2012 IEEE International Conference on Multimedia and Expo Workshops 2012
DOI: 10.1109/icmew.2012.39
|View full text |Cite
|
Sign up to set email alerts
|

A Rule-Based Virtual Director Enhancing Group Communication

Abstract: Audiovisual group communication systems deal with a large number of video streams, and, unlike less advanced videoconferencing systems, require intelligence for selecting adequate views for each of the connected rooms, in order to convey best what is happening in the other locations. Such a decision making component, in our implementation called Orchestration Engine (OE), acts as a Virtual Director. It processes lowlevel events, emitted by content analysis sensors, into editing commands. The OE has two main co… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
12
0

Year Published

2012
2012
2021
2021

Publication Types

Select...
6
1

Relationship

4
3

Authors

Journals

citations
Cited by 14 publications
(12 citation statements)
references
References 12 publications
0
12
0
Order By: Relevance
“…In this work we focused on features which can be computed between pairs of users rather than triples (consisting of the two users and the current message) since we are interested in integrating this work into a real-time video communication tool [9] which exploits users' social media stream as background knowledge for orchestrating the video communication. Therefore, it is necessary to be able to compute the features at the beginning of each communication session rather than re-computing them after each message or sentence.…”
Section: Conclusion Limitations and Future Workmentioning
confidence: 99%
“…In this work we focused on features which can be computed between pairs of users rather than triples (consisting of the two users and the current message) since we are interested in integrating this work into a real-time video communication tool [9] which exploits users' social media stream as background knowledge for orchestrating the video communication. Therefore, it is necessary to be able to compute the features at the beginning of each communication session rather than re-computing them after each message or sentence.…”
Section: Conclusion Limitations and Future Workmentioning
confidence: 99%
“…Detailed examples of rules already incorporated into the system together with challenges and workarounds in their implementation were reported in [8].…”
Section: Fusion and Interpretationmentioning
confidence: 99%
“…A clear example of this situation is rule number 4 which stops other rules from being executed if no more than 2 seconds have passed after the last camera change. Careful implementation of the reasoning mechanism and rule interplay is required to achieve conflict resolution [8] but this is beyond the scope of this paper.…”
mentioning
confidence: 98%
“…While the approach is well suited for static modeling of a production domain, experiments resulted in the conclusion that available reasoning frameworks are not fast and scalable enough for the requirements envisioned -see [9]. Ultimately, a rule-based approach was selected in combination with event processing technology [10], i.e. Complex Event Processing (CEP) [3] engines.…”
Section: Approach and Architecturementioning
confidence: 99%