PhD (M/F) In situ biomechanical analysis and holistic 3D reconstruction (athlete-equipment-environment) for performance optimization in competitive sailing.
New
- FTC PhD student / Offer for thesis
- 36 mounth
- BAC+5
Offer at a glance
The Unit
Institut de recherche en informatique et systèmes aléatoires
Contract Type
FTC PhD student / Offer for thesis
Working hHours
Full Time
Workplace
35042 RENNES
Contract Duration
36 mounth
Date of Hire
01/10/2026
Remuneration
2300 € gross monthly
Apply Application Deadline : 19 May 2026 23:59
Job Description
Thesis Subject
In competitive sailing, particularly on foiling craft (Kitefoil, IQfoil windsurfing), performance relies on an unstable equilibrium. The athlete's posture directly determines the "righting moment" and the trim of the float, both crucial elements for maximizing aerodynamic loading and speed. Evaluating these postures in real-world conditions is a major challenge for optimizing equipment and informing Velocity Prediction Programs (VPP).
However, the maritime environment is hostile (water, spray, variable lighting, vast open spaces). Traditional biomechanical analysis methods (optoelectronic markers like Vicon or intrusive inertial sensors) are either ineffective or interfere with performance. This project, therefore, proposes to develop a markerless computer vision approach using onboard video or drone footage to analyze the athlete's kinematics in their natural environment.Technical Challenges
The primary challenge lies in the ability to extract precise kinematic data and a reliable Center of Mass from monocular video streams or a small number of mobile cameras, while ensuring the physical coherence of the scene. The research axes will address the following hurdles:
• Holistic 3D Reconstruction (Multimodal): Moving beyond single-human pose estimation to model the joint interaction between the athlete and their equipment (board, sail, harness) by leveraging the rigid geometric constraints of the equipment.
• Strict Anthropometric Coherence: Integrating strong biomechanical constraints (3D scans of athletes, real measurements) to go beyond the approximations of generic models (like SMPL) and obtain a precise mass distribution.
• Robustness to "In the Wild" Conditions: Adapting state-of-the-art models (YOLO, Sapiens, RTMPose) to severe occlusions (spray, rigging) and moving cameras, by exploiting recent neural networks (VisionTransformers such as Dust3r/Manst3r) to dynamically calibrate the space (visual SLAM).
• Biomechanical / Hydrodynamic Coupling: Integrating posture and Center of Mass data into physical equilibrium solvers to estimate aerodynamic forces and predict speed.
Your Work Environment
Today, IRISA is one of the largest French research laboratories (with over 850 people) in the field of computer science and information technology. Structured into seven scientific departments, IRISA is a laboratory of excellence whose scientific priorities include bioinformatics, system security, new software architectures, virtual reality, big data analysis, and artificial intelligence. Focused on the future of computer science and necessarily international in scope, IRISA is at the very heart of society's digital transition and innovation, serving cybersecurity, health, the environment and ecology, transport, robotics, energy, culture, and artificial intelligence.
Presentation of the CNRS as an employer: https://www.cnrs.fr/fr/le-cnrs
Presentation of IRISA as the host laboratory: https://www.irisa.fr/umr-6074
This position is located in a sector subject to the protection of scientific and technical potential (PPST) and, in accordance with regulations, requires that your arrival be authorized by the competent authority of the MESR (Ministry of Higher Education and Research).
Constraints and risks
Not applicable
Compensation and benefits
Compensation
2300 € gross monthly
Annual leave and RTT
44 jours
Remote Working practice and compensation
Pratique et indemnisation du TT
Transport
Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€
About the offer
| Offer reference | UMR6074-PIEHEL-004 |
|---|---|
| CN Section(s) / Research Area | Information sciences: processing, integrated hardware-software systems, robots, commands, images, content, interactions, signals and languages |
About the CNRS
The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.
Create your alert
Don't miss any opportunity to find the job that's right for you. Register for free and receive new vacancies directly in your mailbox.