Abstract—We have proposed a 3D object tracking framework
with a Coarse-to-Fine combination strategy for robot vision
applications. In the coarse step, compared with those edgebased
only methods, the convergence range of initial camera
pose estimation has been enlarged in our system by a templatebased
matching between a series of template images rendered
from Computer Graphics (CG) and a current image. In the fine
step an edge-based object tracking method is used to realize a
more accurate visual tracking application with the results from
the previous coarse step. In the video, two experiments have been
carried out to evaluate our proposed template-based matching
method using CG images. An application demo is included to
show that our strategy is applicable for a real robot system.