Abstract | ||
---|---|---|
For applications such as video games and virtual walk-throughs, on-line locomotion control is an important issue. In general, the user prescribes a sequence of motions one by one while providing an input trajectory. Since the input trajectory lacks in human characteristics, one may not synthesize quality motions by blindly following it. In this paper, we present a novel data-driven scheme for transforming a user-prescribed trajectory to a human trajectory in an on-line manner. As preprocessing, we analyze example motion data to extract human steering behavior. At run-time, the input trajectory is refined to reflect the steering behavior. Together with an existing on-line motion synthesis system, our scheme forms a feedback loop, in which the user effectively specifies an intended human trajectory. Copyright © 2007 John Wiley & Sons, Ltd. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1002/cav.v18:4/5 | Journal of Visualization and Computer Animation |
Keywords | Field | DocType |
feedback loop,motion control,character animation,computer animation | Computer vision,Motion control,Computer graphics (images),Computer science,Simulation,Character animation,Feedback loop,Preprocessor,Artificial intelligence,Computer animation,Motion synthesis,Trajectory | Journal |
Volume | Issue | ISSN |
18 | 4-5 | 1546-4261 |
Citations | PageRank | References |
6 | 0.56 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taesoo Kwon | 1 | 800 | 56.37 |
Sung Yong Shin | 2 | 1904 | 168.33 |