eprintid: 10119196 rev_number: 18 eprint_status: archive userid: 608 dir: disk0/10/11/91/96 datestamp: 2021-01-22 16:17:22 lastmod: 2022-02-16 18:16:34 status_changed: 2021-01-22 16:17:22 type: article metadata_visibility: show creators_name: Robu, M creators_name: Kadkhodamohammadi, A creators_name: Luengo, I creators_name: Stoyanov, D title: Towards real-time multiple surgical tool tracking ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 keywords: Multiple tool tracking, Surgical data science, Computer-Assisted Interventions note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Surgical tool tracking is an essential building block for computer-assisted interventions (CAI) and applications like video summarisation, workflow analysis and surgical navigation. Vision-based instrument tracking in laparoscopic surgical data faces significant challenges such as fast instrument motion, multiple simultaneous instruments and re-initialisation due to out-of-view conditions or instrument occlusions. In this paper, we propose a real-time multiple object tracking framework for whole laparoscopic tools, which extends an existing single object tracker. We introduce a geometric object descriptor, which helps with overlapping bounding box disambiguation, fast motion and optimal assignment between existing trajectories and new hypotheses. We achieve 99.51% and 75.64% average accuracy on ex-vivo robotic data and in-vivo laparoscopic sequences respectively from the Endovis’15 Instrument Tracking Dataset. The proposed geometric descriptor increased the performance on laparoscopic data by 32%, significantly reducing identity switches, false negatives and false positives. Overall, the proposed pipeline can successfully recover trajectories over long-sequences and it runs in real-time at approximately 25–29 fps. date: 2021 date_type: published official_url: https://doi.org/10.1080/21681163.2020.1835553 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1838339 doi: 10.1080/21681163.2020.1835553 lyricists_name: Stoyanov, Danail lyricists_id: DSTOY26 actors_name: Stoyanov, Danail actors_id: DSTOY26 actors_role: owner full_text_status: public publication: Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization volume: 9 number: 3 pagerange: 279-285 citation: Robu, M; Kadkhodamohammadi, A; Luengo, I; Stoyanov, D; (2021) Towards real-time multiple surgical tool tracking. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization , 9 (3) pp. 279-285. 10.1080/21681163.2020.1835553 <https://doi.org/10.1080/21681163.2020.1835553>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10119196/1/2020CMBBE_Robu.pdf