Video conferencing is part of a $5 Billion dollar real-time collaboration market that includes audio, video and web conferencing products and services.
Video conferencing usually involves three channels of information: video, audio and data. Data collaboration, adopted by virtually all video conferencing manufacturers, allows for a presenter to send data to all participants via a dedicated channel (usually using H.239). Data is usually a desktop view or documents such as presentations encoded as a video stream.
With the video conferencing market moving out of the meeting rooms and into laptops, netbooks, mobile devices, etc., data collaboration becomes a big challenge. The data, usually sent in high, native PC resolution (such as XGA), has to be adapted to multiple devices, each with its own processing and screen capabilities.
This challenge focuses on adapting, in real-time, the data collaboration channel to different receiving devices, in a way that would be regarded as optimal perceptually by users.
Input/Output
Input for this challenge is a capture of a document, a PowerPoint presentation for example, in XGA resolution (either image or video).
Output for this challenge should be a set of “adapted” captures (images or videos), with the same document in different (smaller) resolutions – VGA and QVGA. The adapted captures would ideally be regarded by users as perceptually optimal.
Dataset
A dataset with captures of data collaboration channels will be made available soon, here on the Multimedia Grand Challenge web site.
Metrics/Evaluation
The following criteria could be used, as well as other evaluation metrics that you may devise:
- Subjective comparison between the perceptual quality of the original and the “adapted” content.
- Subjective comparison between the perceptual quality of a scaled-down version of the original (using a 5-tap poly-phase filter) and the “adapted” content.
- Real-time Performance.
Such subjective comparison can relate to the “quality” of the image and/or the average time it takes a user to comprehend/consume the adapted content.
About Radvision
Radvision (Nasdaq: RVSN) is the industry’s leading provider of products and technologies for unified visual communications over IP, 3G and emerging IMS/Next Generation networks - enabling high definition video-conferencing, converged video telephony services, and scalable desktop–based visual communications.
Feel free to correspond with the challenge authors via the comments form below.
For private correspondence, consult the About page for contact details.
on Feb 2nd, 2009 at 7:20 am
[...] moves towards mobility (pdf), various devices will be used to display such data. This then raises the challenge of adaptation of the data, in real-time, to different devices with different [...]
on Feb 8th, 2009 at 9:41 am
how to evluate perceptual quality?
on Feb 8th, 2009 at 9:53 am
As mentioned in the challenge, the following criteria could be used for “percpetual quality” measurment - the amount of time it takes a user to comprehend/consume the “scaled” content.
Of course, any other measurement that relates to the quality of a user’s perception of the “scaled” content is acceptable.
on Feb 11th, 2009 at 7:11 pm
[...] Real-time Data Collaboration Adaptation for Multi-Device Video Conferencing With the video conferencing market moving out of the meeting rooms and into laptops, netbooks, [...]
on Feb 24th, 2009 at 5:11 am
[...] : CC email linking to More … February 24th, 2009 | Category: Uncategorized | Leave a [...]