| Tartalom: |
http://eprints.sztaki.hu/7149/ |
| Archívum: |
SZTAKI Repozitórium |
| Gyűjtemény: |
Status = In Press
Type = Conference or Workshop Item
|
| Cím: |
A Two-Layer Marked Point Process Framework for Multilevel Object Population Analysis
|
| Létrehozó: |
Benedek, Csaba
|
| Dátum: |
2013-03-13
|
| Téma: |
QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
|
| Tartalmi leírás: |
In this paper we introduce a probabilistic approach for extracting object ensembles from various digital images used by machine vision applications. The proposed framework extends conventional Marked Point Process models by allowing corresponding entities to form coherent object groups, by a Bayesian segmentation of the population. A global optimization process attempts to find the optimal configuration of entities and entity groups, considering the observed data, prior knowledge, and local interactions between the neighboring and semantically related objects. The proposed method is demonstrated in three different application areas: built in area analysis in remotely sensed images, traffic monitoring on airborne Lidar data and optical inspection of printed circuit boards.
|
| Nyelv: |
angol
|
| Típus: |
Conference or Workshop Item
PeerReviewed
|
| Formátum: |
text
|
| Azonosító: |
Benedek, Csaba (2013) A Two-Layer Marked Point Process Framework for Multilevel Object Population Analysis. In: International Conference on Image Analysis and Recognition, June 26-28, 2013, Póvoa de Varzim, Portugal. (In Press)
|
| Kapcsolat: |
|
