{"511511":{"#nid":"511511","#data":{"type":"news","title":"Algorithm Allows a Computer to Create a Vacation Highlight Video","body":[{"value":"\u003Cp\u003EResearchers 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.\u003C\/p\u003E\u003Cp\u003EThe new approach is an algorithm \u2013 developed by students Daniel Castro and Vinay Bettadapura under the guidance of Professor Irfan Essa \u2013 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. \u003Ca href=\u0022https:\/\/www.youtube.com\/watch?v=lIONi21y-mk\u0022\u003ESee the finished product here\u003C\/a\u003E.\u003C\/p\u003E\u003Cp\u003ECastro 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.\u003C\/p\u003E\u003Cp\u003E\u201cThe data was essentially useless because there was just too much of it,\u201d said Bettadapura, who completed his Ph.D. in the fall and now is a Google software engineer. \u201cWe liked the idea of being able to automatically generate photo albums from your vacation, algorithmically.\u201d\u003C\/p\u003E\u003Cp\u003EThe algorithm turned 26 hours of video into a 38-second highlight reel in three hours. \u0026nbsp;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.\u003C\/p\u003E\u003Cp\u003EThe algorithm can be adapted to user preferences.\u003C\/p\u003E\u003Cp\u003E\u201cWe can tweak the weights in our algorithm based on the user\u0027s aesthetic preferences,\u201d Bettadapura said. \u201cBy incorporating facial recognition, we can further adapt the system to generate highlights that include people the user cares about.\u201d\u003C\/p\u003E\u003Cp\u003ECastro and Bettadapura presented their findings at WACV 2016: IEEE\u2019s 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.\u003C\/p\u003E\u003Cp\u003E\u201cThis research brings together multiple modalities to more efficiently understand large amounts of data,\u201d said Castro, who is completing his Ph.D. in computer science and also working as an intern at Google. \u201cWe 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.\u201d\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EResearchers 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.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Algorithm allows computer to scan 26 hours of video in three hours to create a highlight reel."}],"uid":"27560","created_gmt":"2016-03-10 09:54:58","changed_gmt":"2016-10-08 03:21:01","author":"Jason Maderer","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2016-03-10T00:00:00-05:00","iso_date":"2016-03-10T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"511531":{"id":"511531","type":"image","title":"How the Process Works","body":null,"created":"1458923712","gmt_created":"2016-03-25 16:35:12","changed":"1475895273","gmt_changed":"2016-10-08 02:54:33","alt":"How the Process Works","file":{"fid":"204987","name":"flowchart_of_process.png","image_path":"\/sites\/default\/files\/images\/flowchart_of_process_0.png","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/flowchart_of_process_0.png","mime":"image\/png","size":626230,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/flowchart_of_process_0.png?itok=OSrRtB_z"}},"511451":{"id":"511451","type":"image","title":"Vinay Bettadapura","body":null,"created":"1458923712","gmt_created":"2016-03-25 16:35:12","changed":"1475895273","gmt_changed":"2016-10-08 02:54:33","alt":"Vinay Bettadapura","file":{"fid":"204968","name":"vinay-headshot.png","image_path":"\/sites\/default\/files\/images\/vinay-headshot_0.png","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/vinay-headshot_0.png","mime":"image\/png","size":106504,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/vinay-headshot_0.png?itok=_P8PFUVu"}}},"media_ids":["511531","511451"],"related_links":[{"url":"http:\/\/www.ic.gatech.edu\/","title":"School of Interactive Computing"}],"groups":[{"id":"1183","name":"Home"}],"categories":[],"keywords":[{"id":"3167","name":"algorithm"},{"id":"171815","name":"editing"},{"id":"15155","name":"Irfan Essa"},{"id":"171816","name":"Vacation video"}],"core_research_areas":[{"id":"39501","name":"People and Technology"},{"id":"39541","name":"Systems"}],"news_room_topics":[{"id":"71881","name":"Science and Technology"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003ETara LaBouff\u003Cbr \/\u003ECollege of Computing\u003Cbr \/\u003EMarketing Communications Manager\u003Cbr \/\u003E602-770-0264\u003C\/p\u003E","format":"limited_html"}],"email":["tlabouff@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}