Students-researchers at the Georgia Institute of Technology created a computer software that can sort and edit vacation footage and create the ultimate, most picturesque highlights for a vacation reel.
The algorithm developed by two students, Daniel Castro and Vinay Bettadapura under the guidance of Professor Irfan Essa, is a new approach that can analyze video footage for images with almost ideal artistic properties. The way a perfect vacation video is created is by algorithm considering geolocation and composition, then symmetry and color vibrancy in order to decide what is most important and what is least important. Video frames with the highest scores are then processed into a picturesque highlight reel.
Its creators came up with the approach after Bettadapura came back from a vacation driving coast-to-coast across the southern United States. He had almost 27 hours of vacation footage, recorded with a wearable head-mounted camera.
“The data was essentially useless because there was just too much of it,” said Bettadapura. We liked the idea of being able to automatically generate photo albums from your vacation, algorithmically.”
The algorithm turned all of those hours of video into a 38-second highlight reel in just three hours. It was helpful that the wearable camera Bettadapura used captured GPS data, so that the algorithm could sort by geographical location. This reduced the footage to 16 hours. Shot boundary detection further reduced it to 10.2 hours of video. The algorithm then processed for artistic quality and produced an output of the most visually appealing content.
The new video-editing solution 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.”
Chanwoo's Weekly Tech 