RUN2GETHER – Mapping Runners using AI and Computer Vision

RUN2GETHER explores how collective running, one of the world’s most popular physical activities, can help build healthier citizens and more sustainable cities. Bringing together insights from biomechanics, from social and sport psychology, and from structural engineering stimulated by recent developments in machine learning, the project investigates how runners’ shared social identity can influence their movement synchrony, physical load, and interaction with the running infrastructures. Using cutting-edge computer vision, wearable sensors, and citizen science, RUN2GETHER will capture large-scale, real-world data during running events and group runs. These data will advance our understanding of how human collectives move together and how this can affect the performance and resilience of both individuals and of urban infrastructures such as bridges and running tracks. By engaging citizens as active contributors to science and running surface health monitoring, the project aims to transform running events into living laboratories for innovation in health, social cohesion, and sustainable city design.

There will be three PhD students working closely together in this research project. The PhD research associated with this position focuses on video and other data analysis recorded in real-life environments and the extraction of useful information such as pose, step frequency and synchrony. The recorded data will consist primarily of video, supplemented by on-body sensor data such as IMU measurements, which will be used to track individual runners with AI-based methods. This will be investigated through both controlled experiments and measurements conducted during real-world running events. In addition, an interactive interface will be developed in this project to efficiently collect subjective data from participants while running. 

• You have a Master's degree in Electrical Engineering or Computer Science, or a related field that aligns with the topic of the PhD research.
• You have good knowledge of and/or a strong interest in digital signal processing, machine learning, and computer vision. Knowledge of and interest in biomechanics and experimental data collection (e.g. camera footage from fixed setups and drones, and IMU measurements) are significant assets.
• You have a multidisciplinary mindset. You are creative, take initiative, and can work independently. You are also a team player and are looking forward to work closely with other researchers from different disciplines (engineering, sports psychology, movement and rehabilitation sciences).
• You have an excellent CV and are willing to write a personal funding application with the assistance of the supervisors.
• You have communication skills and a sense of responsibility.
• You are willing to take up some teaching tasks.

(Candidates who have not yet graduated but have a strong curriculum vitae by the application deadline are encouraged to apply.)

• Conducting scientific research in the field of machine learning and computer vision, measuring relevant parameters (step frequency, synchrony, etc.) from video for dynamic running load analysis.
• Conducting scientific research and implementing a user interface (chatbot, visual interface, etc.) to efficiently collect subjective data from runners while they are running. 
• Supervising master thesis projects in this research domain.
• Providing teaching assistance in courses depending on the candidate's profile.
• Providing administrative and technical support for activities within the EAVISE Research Group, and the faculty of Engineering Technology.
• The primary work location for this position is KU Leuven Campus De Nayer (Sint-Katelijne-Waver).