IPOD: Interactive Production On Demand

Yu, Bin; Nahrstedt, Klara

Permalink

https://hdl.handle.net/2142/10823 Copy

Description

Title

IPOD: Interactive Production On Demand

Author(s)

• Yu, Bin
• Nahrstedt, Klara

Issue Date

2004-05

Keyword(s)

Multimedia

Abstract

Traditional TV production systems monitor multiple perspectives of human activities and interests, but hide the source streams by providing all viewers with the same final video program. This approach leaves huge amount of valuable raw media footage unused and prevents individual user content customization. In this paper, we propose a novel video production model, called Interactive Production On Demand (IPOD), where the video content production is on-demand and based on viewers' interactions. Though related work has been done to fuse streams from multiple perspectives and render a virtual view from any view point, IPOD is essentially different in that it solicits and utilizes valuable user interactions via an innovative user interface, it relies on video composition effects that are computationally less expensive, it requires no camera calibration or coordination, and it produces TV-like video program layouts that are already familiar to most users. To combine both user knowledge and automatic feature detection, we propose a scoring framework to keep track of the interestingness of different streams at different time points. Furthermore, we present algorithms to automatically generate the video production schedule on-demand. Preliminary evaluation results confirm that IPOD will lead to a new era of a multiple perspective capturing-composition-presentation model for next generation video applications.

Type of Resource

text

Permalink

http://hdl.handle.net/2142/10823

Copyright and License Information

You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the University of Illinois at Urbana-Champaign Computer Science Department under terms that include this permission. All other rights are reserved by the author(s).

Owning Collections