Ketan Mayer-Patel | University of North Carolina at Chapel Hill, NC, USA

Abstract: There is a gap to be sparked between the fields of multimedia systems and computer vision. That gap is a vision-driven interface for rate controlled compressed video. Advances in vision have made real-world, real-time vision-based applications a reality. In doing so, there is now an imperative to integrate and negotiate systems-level tradeoffs with these vision algorithms as these real-world applications are realized. In this talk, I’ll motivate and propose a rate controlled interface extension for OpenCV to compressed video sources. I’ll discuss a possible compressed-domain implementation that is adaptable to a wide array of existing video standards. Finally, I’ll speculate about the potential impact of such an interface on future directions of research in vision-based multimedia systems.

Bio: Ketan Mayer-Patel is an associate professor in the Department of Computer Science at the University of North Carolina at Chapel Hill. He received his Ph.D. in Computer Science in 1999 from the University of California at Berkeley. He was a recipient of an NSF CAREER award and is the current chair of the MMSys executive committee. His general research interest is in multimedia systems. Currently, he is investigating vision-based rate control, scalable display interfaces, and distributed archival video encoding.