Accelerating Performance with the Artificial Intelligence of Things
Soccer Player Selection Goes High-Tech with
AI
To accurately compile 3D images, BallJames
must distinguish between players, referees
and the ball. Using event stream processing
enables real-time image recognition and
analysis using deep learning models.
Football. Soccer. Whatever you call it, the
world’s most popular sport is being
transformed by a Dutch sports analytics
company bringing AI to the game. SciSports
uses streaming data and applies machine
learning, deep learning and AI to capture and
analyze this data for a variety of uses, from
player recruitment to virtual reality for fans.
When Is a Smart Device an AI Device?
Many smart devices are not AI-enabled
devices. For instance, a device that can be
controlled from an app or learn user
preferences is smart, but that’s not AI.
Traditional football data companies only
generate data on players who have the ball,
leaving everything else undocumented. This
leads to an incomplete picture of player
quality. Seeing an opportunity to capture the
immense amount of data happening away
from the ball, SciSports developed a camera
system called BallJames. 9
For a smart, connected thing to be a thing in
the AI-driven IoT, it needs to be able to make
a decision or perform a task without human
intervention. For example:
BallJames is a real-time tracking technology
that automatically generates three-
dimensional digital images and data from
video. Fourteen cameras placed around the
stadium record every movement on the
field. BallJames then generates data such as
the precision, direction and speed of the
passing, sprinting strength and jumping
strength. The result is a much more
comprehensive view of players.
A residential heating system that
learns temperature preference is not
an AIoT system unless it does
something – it adjusts the
temperature on your behalf.
An autonomous vehicle is an AI
system – it drives for you. When it is
connected to other cars or the
internet, it is a “thing” in the
artificially intelligent IoT – the AIoT.
S UCCESS WITH AI O T: 4 E SSENTIAL
S TEPS
Machine learning algorithms calculate the
quality, talent and value of more than
200,000 players in more than 1,500 matches
a week in 210 leagues. This analysis helps
clubs find talent, look for players that fit a
certain profile and analyze their opponents.
Looking beyond the physical infrastructure
of the intelligent IoT – the sensors, cameras,
network infrastructure and computers –
there are 4 essential steps that underpin a
successful deployment:
9
McCaskill, Steve. Forbes https://www.forbes.com/sites/stevemccaskill/2019/01/28/this-analytics-firm-wants-to-make-soccer-
transfers-more-like-video-games/#5fc543e7777a
IIC Journal of Innovation
- 42 -