Book chapter
Chapter 3 - Using Active Deformable Models in Robotic Visual Servoing
Control in Robotics and Automation, pp.91-113
Academic Press
1999
DOI: 10.1016/B978-012281845-5/50004-3
Abstract
This chapter presents an approach to visual servoing using active deformable models to track image contours. It uses deformable active models to track image contours related to the object of interest. These contour models provide global information about the position of the object. In addition, by combining such models with a priori knowledge of the object shape, this approach may be extended to provide the orientation of the object in three dimensions. The chapter also presents a model-based approach for visual tracking and eye-in-hand robotic visual servoing. The approach uses active deformable models to track a rigid or a semi-rigid object in the manipulator's work space. These deformable models approximate the contour of the object boundary, defined by a set of control points. During tracking, the control points are updated at frame rates by minimizing an energy function involving the relative position of model points, image data, and the characteristics of figure pixels. When visual servoing is combined with the use of active deformable models, movement of the manipulator can compensate for the translations and deformations of the object's image. To verify the potential of the approach, several experiments are run and their findings are presented.
Details
- Title: Subtitle
- Chapter 3 - Using Active Deformable Models in Robotic Visual Servoing
- Creators
- Michael J. Sulliva - University of MinnesotaNikolaos P. Papanikolopoulos - University of MinnesotaRahul SinghIoannis Pavlidis - University of Minnesota
- Resource Type
- Book chapter
- Publication Details
- Control in Robotics and Automation, pp.91-113
- Publisher
- Academic Press
- DOI
- 10.1016/B978-012281845-5/50004-3
- Language
- English
- Date published
- 1999
- Academic Unit
- Computer Science
- Record Identifier
- 9984455943202771
Metrics
1 Record Views