Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Probabilistic reasoning on object occurrence in complex scenes

 
: Bauer, A.

:
Postprint urn:nbn:de:0011-n-1159486 (489 KByte PDF)
MD5 Fingerprint: 7a30a84377ae8dc01eea3cea3115f1bc
Copyright 2009 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
Created on: 13.2.2010


Bruzzone, L. ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Europe, Cardiff:
Image and signal processing for remote sensing XV : 31 August - 3 September 2009, Berlin, Germany
Bellingham, WA: SPIE, 2009 (Proceedings of SPIE 7477)
ISBN: 978-0-8194-7782-8
Paper 74770A
Conference "Image and Signal Processing for Remote Sensing" <15, 2009, Berlin>
English
Conference Paper, Electronic Publication
Fraunhofer IITB ( IOSB) ()
image understanding; high-level vision; Bayesian inference; selective perception; Monte-Carlo estimation; SiteAnalyst

Abstract
The interpretation of complex scenes requires a large amount of prior knowledge and experience. To utilize prior knowledge in a computer vision or a decision support system for image interpretation, a probabilistic scene model for complex scenes is developed. In conjunction with a model of the observe's characteristics (a human interpreter or a computer vision system), it is possible to support bottom-up inference from observations to interpretation as well as to focus the attention of the observer on the most promising classes of objects. The presented Bayesian approach allows rigorous formulation of uncertainty in the models and permits manifold inferences, such as the reasoning on unobserved object occurrences in the scene. Monte-Carlo methods for approximation of expectations from the posterior distribution are presented, permitting the efficient application even for high-dimensional models. The approach is illustrated on the interpretation of airfield scenes.

: http://publica.fraunhofer.de/documents/N-115948.html