Project

Back to overview

Advanced Learning for Tracking and Detection in Medical Workflow Analysis.

English title Advanced Learning for Tracking and Detection in Medical Workflow Analysis.
Applicant Fua Pascal
Number 131549
Funding scheme Project funding (Div. I-III)
Research institution Laboratoire de vision par ordinateur EPFL - IC - ISIM - CVLAB
Institution of higher education EPF Lausanne - EPFL
Main discipline Information Technology
Start/End 01.04.2012 - 30.06.2015
Approved amount 165'210.00
Show all

Lay Summary (English)

Lead
Lay summary
Research in computer vision has made a remarkable impact in many real world situations and had provided robust solutions. For example, face detection algorithms have been integrated in most mass-consumer digital cameras. This has been made possible by the combination of robust feature extraction with statistical learning algorithms.In this project we want to similarly advance object detection and tracking by considering a challenging and complex scenario. Surgical work-flow recovery is crucial for designing context-sensitive service systems in future operating rooms. Abstract knowledge about actions which are being performed is particularly valuable in the operating room (OR). This knowledge can be used for many applications such as optimizing the work-flow, recovering average work-flows for guiding and evaluating training surgeons, automatic report generation and ultimately for monitoring in a context aware operating room. Our objective is to analyze the events happening in the medical operating room, equipped with multiple cameras, in order to prepare the necessary input for fully automatic work-flow analysis.
Direct link to Lay Summary Last update: 21.02.2013

Responsible applicant and co-applicants

Employees

Publications

Publication
Multi-Commodity Network Flow for Tracking Multiple People
Fleuret François, BenShitrit Horesh, Fua Pascal (2014), Multi-Commodity Network Flow for Tracking Multiple People, in IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), 1614-1627.
Multiple Human Pose Estimation with Temporally Consistent 3D Pictorial Structures
BelagiannisV, Wang X, Schiele B, Fua P, Ilic S, Navab N (2014), Multiple Human Pose Estimation with Temporally Consistent 3D Pictorial Structures, in ECCV ChaLearn Looking at People Workshop, Zurich.
Re-Identification for Improved People Tracking
Fleuret François, BenShitrit Horesh, Fua Pascal (2014), Re-Identification for Improved People Tracking, in Cristani Marco, Loy Chen Change, Gong Shaogang , Shuicheng Yan (ed.), Springer, London, 309-330.
Tracking Interacting Objects Optimally Using Integer Programming
Wang X, Turetken E, Fleuret F, Fua P. (2014), Tracking Interacting Objects Optimally Using Integer Programming, in European Conference on Computer Vision, Zurich.

Collaboration

Group / person Country
Types of collaboration
T.U. Graz Austria (Europe)
- in-depth/constructive exchanges on approaches, methods or results
- Exchange of personnel
T.U. Munich Germany (Europe)
- Publication
- Research Infrastructure
- Exchange of personnel

Associated projects

Number Title Start Funding scheme
149866 Delineating Trees in Noisy 2D Images and 3D Image-Stacks 01.10.2013 Project funding (Div. I-III)
159248 Motion Models for Monocular People Tracking 01.09.2015 Project funding (Div. I-III)
147693 Tracking in the Wild 01.01.2014 Sinergia

Abstract

Research in computer vision has made a remarkable impact in many real world situations and had provided robust solutions. For example, face detection algorithms have been integrated in most mass-consumer digital cameras. This has been made possible by the combination of robust feature extraction with statistical learning algorithms.In this project we want to similarly advance object detection and tracking by considering a challenging and complex scenario. Surgical work-flow recovery is crucial for designing context-sensitive service systems in future operating rooms. Abstract knowledge about actions which are being performed is particularly valuable in the operating room (OR). This knowledge can be used for many applications such as optimizing the work-flow, recovering average work-flows for guiding and evaluating training surgeons, automatic report generation and ultimately for monitoring in a context aware operating room. Our objective is to analyze the events happening in the medical operating room, equipped with multiple cameras, in order to prepare the necessary input for fully automatic work-flow analysis.
-