Share Email Print
cover

Proceedings Paper

Robust feature tracking for endoscopic pose estimation and structure recovery
Author(s): S. Speidel; S. Krappe; S. Röhl; S. Bodenstedt; B. Müller-Stich; R. Dillmann
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Minimally invasive surgery is a highly complex medical discipline with several difficulties for the surgeon. To alleviate these difficulties, augmented reality can be used for intraoperative assistance. For visualization, the endoscope pose must be known which can be acquired with a SLAM (Simultaneous Localization and Mapping) approach using the endoscopic images. In this paper we focus on feature tracking for SLAM in minimally invasive surgery. Robust feature tracking and minimization of false correspondences is crucial for localizing the endoscope. As sensory input we use a stereo endoscope and evaluate different feature types in a developed SLAM framework. The accuracy of the endoscope pose estimation is validated with synthetic and ex vivo data. Furthermore we test the approach with in vivo image sequences from da Vinci interventions.

Paper Details

Date Published: 8 March 2013
PDF: 7 pages
Proc. SPIE 8671, Medical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling, 867102 (8 March 2013); doi: 10.1117/12.2007278
Show Author Affiliations
S. Speidel, Karlsruher Institut für Technologie (Germany)
S. Krappe, Fraunhofer-Institut für Integrierte Schaltungen (IIS) (Germany)
S. Röhl, Karlsruher Institut für Technologie (Germany)
S. Bodenstedt, Karlsruher Institut für Technologie (Germany)
B. Müller-Stich, Heidelberg Univ. (Germany)
R. Dillmann, Karlsruher Institut für Technologie (Germany)


Published in SPIE Proceedings Vol. 8671:
Medical Imaging 2013: Image-Guided Procedures, Robotic Interventions, and Modeling
David R. Holmes III; Ziv R. Yaniv, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray