Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

ignality - Artificial intelligence for video

Reference number
Coordinator Signality AB
Funding from Vinnova SEK 300 000
Project duration March 2017 - September 2017
Status Completed
Venture Innovative Startups

Purpose and goal

We went into this project with the aim of providing intelligence to video and video cameras in sports. Now that we look back on the project we have come a long way. Our player tracking and ball tracking algorithm is state-of-the-art, with a precision of over 95% and we can track all players in real time. That we came so far with the platform is a potential for the second part; To be able to create cool highlights without a lot of work. It has resulted in the GoalFX app; The user selects a video, then an effect and then which (a) player the effect should be on.

Expected results and effects

The work of GoalFX and the platform has generated a lot of interested potential customers who see great potential to exploit our media, broadcasting and betting technology, but professional teams and leagues have also opened their eyes to Signality. We believe our Our real-time focused solution has great potential in the market. The port market has huge potential and in the largest team sports it is estimated that there are about one billion active practitioners. The market for sports analytics is estimated to reach 42 billion SEK in 2021.

Planned approach and implementation

436/5000 Layout and implementation have been divided into a number of different steps: 1. Examine which basic algorithms to use as a base. 2. Build web tools to annotate videos and thus create a foundation for the neural networks to identify players and balls. 3. Build infrastructure for development in the cloud as it is very process-demanding with AI / Deep Learning. 4. Design and development of iOS for GoalFX.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 28 January 2019

Reference number 2016-05520

Page statistics