University of Twente Student Theses


A sensor fusion technique for head motion controlled endoscope camera system

Panambur Venkatraman, V. (2019) A sensor fusion technique for head motion controlled endoscope camera system.

[img] PDF
Abstract:Video assisted thoracic surgery (VATS) is a type of minimally invasive surgery (MIS) in which the movement of the endoscope camera is done by assistant of an surgeon. A head motion controlled endoscope system was developed to enable the surgeon to directly control the endoscope using his/her head motion. The image output obtained from the endoscope was displayed on the screen. A compensation of the image rotation is done to remove the rotation component in the motion of the output image. This is done to keep the directionality in the image same as the head movement of the user. The compensation was done using the angle of rotation of the servo encoder measurement at the image plane and the angle of rotation obtained from optical flow based estimation. However, the image rotation compensation of the image output was not accurate because the output obtained from optical flow based estimation was suffering from drift and the output obtained from the servo encoder measurement was not accurate in finer motions. During this master’s assignment, a sensor fusion technique for obtaining a better image rotation compensation and compensating for non-linearities in the actuation of the head motion controlled endoscope camera system has been developed and evaluated. The rotation obtained from the servo encodermeasurement and the rotation obtained from the optical flow based estimation on the image output is fused together. Complementary filter and Extended kalman filter (EKF) were the two sensor fusion algorithms used. The complete software implementation was done in ROS Kinetic. Human trialswere conducted to evaluate the performance of the head motion controlled endoscope camera system after compensating for image rotation. The accuracy test suggested that EKF was comparitively better sensor fusion algorithm and the test for compensating hysteresis behavior suggested that Complementary filter was relatively better sensor fusion algorithm. From the response of human trials for overall performance of the system, it was observed that the complementary filter was preferred over EKF and servo encoder measurements. These results obtained from this study prove that sensor fusion algorithms can be used for improving the performance of the head motion controlled endoscope camera system.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:52 mechanical engineering, 53 electrotechnology, 54 computer science
Programme:Mechatronics MSc (60027)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page