A Shape Tracking Algorithm for Visual Servoing

The paper contributes to presenting both an accurate and robust shape tracking algorithm and a novel visual servoing method. Two steps are involved in the tracking algorithm. Firstly the object shape is assumed to vary under an affine model, and the edge detection is performed along the normal lines to the contour. As a result it is possible to use a Kalman filter to perform efficient tracking. The second step concerns image matching based on perspective model, which is achieved iteratively by searching locally along the normal lines also. As to visual servoing we propose to control the translations of the robot with the normalized zeroth and first order image moments, and to control the orientation with rotation axis and angle extracted from a Homography matrix. Two experiments demonstrate that the tracking algorithm is accurate and robust enough to be used in visual servoing, and the novel visual servoing method is superior to traditional ones.

Authors

• Peihua Li
• François Chaumette
• Omar Tahri

Keywords

• Visual servoing
• Robustness
• Shape control
• Transmission line matrix methods
• Cameras
• Image matching
• Robot vision systems
• Control systems
• Particle filters
• Image edge detection
• Tracking Algorithm
• Image Registration
• Kalman Filter
• Visual Methods
• Rotation Axis
• Edge Detection
• Object Shape
• Tracking Accuracy
• Axis Angle
• Affine Model
• Image Moments
• Homography Matrix
• Measurement Model
• Visual Features
• Autoregressive Model
• Nonlinear Problem
• Complex Situations
• Continuous System
• Tracking Error
• Current Curves
• Tracking Results
• Camera Rotation
• Motion Model
• Natural Shape
• Particle Filter
• Types Of Frames
• Object tracking