SURGICAL TOOL DETECTION BY MODELLING LOCAL APPEARANCE AND GLOBAL SHAPE

====== Members ====== * [[members:pierre.jannin:index|Pierre Jannin]] - Leader * [[members:david.bouget:index|David Bouget]] - PhD student * [[members:laurent.riffaud:index|Laurent Riffaud]] - Medical expert ====== General purpose ====== Detecting tools in surgical videos is an important indregient for context-aware computer-assisted intervention systems. We propose a new two-stage pipeline for tool detection and pose estimation in 2d images, named ShapeDetector. Our approach is data-driven and overcomes strong assumptions made regarding the geometry, number, and position of tools in the image. Our method has been validated for the following three pose parameters: overall position, tip location, and orientaton; using a new surgical tool dataset: the NeuroSurgicalTools data-set made of 2476 monocular images from neurosurgical microscopes during in-vivo surgeries. [[https://ecm.univ-rennes1.fr/nuxeo/nxdoc/default/55cab40f-6564-4026-99b5-37ffb10cdfb3/view_documents|{{ :activities:theme1:representativeimage.png?400 }}]] [[https://ecm.univ-rennes1.fr/nuxeo/nxdoc/default/55cab40f-6564-4026-99b5-37ffb10cdfb3/view_documents|**IMAGES AND ANNOTATIONS**]] We provide separate train and test splits as long as corresponding annotations in the LabelMe format (one annotation file per image). [[http://dbouget.bitbucket.org/2015_tmi_surgical_tool_detection/|More info]] ====== Main Collaborators ====== * [[https://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-computing/|Rodrigo Benenson, Bernt Schiele, Max-Planck-Institut für Informatik, in Saarbrücken, Germany.]] * Funding by Carl Zeiss, Germany ====== Publications ======