Case
Arinti - DAIQUIRI: Data & Artificial Intelligence for Quantified Reporting In sport
DAIQUIRI
During sports events, athletes use wearables and sensors to track their performances. Currently, this data is used mainly for coaching, yet it might be useful for covering the events as well.
As such, new Artificial intelligence (AI) applications in professional sports based on sensors, wearables and video data might enrich live sports reporting. However, a platform capable of turning insightful sports data into stories for live commenters, content editors or viewers does not yet exist. The missing gap here is the adequate translation of the sensor data into useful narrative elements tailored to be used and integrated in real-time dynamic visualizations and storytelling for sports events.
The DAIQUIRI project will develop AI algorithms that address current challenges associated with data overload, sensor-video matching, dynamic captioning and multi-modal stories. The outcome will be a sensor data platform and dashboard that supports media professionals in their live sports coverage and the audiences’ viewing experiences.
Bridging the gap
There is a gap between traditional reporting and the translation of sports sensor data into interesting stories in real time – including the visualization of these data. During the DAIQUIRI project we are developing a scalable data workflow to support broadcasters in augmenting live sports reporting using Internet of Things (IoT) data generated by athletes and their equipment. The platform will enable content creators to bring professional stories about the athletes, team performance and in-competition circumstances to their audiences.
Project goals
With the research consortium, we aim to achieve 4 key project outcomes:
- Optimizing sensor connection, data linking and data quality to reduce data stream sizes by 30%
- Enabling insight-driven data capturing and real-time dynamic visualization, for personalized user experiences
- Develop AI algorithms that serve to generate different types of story snippets
- Unlock different storytelling techniques that complement traditional reporting based on new sensor data
Proven value
The scalable data workflow developed by the consortium will be showcased via applications in professional cyclocross and elite hockey. The sensor data and insights gathered by the platform will be used to create templates for real-time visualization and will then be fed into a content creation dashboard. Media professionals can then use this dashboard to rapidly and dynamically add data-driven insights to sports stories.
Hyperion
Both Arinti (cross-functional team of AI experts) and 23:Seconds (Javascript competence center) are a part of the DAIQUIRI research consortium.
DAIQUIRI is an imec.icon research project funded by imec and Agentschap Innoveren & Ondernemen.
It started on 01.10.2019 and is set to run until 30.09.2021.
Do you want to learn more about DAIQUIRI?
