Model-Based 3D Rigid Objects Tracking
 
The goal of this work is to develop a visual object tracking system that can give accurate 3D pose -- both position and orientation in 3D Cartesian space -- of a rigid object. Our system tracks a target object by applying a model-based pose estimation algorithm sequentially to the images in the input sequence.
 
Typically with model-based pose estimation approaches, the features on the target object model are projected on to the input scenes. The correspondences between the projected model features and the scene features extracted from the input scenes are then sought.  The pose of the target is estimated by minimizing the corresponding model and scene features.
 
For estimating the correspondences between the projected model features and the scene features extracted from input scenes, we use a hypothesis generation and verification framework.  Our hypothesis-based correspondence search algorithm shows high level of robustness to image sequences with severe occlusion and highly cluttered background.
A few tracking sequences with our model-based tracking algorithm are listed below:
PROJECT TEAM
 
    •    Youngrock Yoon
 
PUBLICATIONS
 
Y. Yoon, A. Kosaka, J. B. Park and A. C. Kak, "A New Approach to the Use of Edge Extremities for Model-based Object Tracking", in Proceedings of the 2005 IEEE International Conference on Robotics and Automation, pp. 1883-1889, Barcelona, Spain, April 2005 [pdf]
 
VIDEOS
 
QUANTITATIVE ACCURACY ANALYSIS
 
       
Station Smooth                                                    Truck Smooth
 
       
Station 400                                                                Truck 750
 
       
Station 450                                                                Truck 800
 
       
Station non-smooth                                                    Truck non-smooth
 
QUALITATIVE TRACKING RESULTS
 
       
Station-Clutter                                                                Truck-Clutter
 
       
Station-Occlusion                                                          Truck-Occlusion
 
       
Jeep                                                                               Camera
 
Real-Time Tracking Demo Video
 
 
 
RELATED PROJECTS
 
 
 
PROJECT DESCRIPTION