Video Analysis and Enhancement: Spatio-Temporal Methods for Extracting Content from Videos and Enhancing Video Output
Irfan Essa (prof.irfanessa.com)
Georgia Institute of Technology
School of Interactive Computing
Hosted by Max-Planck-Institut für Informatik in Saarbrucken (Bernt Schiele, Director of Computer Vision and Multimodal Computing)
In this talk, I will start with describing the pervasiveness of image and video content, and how such content is growing with the ubiquity of cameras. I will use this to motivate the need for better tools for analysis and enhancement of video content. I will start with some of our earlier work on temporal modeling of video, then lead up to some of our current work and describe two main projects. (1) Our approach for a video stabilizer, currently implemented and running on YouTube, and its extensions. (2) A robust and scaleable method for video segmentation.
I will describe, in some detail, our Video stabilization method, which generates stabilized videos and is in wide use running on YouTube, with Millions of users. Then I will describe an efficient and scalable technique for spatiotemporal segmentation of long video sequences using a hierarchical graph-based algorithm. I will describe the videosegmentation.com site that we have developed for making this system available for wide use.
Finally, I will follow up with some recent work on image and video analysis in the mobile domains. I will also make some observations about the ubiquity of imaging and video in general and need for better tools for video analysis.