Tracking and Estimation of Surgical Instrument Position and Angle in Surgical Robot Using Vision System

A da Vinci robot endoscopic-camera gives surgeons a magnified 2D view of the operating area, but additional time is required to detect and estimate the location of the surgical-instrument during an operation. The main focus and novelty of this research is to develop a new virtual coloured marker-based tracking algorithm for estimating the posture and orientation of the instrument. Initially, the developed algorithm begins by determining the coloured area of the instrument as reference-contour. Followed by a new Virtual-Rotating Bounding Rectangle (V-RBR) created over the reference-contour by meeting the minimum area of contour criteria. Additionally, a new Virtual Dynamic Multi-line Crossbar and a Virtual Static Graph (VDMC-VSG) was constructed to trace the movement of V-RBR, which helps to estimate the pose and angle of the targeted instrument in 2D during observations. V-RBR is considered as virtual coloured marker, it avoids ambient illumination-related difficulties. The proposed approach performed excellently in Gazebo-simulation and the overall accuracy is 91.3 % obtained by comparing with Robot Operating System (ROS)-based Transform measuring system, which uses robot kinematics.