An application driven comparison of several feature extraction algorithms in bronchoscope tracking during navigated bronchoscopy

Authors:
Xióngbiao Luó;Marco Feuerstein;Tobias Reichl;Takayuki Kitasaka;Kensaku Mori
Affiliations:
Graduate School of Information Science, Nagoya University, Japan;Graduate School of Information Science, Nagoya University, Japan and Computer Aided Medical Procedures, Technische Universität München, Germany;Computer Aided Medical Procedures, Technische Universität München, Germany;Faculty of Information Science, Aichi Institute of Technology, Japan;Information and Communications Headquarters, Nagoya University, Japan and Graduate School of Information Science, Nagoya University, Japan
Venue:
MIAR'10 Proceedings of the 5th international conference on Medical imaging and augmented reality
Year:
2010

Citing 4
Cited 1

Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Speeded-Up Robust Features (SURF)

Computer Vision and Image Understanding

Real-Time methods for long-term tissue feature tracking in endoscopic scenes

IPCAI'12 Proceedings of the Third international conference on Information Processing in Computer-Assisted Interventions

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper compares Kanade-Lucas-Tomasi (KLT), speeded up robust feature (SURF), and scale invariant feature transformation (SIFT) features applied to bronchoscope tracking. In our study, we first use KLT, SURF, or SIFT features and epipolar constraints to obtaininterframe translation (up to scale) and orientation displacements and Kalman filtering to recover an estimate for the magnitude of the motion (scale factor determination), and then multiply inter-frame motion parameters onto the previous pose of the bronchoscope camera to achieve the predicted pose, which is used to initialize intensity-based image registration to refine the current pose of the bronchoscope camera. We evaluate the KLT-, SURF-, and SIFT-based bronchoscope camera motion tracking methods on patient datasets. According to experimental results, we may conclude that SIFT features are more robust than KLT and SURF features at predicting the bronchoscope motion, and all methods for predicting the bronchoscope camera motion show a significant performance boost compared to sole intensity-based image registration without an additional position sensor.