A Deformable Object Tracking Algorithm Robust to Occlusions and Spurious Edges

Deformable object tracking is used in many robotics applications including biomanipulation, vision-based force sensing, and the control of deformable structures. A tracking algorithm that is robust to occlusions and to spurious edges is essential since these situations can arise unexpectedly in the unstructured environments in which robots must operate. This paper presents a deformable object tracking algorithm that is robust to occlusion and to spurious edges. Robust statistical methods are used to handle occlusion and a modification of the Canny edge detector is presented to handle spurious edges. The modification of the Canny edge operator makes use of information about the object being tracked in order to eliminate spurious edges. The deformable object tracking algorithm's performance is evaluated visually and quantitively by tracking a four degree-of-freedom compliant gripper.

Authors

• Michael A. Greminger
• Bradley J. Nelson

Keywords

• Robustness
• Grippers
• Robot vision systems
• Robot sensing systems
• Intelligent robots
• Force measurement
• Image edge detection
• Micromechanical devices
• Deformable models
• Mechanical engineering
• Tracking Algorithm
• Deformable Objects
• Spurious Edges
• Degrees Of Freedom
• Edge Detection
• Canny Edge Detection
• Neural Network
• Artificial Neural Network
• Image Pixels
• Finite Element Method
• Normal Vector
• Rigid Body
• Error Function
• Object Of Interest
• Affine Transformation
• Image Edge
• Template Matching
• Fiducial Markers
• Training Pairs
• Neural Classifier
• Edge Pixels
• Boundary Element Method
• Least Square Error
• Occlusion Problem
• Real-world Scenes
• True Edges
• Image Gradient
• Deformation Model
• Neural Network Training
• Edge Detection Algorithm
• Deformable templates
• nonrigid tracking
• robust tracking