Although the days of endless drawers of VCR tapes are over, home videos are still alive and well. With cameras fitted to our mobiles and tablets and more affordable camera technology, everyone’s become an amateur videographer. But often, we’ll shoot five minutes of video for an interesting moment which could be perfectly captured in one. There is where Livelight comes in.
Livelight is a machine learning application which cuts out the dull bits of videos by detecting and then removing erroneous action. It was developed by Carnegie Mellon’s Professor of Machine Learning Eric P. Xing and Bin Zhao, a Ph.D. student in the Machine Learning Department. To see the results, watch the video above.
According to the Livelight website, the platform works like so: “Without human supervision, LiveLight automatically scans through the video stream, removing repetitive and uninteresting contents. The result is a compilation of the most salient and informative portions of the video”. The compilation is created after one single pass through the video.
What you’re left with is a video with all of the dull, repetitive action taken out. Livelight can run on a standard laptop, but it also fast and powerful enough to summarise an hour’s worth of footage in 1-2 hours.
Interested in more content like this? Sign up to our newsletter, and you wont miss a thing!