A knowledge-based moviemaking approach

Authors:
Jinhong Shen;Seiya Miyazaki;Terumasa Aoki;Hirhoshi Yasuda
Affiliations:
The University of Tokyo, Tokyo, Japan;Matsushita Electric Industrial Co., Ltd., Tokyo, Japan;The University of Tokyo, Tokyo, Japan;The University of Tokyo, Tokyo, Japan
Venue:
AIKED'05 Proceedings of the 4th WSEAS International Conference on Artificial Intelligence, Knowledge Engineering Data Bases
Year:
2005

Citing 7
Cited 0

The virtual cinematographer: a paradigm for automatic real-time camera control and directing

SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Cognitive modeling: knowledge, reasoning and planning for intelligent characters

Proceedings of the 26th annual conference on Computer graphics and interactive techniques
WordsEye: an automatic text-to-scene conversion system

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Planning animation cinematography and shot structure to communicate theme and mood

Proceedings of the 2nd international symposium on Smart graphics
The Application of AI to Automatically Generated Animation

AI '01 Proceedings of the 14th Australian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence
Content-based video retrieval and compression: a unified solution

ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 1 - Volume 1
Declarative camera control for automatic cinematography

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

We are developing an intelligent approach of motion picture generation for desktop software system EMM (Electronic MovieMaker) that aims at automating the production of digital movies with various visual effects like three-dimension animation, real image, and their composition. This paper describes our efforts on EMM focusing on automatic synthesis of character animation and automatic video retrieval from video database/Web video library dependent on filmmaking rules, both of which have just right inverse processes opposed to each other. Two kinds of screenplay' user interface are introduced along with their theoretical basis of design. Then expounds how to visualize the screenplay by using cinematic 'rules of thumb' to make a scene. The implementation of building knowledge representation includes scene's layout and shooting and character's action written in CLIPS language.