Open positions

Jump to: navigation, search

Open Internship Positions within Project CAMMA

We are looking for motivated and talented students with knowledge in computer vision, machine learning and/or augmented reality who can contribute to the development of our computer vision system for the operating room.

Please feel free to contact Nicolas Padoy if you are interested to do your master's thesis or an internship with us (funding of ~500Euros/month will be provided during 4 to 6 months). The successful candidates will be part of a dynamic and international research group hosted within the IRCAD institute at the University Hospital of Strasbourg. They will thereby have direct contact with clinicians, industrial partners and also have access to an exceptional research environment. The CAMMA project is supported by the laboratory of excellence CAMI, the IdEx Unistra and the MixSurg Institute.


  • Deep Learning for Activity Recognition in Large Video Databases
  • Multi-view Human Body Tracking for the Operating Room using RGBD Cameras

More information about CAMMA


Open Postdoc/Research Engineer Position in Computer Vision/Deep Learning within Project CAMMA

We are looking for a research engineer in Computer Vision/deep Learning to join the development of our clinical prototypes. The project involves the perception of the Operating Room through a set of RGB-D cameras mounted on the ceiling as well as the recognition of surgical activities using both RGB-D and endoscopic videos. More information is available here.

Ph.D. positions in Surgical Robotics -- autonomous intraluminal surgery

The ATLAS project is a Marie Curie ITN-EJD (Innovative Training Network – European Joint Doctorate). The project is coordinated by KU Leuven, with partners in France (ICube laborataory), Italy, Netherlands, and Spain. Within this scheme, 15 Ph.D. positions are funded. We are looking for candidates in the following areas :

  • lumen reconstruction and lumen modelling,
  • sensor technology for intraluminal perception,
  • actuation technology for continuum robots,
  • distributed control and decision making for autonomous continuum robots.

Interested candidates will find detailed informations on the project website :

Please note that specific conditions apply for candidates, see the following webpage for details :

The first round of applications will close on January 15, 2019.

Master internship in Computer vision for medical robotics

  • Title: Detection of instruments motion in flexible endoscopy using computer vision
  • Training period: 5-6 monthes, between January and August 2019
  • Supervisor: F. Nageotte ( and B. Rosa
  • Keywords: motion detection, features tracking, surgical endoscopy
  • Context:

In the STRAS project, we are developing robotic tools for assisting surgeons during complex endoscopy procedures in the digestive tract (see wep page). To improve the control of such instruments, one of the problems to be solved is the compensation of backlash due to imperfections of motion transmission along the instruments shaft. For this purpose, we propose to use the images of the instruments (see figure) provided by the endoscopic camera in order to detect instruments motions.

The challenges for reaching this goal are that

    • tissues in the background are moving due to physiological motion (e.g., breathing),
    • direct lighting from the embedded light source creates many specularities and
    • the visual appearance of the instruments is not always known beforehand

Picture instruments.jpg

  • Work of the intern:

The objective of the internship will be to develop computer vision methods to detect when the instruments are moving. These methods will be coupled with robotic motions to update the backlash mode in real-time.

The work will therefore consist in: Developing and implementing algorithms to detect or track flexible instruments in colonoscopy sequences Proposing methods to detect the presence / absence of motions of these instruments Adapting and improving the algorithms to be robust to the environment motions The use of machine learning techniques is a possibility which may be explored.

The algorithms will be tested on a laboratory setup including the STRAS robot as well as on colonoscopy videos acquired in vivo. The work will be carried out on the robotic platform of the AVR team of the ICube laboratory, located at the hospital in the center of Strasbourg.

  • Profile of candidates : Master student (or student from engineering school) with major in computer vision or real-time image processing or robotics. Interest for / knowledge in medical robotics application can be a plus but is not a requirement. Proficiency in C/C++ or Python are required. Knowledge of OpenCV will be appreciated.
  • To apply: send a CV, cover letter, available grades at master level and programs of master courses to Florent Nageotte :

Master internship in modeling and planning for continuum robots

  • Training period: 5-6 months, between January and August 2019
  • Supervisor: B. Rosa ( and F. Nageotte
  • Keywords: continuum robots, cosserat rod theory, planning, medical robotics
  • Context:

Continuum robots and systems (e.g. endoscopes) are increasingly used in minimally invasive surgery for the unparalleled deported access and dexterity abilities they provide to the surgeon [1]. Mechanical models have been developed in order to compute the shape of such robots given kinematic inputs, using Cosserat Rod theory or minimum energy formulations. Recent studies have shown that those models allow computing compliance matrices explicitely, without resorting to finite difference methods [2,3]. This internship will investigate the properties and use of compliance matrices for safe planning of robot movement inside delicate anatomy.

The work will mainly first consist in analyzing the properties of the compliance matrices and identifying possible solutions to simplify its use and computation. Depending on the strengths of the candidate, several tracks may be considered :

    • Development of a numerically-efficient software package for continuum robot shape and compliance computation
    • Experimental validation on a concentric tube robot prototype
    • Development of a compliance-based planning algorithm for safe deployment of continuum robots in simulation
  • Profile of candidates: We're looking for talented master students with major in mechanical engineering, electrical engineering, or robotics. Strong analytical skills are essential, as well as a good command of a high-level programming language such as C++ or Python. Proficiency in English or in French is required. To apply, please send a CV and a cover letter, if possible with grades from the master semesters already finished, to, with the following key appearing in the email subject: “[MAPP_2019]”. Applications not respecting this formatting will not be considered.
  • References

[1] J. Burgner-Kahrs et al, 2015. Continuum robots for medical applications: A survey. IEEE Transactions on Robotics, 31(6), 1261-1280. [2] G. Smoljkic et al, 2014. Compliance computation for continuum types of robots. IEEE IROS 2014 Proceedings, pp 1066-1073. [3] DC. Rucker et al, 2011. "Computing Jacobians and compliance matrices for externally loaded continuum robots." IEEE ICRA 2011 Proceedings