Name
Abstract | ||
|---|---|---|
In this paper, we present an innovative framework for a 3D game character to adopt human action sequence style by learning from videos. The framework is demonstrated for kickboxing, and can be applied to other activities in which individual style includes improvisation of the sequence in which a set of basic actions are performed. A video database of a number of actors performing the basic kickboxing actions is used for feature word vocabulary creation using 3D SIFT descriptors computed for salient points on the silhouette. Next an SVM classifier is trained to recognize actions at frame level. Then an individual actor's action sequence is gathered automatically from the actor's kickboxing videos and an HMM structure is trained. The HMM, equipped with the basic repertoire of 3D actions created just once, drives the action level behavior of a 3D game character. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/978-3-642-16958-8_39 | MIG |
Keywords | Field | DocType |
basic action,game character,basic kickboxing action,human action sequence style,frame level,action level behavior,kickboxing video,action sequence,hmm structure,basic repertoire,hmm,svm,motion capture | Scale-invariant feature transform,Motion capture,Computer vision,Improvisation,Silhouette,Computer science,Support vector machine,Artificial intelligence,Hidden Markov model,Vocabulary,Salient | Conference |
Volume | ISSN | ISBN |
6459 | 0302-9743 | 3-642-16957-0 |
Citations | PageRank | References |
0 | 0.34 | 18 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| XiaoLong Chen | 1 | 0 | 0.34 |
| Kaustubha Mendhurwar | 2 | 0 | 1.69 |
| Sudhir Mudur | 3 | 5 | 4.77 |
| Thiruvengadam Radhakrishnan | 4 | 117 | 32.44 |
| Prabir Bhattacharya | 5 | 1010 | 147.90 |