Name
Abstract | ||
|---|---|---|
Tracking of rigid and articulated objects is usually addressed within a particle filter framework or by correspondence based gradient descent methods. We combine both methods, such that (a) the correspondence based estimation gains the advantage of the particle filter and becomes able to follow multiple hypotheses while (b) the particle filter becomes able to propagate the particles in a better manner and thus gets by with a smaller number of particles. Results on noisy synthetic depth data show that the new method is able to track motion correctly where the correspondence based method fails. Further experiments with real-world stereo data underline the advantages of our coupled method. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-75703-0_3 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
noisy synthetic depth data,gradient-enhanced particle filter,vision-based motion,better manner,gradient descent method,articulated object,new method,estimation gain,multiple hypothesis,particle filter framework,particle filter,real-world stereo data,motion capture | Motion capture,Particle number,Computer vision,Gradient descent,Computer science,Particle filter,Multiple hypotheses,Vision based,Artificial intelligence,Monte Carlo localization | Conference |
Volume | ISSN | ISBN |
4814 | 0302-9743 | 3-540-75702-3 |
Citations | PageRank | References |
4 | 0.40 | 12 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Grest | 1 | 129 | 10.65 |
| Volker Krüger | 2 | 1312 | 69.60 |