847458
date added to LUP
2016-03-16 12:31:50
date last changed
2016-03-16 12:31:50
@misc{8847458,
  abstract     = {The ball-and-beam process is one of the most famous control laboratory processes [1]. At the Department of Automatic Control at Lund Institute of Technology a light-weight ballandbeam process has been made portable by implementing the controls on a laptop with a webcam. The main contribution of this master thesis was the testing and implementation of a variety of vision-based algorithms used to localize the beam, the ball on it and calculate the angle of the beam. A soft-real-time controller was also implemented which used the camera sampling period. Identification of gestures was used to set reference points on the beam. For further testing of the algorithms a ball-on-plate process was implemented using an IRB2400 6-axis robot, using hard-real-time},
  author       = {Espersson, Magnus},
  issn         = {0280-5316},
  language     = {eng},
  note         = {Student Paper},
  series       = {MSc Theses},
  title        = {Vision Algorithms for Ball on Beam and Plate},
  year         = {2010},
}