Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Probabilistic active vision: An overview

: Huber, M.

Preprint urn:nbn:de:0011-n-1653608 (298 KByte PDF)
MD5 Fingerprint: 13d58c91851902d9cf0a40460a11d370
Created on: 21.6.2011

Beyerer, J.; Huber, M.:
Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory 2010. Proceedings : Was held in La Bresse, France, from July 19 to July 23, 2010
Karlsruhe: KIT Scientific Publishing, 2011 (Karlsruher Schriften zur Anthropomatik 7)
ISBN: 978-3-86644-609-0
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung and Institute for Anthropomatics, Vision and Fusion Laboratory (Joint Workshop) <2010, La Bresse>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

In active vision, the configuration of a camera system is adapted automatically in order to acquire the most informative observations for a given task. This paper gives an overview of a probabilistic approach for active vision. Planning the camera parameters is described as a partially observable Markov decision process. Here, the relevant components of the image acquisition task, i.e., object and camera, are represented by means of probabilistic models for incorporating uncertainties into planning. Additionally including reinforcement learning allows a priori unknown probabilistic models.