Announcement

Finally, we have successfully merged all georeferenced videos, including video dataset collected during recent experiments (Oct., 29 - Nov., 5, 2012).

Introduction

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 experimental, touch-friendly 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.

main menu recording menu

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.

New Experimental Interface Google StreetView Integration

Below is a video that explains the ideas and concepts behind GeoVid. Alternatively, you can directly try 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