Nvidia

Football scores computer vision, AI with Track160

Football scores computer vision, AI with Track160

Eyal Ben-Ari has just fired his first shot in a bid to bring pro-class analytics to amateur soccer players.

The CEO of Tel Aviv-based startup Track160 has seen his company’s AI-based sports analytics software tested and used in the major leagues. Now he is turning his attention to underserved fans in clubs and community teams who he says are “the biggest opportunity” among the world’s 250 million football players.

“Almost everyone in professional sports uses data analytics today. Now we’re trying to enable any team at any level to capture their own data and analytics, and the only way to to do so is to leverage AI,” he said.

A kick off below

In April, the company launched its Coach160 software in Australia, where it is receiving accolades from amateur football clubs in Victoria and Queensland. It uses computer vision to enable teams to automatically generate rich reports and annotated videos with a standard camera and cloud connection.

“The analysis and data provided by Track160 will prove to be a wonderful resource for our coaches and players,” said Vaughn Coveny, a retired professional soccer player who now works with several youth teams in the region.

Startup with an AI heritage

Miky Tamir, a serial sports tech entrepreneur, co-founded Track160 in 2017. The company’s investors include the Deutsche Fussball Liga, Germany’s national soccer league, which has provided annotated datasets of several of its seasons.

“It helped establish a baseline, and then we applied transfer learning and developed an ever-changing internal database,” said Tamir Anavi, CTO of Track160.

Using video from a single camera, the company’s software identifies and tracks players as 3D skeletons, then tags events and actions as they move.

“We use deep learning at every stage to understand where the camera is, where the field is, and where the players are on it,” Anavi said.

With this information, the software provides detailed analyzes and more. It builds a 3D model so players and coaches can see any part of the game from any vantage point, providing what Ben-Ari calls “a metaverse experience.”

Software certified by the pros

Coach160 software scored high for speed and accuracy in a benchmark for electronic tracking systems created by FIFA, the global federation of more than 200 professional football leagues. “We delivered the same performance as others who used six times as many cameras,” Anavi said.

A professional league uses the code to get real-time data on game days. It processes 4K video streams with four NVIDIA GPUs and libraries that speed up work.

When it comes to AI, Track160 relies on NVIDIA TensorRT to make his models lean so that they run fast.

“We couldn’t make any inference without it. The job went from impossible to smooth and it took our system from prototype to production,” said Anavi.

Track160 recently signed as a member of NVIDIA Metropolis, a program for intelligent video analysis companies. Ben Ari says he will leverage the program’s early access to technology and expertise to accelerate the growth of his business.

Look Beyond Oz

Australia was a natural first target given its penchant for new technology and its large number of amateur football players and clubs, said Ben-Ari, who is already planning a US launch.

In the long term, the company also plans to train models for other sports.

“We see a kind of viral effect where everyone will want to have this,” he said.

“As a dad, I want to know what’s going on when my daughter is playing, and even if they’re not pros, people want to know how they’re performing,” said Ben-Ari, who likes to look at his stats. triathlon.