The GeoVid project explores the concept of sensor-rich video tagging. Specifically, recorded videos are tagged with a continuous stream of extended geographic properties that relate to the camera scenes. This meta-data is then utilized for storing, indexing and searching large collections of community-generated videos. By considering video related meta-information, more relevant search results can be returned and advanced searches, such as directional and surround queries, can be executed. This web site demonstrates a more traditional georeferenced video search and a more experimental, HTML5-based video search portal (works best with Google Chrome) that utilize an estimation model of a camera's viewable scene for effective video search.

To acquire video with the relevant properties, we provide smartphone and tablet apps that automatically annotate captured videos with their respective field-of-views (FOV). The acquisition apps, available for Android on our site here and in the Google Play Store here, allow community-driven data contributions to this search portal. Tagged videos can directly be uploaded from the apps. The iPhone and iPad apps are available from the iTunes App Store here.

Below is a video that explains the ideas and concepts behind GeoVid. Alternatively, you can directly try the traditional georeferenced video search portal search or the more experimental, HTML5-based video search portal (works best with Google Chrome). Please note that the site contains a limited number of videos right now.

System Requirements: Because of the significant use of JavaScript FOV animations, the traditional video search page works best with the Chrome and Firefox browsers, while the experimental HTML5 page works best with Chrome.

Demo Video



People Involved
Roger Zimmermann
Seon Ho Kim
Sakire Arslan Ay
Beomjoo Seo
Jia Hao
Lingyan Zhang
Guanfeng Wang
Shunkai Fang
He Ma
Yifang Yin