Loading...
Please wait, while we are loading the content...
Similar Documents
Fast learning to recognize objects : Dynamic Fields in label-feature spaces
| Content Provider | Semantic Scholar |
|---|---|
| Author | Faubel, Christian |
| Copyright Year | 2006 |
| Abstract | We bring Dynamic Field Theory to bear on a problem of robot vision, learning to recognize objects on a fast time scale, while interacting with a human user. Dynamic fields represent each object through low-level features like color, shape, and size cues. Recognition and teaching leads to localized activation peaks in these fields, which leave a memory trace, that preshapes the fields during recognition, promoting activation of the matching object. Mismatches are corrected by user input. We demonstrate the approach in a robotic implementation. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.service-robotik-initiative.de/download/publicationen/RUB/ICDL2006_Faubel_Schoener.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |