With World Cup fever in full force right now, many budding players are hoping for the day when they could be under the global spotlight. Well, a little help from artificial technology (AI) may help take them a step closer.
Copenhagen-based startup Veo has developed a camera that can capture the action of the football field, helping coaches to better analyse and improve play. Placed in the middle of the touchline, the camera uses object-detection model to track movement of the football to follow the action.
Founder and CEO Henrik Teisbaek said Veo was built to offer professional video analytics capabilities widely. It is targeted at more than 100,000 amateur teams around the word.
Veo’s cool-looking, lime-green triangular device packs two 4K video cameras inside for use on a tripod. The cameras require their data to be transferred to Veo’s cloud service, which stitches footage together to produce panoramic videos that track the game action.
Started in 2016, Veo is now working with 20 soccer clubs in Copenhagen. The first generation cameras that it has operating on the soccer fields capture about 100 matches a month.
Coaches can use the processed videos to zoom in on the ball and players for post-game analysis. The system also allows coaches to place lines on the field and other marks to help analyse in the videos whether players are in formation with their practice drills.
Veo is currently developing its next-generation camera, which will launch later this year. Close to 100 clubs have already bought the 1,200 euro camera in pre-sales.
Behind the scenes, Veo’s convolutional neural network acts as a big brain for video processing. Using NVIDIA processors that process about 500 million pixels per second, the neural network has been trained on 1.5 million images consisting of about one million soccer balls and 500,000 players.
Veo’s heavily trained image model makes it possible to quickly find game highlights, such as a scored goal. But the company is continuing to train its model to offer more capabilities.