Intelligent Studios Modeling Space and Action to Control TV Cameras

This article describes strategies to model the geometry and actions occurring in a performance space such as a TV studio. The basic assumption is that in such situations a script is available, providing contextual information that can be coupled with visual data from cameras monitoring the space. The integration of linguistic and visual information is accomplished through the use of approximate world models, a combination of symbolic data and geometrical 3-D models with low positional accuracy. Some commonsense reasoning is often required to infer visual and geometrical attributes from the script, and the article examines how simple inference rules are able to provide most of the necessary information. We also detail an application where an intelligent studio controls three automatic robotic cameras, producing video sequences with TV quality of framing.

[1]  Roger C. Schank,et al.  CONCEPTUAL DEPENDENCY THEORY , 1975 .

[2]  Charles J. Rieger,et al.  CONCEPTUAL MEMORY AND INFERENCE , 1975 .

[3]  Yorick Wilks,et al.  A Preferential, Pattern-Seeking, Semantics for Natural Language Inference , 1975, Artif. Intell..

[4]  Darren Newtson,et al.  The objective basis of behavior units. , 1977 .

[5]  R. Thibadeau.  Artificial Perception of Actions , 1986 .

[6]  Jugal Kalita,et al.  Natural language control of animation of task performance in a physical domain , 1990 .

[7]  David J. Israel,et al.  Actions and Movements , 1991, IJCAI.

[8]  M. R. Manzini.  Learnability and Cognition , 1991 .

[9]  Jeffrey Mark Siskind,et al.  Naive physics, event perception, lexical semantics, and language acquisition , 1992 .

[10]  Yasuo Kuniyoshi,et al.  Qualitative Recognition of Ongoing Human Action Sequences , 1993, IJCAI.

[11]  K. Rohr.  Towards model-based recognition of human movements in image sequences , 1994 .

[12]  Michael J. Black,et al.  A computational and evolutionary perspective on the role of representation in vision , 1994 .

[13]  Steven M. Drucker,et al.  Intelligent camera control for graphical environments , 1994 .

[14]  James W. Davis,et al.  An appearance-based representation of action , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[15]  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.