Tracking Techniques for Visual Servoing Tasks

Many of today's visual servoing systems rely on the use of markers on the object to provide features for control. There is thus a need for a visual system that provides control features regardless of the appearance of the object. Region based tracking is a natural approach since it does not require any special type of features. In this paper we present two different approaches to region based tracking: 1) a multi-resolution gradient based approach (using optical flow); and 2) a discrete feature based search approach. We present experiments conducted with both techniques for different types of image motions. Finally, the performance, drawbacks and limitations of used techniques are discussed.

Authors

• Danica Kragic
• Henrik I. Christensen

Keywords

• Visual servoing
• Robots
• Tracking
• Computer vision
• Numerical analysis
• Control systems
• Grippers
• Image motion analysis
• Motion estimation
• Visual system
• Need For Systems
• Object Appearance
• Cross-correlation
• Translational Motion
• Motion Model
• Rigid Transformation
• Adaptive Selection
• Dissimilarity Measure
• 3D Motion
• Image Coordinates
• Feature Tracking
• Sum Of Squared Differences
• Discrete Approach
• Spatial Content
• Motion Field
• Pyramid Level
• Robotic Gripper
• Track Loss
• Template Feature