If you've been convinced for years that John Madden has been replaced by an iPod filled with generic football commentary, you might be excited to learn that Switzerland's Ecole Polytechnique Federale de Lausanne has been working on an even more advanced version. This one is equipped with artificial intelligence so it can actually see what's happening on the field and provide commentary.
The school, which we will henceforth refer to as EPFL, came up with a complex algorithm that uses several different video feeds, constantly monitored, to follow a soccer, basketball, or football game in the same way a human commentator might. It divides the field into a grid, and tracks individual players based on uniform color, number, and other cues, predicting the likelihood of each player's entrance into each section of the grid.
The next step is to feed all that data into a program that can synthesize the data and create commentary from it. At the moment, the system is intended to be used by coaches to analyze teamwork from a wider view, but we'd personally love to see a robotic commentator. Maybe it can become friends with the robotic journalists of the future?
[via CNET]
140 years of Popular Science at your fingertips.
Each issue has been completely reimagined for your iPad. See our amazing new vision for magazines that goes far beyond the printed page
Stay up to date on the latest news of the future of science and technology from your iPhone or Android phone with full articles, images and offline viewing
Featuring every article from the magazine and website, plus links from around the Web. Also see our PopSci DIY feed
Engineers are racing to build robots that can take the place of rescuers. That story, plus a city that storms can't break and how having fun could lead to breakthrough science.
Also! A leech detective, the solution to America's train-crash problems, the world's fastest baby carriage, and more.


Online Content Director: Suzanne LaBarre | Email
Senior Editor: Paul Adams | Email
Associate Editor: Dan Nosowitz | Email
Contributing Writers:
Clay Dillow | Email
Rebecca Boyle | Email
Colin Lecher | Email
Emily Elert | Email
Intern:
Shaunacy Ferro | Email
Excellent work here. The reason why this is so applicable to spectator sports is because the playing field allows for a 360 degree horizontal view and 180 degree vertical view for video capture.
This means that the velocity and vector can be tracked for all players simultaneously using 3 dimensional analysis and time sequencing. The only way for the algorithm to momentarily get confused is likely during excessive celebration where more than 2 players come into contact and share the same velocity and vector.
This works excellent for lower contact sports like basketball and soccer, but for high contact sports like American football or rugby, it may not adapt well. For contact sports, it would be best to use RFID tracking in the shoes of the players and embedded receiver sensors along each yard line. Combined with the AI tracking, it should work very well.
Good article.
A lot of money will be saved when the players are replaced by robots.