Name
Abstract | ||
|---|---|---|
Ensuring the consistency of memory content is a key feature of cognitive vision systems. This paper presents an approach to deal with functional dependencies of hypotheses stored in a visual active memory. By means of Bayesian networks a probabilistic approach is used to incorporate uncertainty of observations. Furthermore, a measurement to detect inconsistencies in the memory is introduced. The benefit of this validation module as part of an integrated system is shown for the task of visual surveillance in an office scenario. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/ICPR.2004.564 | ICPR |
Keywords | Field | DocType |
Bayes methods,cognitive systems,computer vision,probability,surveillance,Bayesian networks,cognitive vision system,memory consistency validation,memory content,probabilistic approach,visual active memory,visual surveillance | Computer vision,Cognitive systems,Computer science,Functional dependency,Bayesian network,Artificial intelligence,Probabilistic logic,Consistency model,Visual surveillance,Machine learning,Cognitive vision | Conference |
Volume | ISSN | ISBN |
2 | 1051-4651 | 0-7695-2128-2 |
Citations | PageRank | References |
7 | 0.72 | 6 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marc Hanheide | 1 | 261 | 28.74 |
| Christian Bauckhage | 2 | 1979 | 195.86 |
| Gerhard Sagerer | 3 | 830 | 108.85 |