In robotic surgery, tool tracking is important for providin
g
safe tool-tissue interaction and facilitating surgical sk
ills assessment. De-
spite recent advances in tool tracking, existing approache
s are faced with
major difficulties in real-time tracking of articulated tool
s. Most algo-
rithms are tailored for offline processing with pre-recorded
videos. In this
paper, we propose a real-time 3D tracking method for articul
ated tools
in robotic surgery. The proposed method is based on the CAD mo
del
of the tools as well as robot kinematics to generate online pa
rt-based
templates for efficient 2D matching and 3D pose estimation. A r
obust
verification approach is incorporated to reject outliers in
2D detections,
which is then followed by fusing inliers with robot kinemati
c readings
for 3D pose estimation of the tool. The proposed method has be
en val-
idated with phantom data, as well as
ex vivo
and
in vivo
experiments.
The results derived clearly demonstrate the performance ad
vantage of
the proposed method when compared to the state-of-the-art.