Published in


What kind of video is good for vball.io

After monitoring vball.io customers during the first months, I noticed a lot of people attempt to process TV records (or at least professionally edited games from multiple cameras).

Unfortunately, such a source will not work because of the technology limits. The original approach uses background removal algorithms, but that makes sense only with an immobile camera.

Good static view
Moving camera

Another problem could be a video with a moving background (when the ball moves over human viewers — even if it seems they sit still, they actually are doing a lot of small movements). These movements make the background pretty vivid and then generate a lot of noise.

People on background

So to get the best results it is recommended to apply vball.io to raw videos from static cameras.



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Constantin Toporov

Working on artificial intelligence and computer vision applied to sports.