Abstract | ||
---|---|---|
This paper proposes a novel real-time hand tracking algorithm in the presence of occlusion. For this purpose, we construct
a limb model and maintain the model obtained from ARKLT methods with respect to second-order auto-regression model and Kanade-Lucas-Tomasi(KLT)
features, respectively. Furthermore, this method do not require to categorize types of superimposed hand motion based on directivity
obtained by the slope’s direction of KLT regression. Thus, we can develop a method of hand tracking for gesture and activity
recognition techniques frequently used in conjunction with Human-Robot Interaction (HRI) components.
|
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11751540_104 | Computational Science and Its Applications |
Keywords | Field | DocType |
limb model,activity recognition technique,klt regression,auto-regression model,bimanual hand tracking,human-robot interaction,novel real-time hand tracking,hand tracking,hand motion,arklt method,second order,activity recognition,human robot interaction,auto regressive,real time | Computer vision,Occlusion detection,Activity recognition,Regression,Directivity,Gesture,Computer science,Gesture recognition,Artificial intelligence,User interface | Conference |
Volume | ISSN | ISBN |
3980 | 0302-9743 | 3-540-34070-X |
Citations | PageRank | References |
1 | 0.36 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hye-jin Kim | 1 | 51 | 6.18 |
Keun-chang Kwak | 2 | 361 | 32.96 |
Jaeyeon Lee | 3 | 120 | 21.40 |