Algorithm Allows a Computer to Create a Vacation Highlight Video

By Tara La Bouff | March 10, 2016 • Atlanta, GA

Georgia Tech students created a computerized system that scanned 26 hours of video, selected the best clips and produced this 38-second highlight reel. The process took three hours.

Researchers at the Georgia Institute of Technology unveiled a novel video-editing solution this week that automatically sorts and edits untouched footage into the most picturesque highlights for a vacation reel that could fill anyone with envy.

The new approach is an algorithm – developed by students Daniel Castro and Vinay Bettadapura under the guidance of Professor Irfan Essa – that analyzes video for images with ideal artistic properties. It first considers geolocation, then composition, symmetry and color vibrancy to determine what is important or picturesque. Video frames with the highest scores are processed into a highlight reel. See the finished product here.

Castro and Bettadapura conceived the approach after the latter returned from a two-week vacation, driving coast-to-coast across the southern United States. He ended the trip with 26.5 hours of footage from a wearable, head-mounted camera. He had no idea what do with it.

“The data was essentially useless because there was just too much of it,” said Bettadapura, who completed his Ph.D. in the fall and now is a Google software engineer. “We liked the idea of being able to automatically generate photo albums from your vacation, algorithmically.”

The algorithm turned 26 hours of video into a 38-second highlight reel in three hours. Because Bettadapura had worn a head-mounted Contour Action Camera that captured GPS data, the algorithm could filter by geographical location. That reduced the footage to 16 hours. Shot boundary detection further reduced it into 1,724 video shots or about 10.2 hours of video. It then processed for artistic quality and provided an output of the most picturesque content. Processing time is variable and depends on the number of computers used.

The algorithm can be adapted to user preferences.

“We can tweak the weights in our algorithm based on the user's aesthetic preferences,” Bettadapura said. “By incorporating facial recognition, we can further adapt the system to generate highlights that include people the user cares about.”

Castro and Bettadapura presented their findings at WACV 2016: IEEE’s Winter Conference on the Applications of Computer Vision, March 7 in Lake Placid, N.Y. The pair will continue to work together testing the algorithm with multiple participants to help generalize the approach, incorporate facial recognition, and develop data visualization techniques that make it easy to browse and search specific moments. The implications of future, successful tests could echo far beyond their initial work at Georgia Tech.

“This research brings together multiple modalities to more efficiently understand large amounts of data,” said Castro, who is completing his Ph.D. in computer science and also working as an intern at Google. “We are trying to optimize how easy it is to understand all of the data we have in an efficient manner because otherwise it would be impossible to do so.”

The Next Frontiers in Space

A new report, written by The Planetary Society, says the clock is ticking for exploration on Mars. Quickly. As the group notes, NASA only has one mission in development for the Red Planet — the Mars 2020 Rover. More is needed, according to the Society, particularly an updated orbiter and a rover that can land and retrieve samples dug up by the 2020 robot. James Wray in the School of Earth and Atmospheric Sciences is a science team member on most of NASA and the European Space Agency’s missions currently active on Mars.

I’m excited and re-energized by our President’s support of planetary exploration, from his inaugural address to his proposal of an all-time record(!) budget for NASA’s Planetary Science Division. The proposed funding will enable the long-overdue launch of a robust program to explore ocean worlds in the outer solar system, beginning with Jupiter’s most fascinating moon, Europa. For far too long, NASA has obeyed Arthur C. Clarke’s fictional admonishment on Europa in his 2010: Odyssey Two: “Attempt no landings there.” And yet, we must! And, someday soon, we will.

NASA’s budding ocean worlds program can benefit from many lessons — mostly positive, and perhaps a few negative — from its extremely productive Mars Exploration Program. I can directly attest to the synergies enabled by a well-integrated series of orbital and surface missions. Maintaining this degree of complementarity requires careful planning, and (as The Planetary Society notes) the time is nigh for action to ensure that our expanded exploration of the outer solar system does not leave our samples — and our science — stranded at Mars. We do not want NASA’s next (sample-caching) rover to be nicknamed “Watney.”

Two years ago, I coauthored a NASA-solicited report on the objectives that a new Mars orbiter could address in the early 2020s. Such a robotic mission not only could follow up on new evidence for modern liquid flows on Mars, but also represents one way to fulfill the scientific community’s consensus top priority for Mars exploration in this decade: returning carefully selected samples from the surface of Mars. But there’s another way to achieve this. As Neil Armstrong and Buzz Aldrin did for the moon, human astronauts could return the first samples from Mars, whether via their own geological survey of the planet or by retrieving samples robotically cached prior to their arrival. And therein lies perhaps the biggest question for NASA’s near future: how soon will astronauts be visiting Mars?

To answer this question, I am eagerly awaiting the President’s appointment of a new NASA Administrator. The agency has embarked on a multi-decade journey to Mars, requiring still much new technology development. But the President has argued for a more accelerated timeline, and if Apollo is any guide, then the proper funding and focus can make anything possible. New leadership at NASA should be empowered to balance these visions and pursue a synergistic robotic-and-human program of exploration, taking full advantage of the unprecedented international interest in Mars. Half a dozen different government agencies and at least one private company are planning missions there in the next few years. NASA has provided an undisputed head start, representing the only nation thus far to safely land on and return science from the Red Planet (seven times!). Ad astra per Mars!

Georgia Institute of Technology

Search form

News Center