Machine Learning Can Automatically Cut The Boring Parts Out Of Movies

Just about every device has a camera in it, so we’re shooting more and more video than we have ever before. If only all of it were worth watching.

The latest application of machine learning was developed by Eric P. Xing, professor of machine learning from Carnegie Mellon University, and Bin Zhao, a Ph.D. student in the Machine Learning Department. It’s called LiveLight, and it can help automate the reduction of videos to just their good parts.

To get a quick idea what it’s all about, watch the demo above.

LiveLight takes a long piece of source footage and “evaluates action in the video, looking for visual novelty and ignoring repetitive or eventless sequences, to create a summary that enables a viewer to get the gist of what happened.” Put another way, it watches your movie and edits out the boring stuff. This all happens with just one pass through said video — LiveLight never works backwards.

You’re left with something more like a highlight reel than the too-long original video pictured on the left above. LiveLight is robust enough to run on a standard laptop and is powerful enough to process an hour of video in one or two hours.


Donate Your Eyes

Smoothini: Bar Magician Flies Through Amazing Tricks – America’s Got Talent 2014


An ovitrap is a device which consists of a black cylinder with a piece of cardboard submerged into the water in the cup. Ovitraps mimic the preferred breeding site for container breeding mosquitoes, including Aedes albopictus and Aedes aegypti.

The Ovitrap was first described in 1966[1] and was initially designed for monitoring Aedes populations. Researchers found that if they provided artificial breeding sites, they could easily collect and study the eggs found in the container. Since the original ovitrap was invented, lethal ovitraps have been developed, which kill the larvae and/or the adult mosquitoes that enter.

Ovitraps used for monitoring can detect Aedes mosquito populations thus acting as an early warning signal to preempt any impending dengue outbreaks.[2] Analysis can be done on the ovitrap breeding data collected weekly to identify mosquito breeding hotspots and risk areas when there is a danger of high Aedes infestation. This analysis is used to plan vector surveillance and control operations.

The extensive use of the ovitrap in a community can be used in Aedes population control and effectively reduce the Aedes population in that area. It has been used in countries like Singapore, United States and Hong Kong since the 1970s.

Important Links: