Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Probabilistic scene models for image interpretation

: Bauer, A.

Preprint urn:nbn:de:0011-n-1374511 (448 KByte PDF)
MD5 Fingerprint: e2ccfc89f34f5c2ded31a2f02259fbdd
The original publication is available at
Created on: 19.8.2010

Hüllermeier, E.:
Information Processing and Management of Uncertainty in Knowledge-Based Systems. Proceedings, Part II : 13th International Conference, IPMU 2010, Dortmund, Germany, June 28-July 2, 2010
Berlin: Springer, 2010 (Communications in computer and information science 81)
ISBN: 978-3-642-14057-0
ISBN: 978-3-642-14058-7
ISSN: 1865-0929
International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU) <13, 2010, Dortmund>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()
image interpretation; image understanding; high-level vision; generative models; Bayesian inference; relaxation labeling; importance sampling; SiteAnalyst

Image interpretation describes the process of deriving a semantic scene description from an image, based on object observations and extensive prior knowledge about possible scene descriptions and their structure. In this paper, a method for modeling this prior knowledge using probabilistic scene models is presented. In conjunction with Bayesian Inference, the model enables an image interpretation system to classify the scene, to infer possibly undetected objects as well as to classify single objects taking into account the full context of the scene.