Abstract | ||
---|---|---|
Self-organising neural networks preserves the topology of an input space by using their competitive learning. In this work we use a kind of self-organising network, the Growing Neural Gas, to represent non rigid objects as a result of an adaptive process by a topology-preserving graph that constitutes an induced Delaunay triangulation of their shapes. The neural network is used to build a system able to track image features in video image sequences. The system automatically keeps correspondence of features among frames in the sequence using its own structure. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-02481-8_35 | IWANN (2) |
Keywords | Field | DocType |
self-organising network,input space,neural network,induced delaunay triangulation,image feature,neural gas,video image sequence,competitive learning,non rigid object,adaptive process,visual surveillance,objects motion,delaunay triangulation | Competitive learning,Graph,Computer vision,Feature (computer vision),Computer science,Artificial intelligence,Artificial neural network,Visual surveillance,Machine learning,Neural gas,Delaunay triangulation | Conference |
Volume | ISSN | Citations |
5518 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
José García Rodríguez | 1 | 192 | 29.10 |
Francisco Flórez-revuelta | 2 | 481 | 34.95 |
Juan Manuel García-Chamizo | 3 | 72 | 8.98 |