Name
Abstract | ||
|---|---|---|
Touch-free gesture technology opens new avenues for human–machine interaction. We show how self-organizing maps (SOM) can be used for hand and full body tracking. We use a range camera for data acquisition and apply a SOM-learning process for each frame in order to capture the pose. In a next step we introduce an extension of the SOM to 1D and 2D segments for an improved representation and skeleton tracking of body and hand. The proposed SOM based algorithms are very efficient and robust, and produce good tracking results. Their efficiency allows to implement these algorithms on embedded systems, which we demonstrate on an ARM-based embedded platform. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1016/j.neucom.2013.10.041 | Neurocomputing |
Keywords | Field | DocType |
Body tracking,Hand skeleton tracking,Gestures,Self-organizing maps,Kinect,TOF cameras | Computer vision,Computer graphics (images),Gesture,Data acquisition,Self-organizing map,Artificial intelligence,Mathematics | Journal |
Volume | ISSN | Citations |
147 | 0925-2312 | 8 |
PageRank | References | Authors |
0.47 | 15 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Foti Coleca | 1 | 14 | 1.57 |
| Andreea State | 2 | 11 | 0.86 |
| Sascha Klement | 3 | 24 | 3.26 |
| Erhardt Barth | 4 | 653 | 58.33 |
| Thomas Martinetz | 5 | 1462 | 231.48 |