{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/simultaneous-recognition-and-pose-estimation","title":"Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery","arxiv_id":"1710.06668","date":"2017-10-18","proceeding":null,"authors":["Thomas Kurmann","Pablo Marquez Neila","Xiaofei Du","Pascal Fua","Danail Stoyanov","Sebastian Wolf","Raphael Sznitman"],"abstract":"Detection of surgical instruments plays a key role in ensuring patient safety\nin minimally invasive surgery. In this paper, we present a novel method for 2D\nvision-based recognition and pose estimation of surgical instruments that\ngeneralizes to different surgical applications. At its core, we propose a novel\nscene model in order to simultaneously recognize multiple instruments as well\nas their parts. We use a Convolutional Neural Network architecture to embody\nour model and show that the cross-entropy loss is well suited to optimize its\nparameters which can be trained in an end-to-end fashion. An additional\nadvantage of our approach is that instrument detection at test time is achieved\nwhile avoiding the need for scale-dependent sliding window evaluation. This\nallows our approach to be relatively parameter free at test time and shows good\nperformance for both instrument detection and tracking. We show that our\napproach surpasses state-of-the-art results on in-vivo retinal microsurgery\nimage data, as well as ex-vivo laparoscopic sequences.","url_abs":"http://arxiv.org/abs/1710.06668v1","url_pdf":"http://arxiv.org/pdf/1710.06668v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"simultaneous-recognition-and-pose-estimation","repo_url":"https://github.com/otl-artorg/instrument-pose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}