Automated camerawork for capturing desktop presentations - camerawork design and evaluation in virtual and real scenes

This paper introduces a novel automated camera control method for capturing desktop presentations. For this purpose, we first discuss typical features of shots and their cameraworks that frequently appear in TV programs. To realize those features in our automated video capturing system, we classify the purpose of a camerawork from two points of view: target and aspect-of-target. Then, we consider the correspondence between the classification and typical shots and cameraworks. We propose the virtual-frame control algorithm based on this idea, and the implementation in our video production system. We then show experimental results that verified our method through two kinds of experiments: virtual video capturing using CG animations and real video capturing of real presentations.

[1]  Kentaro Ishizuka,et al.  A live video imaging method for capturing presentation information in distance learning , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[2]  Claudio S. Pinhanez,et al.  Controlling view-based algorithms using approximate world models and action information , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Anoop Gupta,et al.  Auto-summarization of audio-video presentations , 1999, MULTIMEDIA '99.

[4]  David Salesin,et al.  The virtual cinematographer: a paradigm for automatic real-time camera control and directing , 1996, SIGGRAPH.

[5]  Anoop Gupta,et al.  Automating camera management for lecture room environments , 2001, CHI.

[6]  Brian Christopher Smith,et al.  Passive capture and structuring of lectures , 1999, MULTIMEDIA '99.

[7]  Yuichi Ohta,et al.  Human Behavior Recognition for an Intelligent Video Production System , 2002, IEEE Pacific Rim Conference on Multimedia.

[8]  Steven M. Drucker,et al.  CamDroid: a system for implementing intelligent camera control , 1995, I3D '95.

[9]  T Katsuura,et al.  Automatic control of a robot camera for broadcasting based on cameramen's techniques and subjective evaluation and analysis of reproduced images. , 2000, Journal of physiological anthropology and applied human science.

[10]  Yuichi Ohta,et al.  Tracking hands and objects for an intelligent video production system , 2002, Object recognition supported by user interaction for service robots.