Skyrocket your IELTS band score by 1-2 points in under a month with our premium plan!
↔
50 minutes and 25 seconds into the 1986
World cup match between Argentina and England,
Diego Maradona did something infamous.
“And Maradona has scored”
This moment goes down in history because because
of what the commentators could clearly see:
“ That is why England is so furious, Maradona
has punched it in with his left hand”
But in 1986, referees didn’t
have access to instant replays.
They had to make judgment calls from the field,
based on their limited
perspective on what happened.
And their subjective view on
it was that this goal was good.
This would never happen today, as technology
has empowered referees to view moments
again and again from multiple different
angles before making a final decision.
And this year’s world cup features a
technology that takes that a step further:
Judging when someone is offside — using AI.
Alright, so, the simplest way of explaining
offsides is that the offensive player has
to have two defensive players between them
and the goal, or be behind where the ball is.
Most of the time it's the
goalkeeper plus one defender.
For the most part, if any offensive
players are behind this second to
last defender while the ball
is in play, they’re offside.
That’s Jeremiah Oshan by the way.
Soccer editor of SB Nation.
Offside should be an objective call — either
you’re in front of this line, or behind it.
What makes it tricky is that we’re often
judging with subjective perspectives,
and it can be hard to tell when a
player is teetering over the line.
As this tweet by Dale Johnson of ESPN shows, the
angle at which you see something really matters.
These two images from the March 20th game
between Liverpool and Nottingham Forest
show the same moment in time from
two slightly different perspectives
In the image on the left #20
looks like he's in front of #3,
but on the right, it looks like
their positions are inverted.
If audience members only see an angle they feel
is uncompelling, it can leave them
unsure that the right call was made.
Like in this October 7th game
between England and the US.
“Maybe they’re looking at
an offside call potentially,
but it looks like Sophia Smith is onside”
This call shocked even the commentators.
“No goal?!?’
“Right there…is where they’re
saying…Sophia was offside already”
This goal would’ve tied the match at 2-2,
but because it was revoked, England won 2-1.
It was revoked, in part, because of VAR. Video
Assisted Referees were introduced in 2018,
with the intention of making calls
like this a little more objective.
These refs are in a room, away from the match,
but have the advantage of seeing
the event from 33 camera angles.
If they see something they think a
referee didn’t or couldn’t have seen,
they can suggest that the footage
be reviewed on the field monitor.
This enhances the accuracy and objectivity
of calls, but it still relies on perspective.
For the 2022 World cup, FIFA is introducing
semi-automated AI offside technology.
A sensor in the ball will relay its
position on the field 500 times a second
And 12 motion cameras mounted underneath the roof
of stadiums will use machine learning
to triangulate players body positions
This data can be used to create a 3D visualization
of a play that can be viewed from any angle,
Like in this early test during a September match.
The virtual camera is able to fly around, giving
an almost godlike perspective of the scenario.
There are no viewing angle limitations,
no frame rate delays — it’s a near 1 to
1 recreation of the event — seemingly
indisputable evidence for referees and
audience members that this player’s
knee was offside by this much.
Subjectivity isn’t being totally removed from
the equation though — the technology
being only semi-automated means that
human referees will still make the final calls,
after taking what the AI shows under consideration.
And that can be critical because while
this tech can judge space flawlessly,
it can’t see everything.
Like a player's intentions.
There was an MLS game between LAFC and
Austin FC where a foul potentially occurred.
The referee decided not give the penalty
for subjective reasons, which was, you know,
his touch was taking him away from
the ball, which implied that maybe
he wasn't really fouled as much as the
replay made it kind of look like he was.
I thought that was actually a really good use
of VAR, where he clearly was shown what happened
and he was allowed to make a decision about
whether or not he thought it was a foul or not.
Semi automated AI offside tech is meant to make
referees less reliant on subjective
perspective. But it’s just a tool.
How it’ll change gameplay depends
on how it gets used and ultimately,
how it gets reconciled with what
a human being sees on the field.
Offside is a complicated rule, and this video
only scratches the surface on it - but the
new semi automated AI offside system
is already at work in the world cup.
According to ESPN, in an early match between Qatar
and Ecuador, the system made a correct offside
call, and the 3D representation gave fans clarity
over a play that was somewhat hard to see — though
there also seemed to be some dissatisfaction
over how long it took to make that decision.
In a game between Argentina and Saudi Arabia,
though, the call was made much faster.
Ultimately, while this tech can give
human referees information more quickly,
their decisions will always take some time.
Please play the YouTube video first