Name
Abstract | ||
|---|---|---|
This paper's intention is to present a new approach for decomposing motion trajectories. The proposed algorithm is based on non-negative matrix factorization, which is applied to a grid like representation of the trajectories. From a set of training samples a number of basis primitives is generated. These basis primitives are applied to reconstruct an observed trajectory, and the reconstruction information can be used afterwards for classification. An extension of the reconstruction approach furthermore enables to predict the observed movement further into the future. The proposed algorithm goes beyond the standard methods for tracking, since it doesn't use an explicit motion model but is able to adapt to the observed situation. In experiments we used real movement data to evaluate several aspects of the proposed approach. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1007/978-3-642-04277-5_81 | ICANN (2) |
Keywords | Field | DocType |
reconstruction approach,explicit motion model,observed movement,decomposing motion trajectory,spatio-temporal nmf,observed trajectory,basis primitive,observed situation,new approach,basis decomposition,proposed algorithm,non negative matrix factorization,prediction,human interaction,robot | Pattern recognition,Computer science,Matrix decomposition,Non-negative matrix factorization,Artificial intelligence,Robot,Machine learning,Trajectory,Grid | Conference |
Volume | ISSN | Citations |
5769 | 0302-9743 | 3 |
PageRank | References | Authors |
0.40 | 5 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sven Hellbach | 1 | 63 | 9.77 |
| Julian Eggert | 2 | 299 | 43.23 |
| Edgar Körner | 3 | 424 | 48.91 |
| Horst-Michael Gross | 4 | 761 | 92.05 |