This experimental service allows the user to extract a set of representative keyframes from a video and
enhance key elements, i.e. detected faces and text regions.
To submit a video for analysis the user can either provide its URL or upload a local copy of it from his/her machine
(please notice that the maximum permitted video size is 2GB, and duration up to 30 minutes).
The supported on-line video sources include YouTube, Facebook, Twitter, Instagram, Vimeo, DailyMotion, LiveLeak and
Dropbox (beware though that not all videos from these platforms are accessible to our service, due to platform-specific
or user-defined restrictions about the use of each specific video; moreover, the provided URL should always point to a
single video, rather than a playlist of videos). The service can handle videos in mp4, webm, avi, mov, wmv, ogv, mpg,
flv, and mkv format.
The complete service runs at high speed (i.e., it is faster than real-time video processing, though
delays may be noticed if multiple video processing jobs are in the queue).
After submitting a video, the user can monitor the progress of the analysis. The submitted video is temporarily cached
in our server to enable its processing, and it is automatically deleted from the server right after the completion of
the analysis. Subsequently, the user is shown the collection of extracted keyframes.
Optionally, if the user provided an e-mail address s/he may close the web application and be notified by e-mail when
the analysis results are ready. This e-mail contains a unique link to the analysis results, that is active only for 48
hours; after this time period, the link, the analysis results and the e-mail address (if provided) are automatically
deleted from our server.
All video rights remain with the uploader, who is assumed to have the right to submit the video to this service for
analysis.
Any feedback you may have on the web service is most welcome; please send it to
kapost@iti.gr and
bmezaris@iti.gr