Abstract: Real-Time Online Adaption for Robust Instrument Tracking and Pose Estimation

In [1], we propose a novel method for instrument tracking in Retinal Microsurgery (RM) which is apt to withstand the challenges of in-vivo RM visual sequences. The proposed approach is a robust closed-loop framework to track and localize the instrument parts in real-time, based on a dual-random forest (RF). First, a tracker employs the pixel intensities in a RF to infer the bounding box around the tool tip. In the second step, this region of interest is forwarded to another RF, which predicts the locations of the tool joints based on HOG features.

Authors and Affiliations

1. Computer Aided Medical Procedures, Technische Universität München, München, Deutschland

   Nicola Rieke, David Joseph Tan, Federico Tombari, Josué Page Vizcaíno & Nassir Navab

2. Carl Zeiss MEDITEC München, München, Deutschland

   Chiara Amat di San Filippo & Abouzar Eslami

Corresponding author

Correspondence to Nicola Rieke .

Editors and Affiliations

1. Deutsches Krebsforschungszentrum, Juniorgruppe Medizinische Bildverarbeitung, Heidelberg, Germany

   Klaus Hermann Maier-Hein, geb. Fritzsche

2. Uniklinik RWTH Aachen, Institut für Medizinische Informatik, Aachen, Germany

   Thomas Martin Deserno, geb. Lehmann

3. Universität zu Lübeck, Institut für Medizinische Informatik, Lübeck, Germany

   Heinz Handels

4. Charité – Universitätsmedizin Berlin, Institut für Medizinische Informatik, Berlin, Germany

   Thomas Tolxdorff

Reprints and permissions

© 2017 Springer-Verlag GmbH Deutschland

Policies and ethics