Pitch Studio 42

Videos to re-live a sports challenge personalised on each athlete
Thematic area: Projects, Tech
Financing: IFAB for PMI
Enabling Technology: Artificial Intelligence, Big Data Analytics, Geographic Information Systems (GIS), High Performance Computing, Image recognition, IoT

The Jubatus project focuses on developing an innovative solution to improve the experience of participants in endurance sports events, such as marathons and triathlons, which are growing in Italy. The problem identified is the lack of a way for athletes to relive and share their post-event experience. Market research has revealed that the most desired format is a vertical reel ready within 48 hours of the event. The solution proposed by Studio 42 is based on a 3-stage process

  • the first phase of filming built using videomakers with cameras for active athlete tracking, a fleet of drones with auto-tracking for aerial shots, and fixed cameras at key points along the course;
  • A second phase of recognition of the athlete and the discipline based on identifying and distinctive elements;
  • A final phase dedicated to the creation of the video content in a semi-automatic manner.

Studio 42 uses state-of-the-art solutions such as AI 2.0 for the entire process component dedicated to content analysis and creation (e.g. image quality improvement) with a pioneering approach aimed at exploring new application areas. The project aims to achieve an innovative and scalable tool, which will require high-performance computing resources.

Goals

The aim is to improve the existing self-editing solution by modelling the identification of objective factors and the generation of context-bound subjective factors with a good deal of ‘exploration’. Improving the solution requires training the algorithm on the basis of acquired skills and experience.

The initial challenge

After participating in a sports event, the participant would like to be able to see and share his or her experience. The event itself is considered the culmination of a journey in which the athlete invests time, energy and resources in long and tiring training sessions. Every athlete would like to remember, relive and share those moments. Photography is widely used, while video footage is relatively rare as it is much more difficult to immortalise each athlete with an individual video than a photo.

The solution

The system devised consists of two components: athlete recognition based on identification elements, and semi-automatic assembly of the reel with high industrialisation of the product. The accuracy in the recognition of the individual athlete stands at 99.4%, although the accuracy of the mounting does not yet reach the same standard.

Benefits

  • Reducing the timeframe for editing and creating more professional, emotional and quality videos for each individual.
  • Creating a video format that is suitable for sharing on social media platforms;
  • Exploration of a growing technology with generalisation to other businesses.

Partners

 

For further information, please contact: barbara.vecchi@ifabfoundation.org

Sustainable Development Goals

Share on:

You may also be interested in:

Stay updated on the latest IFAB events and projects.Subscribe to our monthly newsletter