Abstract | ||
---|---|---|
In this paper we address the correspondence problem, with its application to nonrigid tracking and unsupervised modelling, as a nonparametric, active-linking topology learning problem. Unlike existing soft competitive learning methods, Active Growing Neural Gas (A-GNG) has both global and local properties which allows part of the network to reconfigure while tracking. In addition, A-GNG uses a number of features (e.g. topographic product, local grey-level and map transformation) so that the topological relations are preserved and nodes correspondences are retained between tracked configurations. Experimental results in a sequence of hand gestures and artificial data have shown the superiority of our proposed method over the original GNG. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-75773-3_11 | ICCV-HCI |
Keywords | Field | DocType |
local property,artificial data,local grey-level,nonparametric modelling,active-linking topology,neural gas,correspondence problem,map transformation,hand gesture,soft competitive learning method,competitive learning | Competitive learning,Gesture,Computer science,Self-organizing map,Human–computer interaction,Artificial intelligence,Correspondence problem,Pattern recognition,Topographic map,Reference vector,Nonparametric statistics,Neural gas,Machine learning | Conference |
Volume | ISSN | ISBN |
4796 | 0302-9743 | 3-540-75772-4 |
Citations | PageRank | References |
4 | 0.44 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anastassia Angelopoulou | 1 | 102 | 21.29 |
Alexandra Psarrou | 2 | 199 | 27.14 |
Gaurav Gupta | 3 | 14 | 7.06 |
José García Rodríguez | 4 | 192 | 29.10 |