Probabilistic Scene Modeling for Situated Computer Vision

Wachsmuth S, Swadzba A (2008)
In: Logic and Probability for Scene Interpretation. Cohn AG, Hogg DC, Möller R, Neumann B (Eds); Dagstuhl Seminar Proceedings, 8091. Dagstuhl, Germany: Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany.

Download
Restricted
Conference Paper | Published | English
Editor
Cohn, Anthony G. ; Hogg, David C. ; Möller, Ralf ; Neumann, Bernd
Abstract
Verbal statements and vision are a rich source of information in a human-machine interaction scenario. For this reason Situated Computer Vision aims to include knowledge about the communicative situation in which it takes place. This paper presents three approaches how to achieve scene models of such scenarios combining different modalities. Seeing (planar) scenes as configurations of parts leads to a probabilistic modeling with Bayes’ nets relating spoken utterances with results of an object recognition step. In the second approach parallel datasets form the basis for analyzing the statistical dependencies between them through learning a statistical translation model which maps between these datasets (here: words in a text and boundary fragments extracted in 2D images). The third approach deals with complex indoor scenes from which 3D data is acquired. Planar structures in the 3D points and statistics extracted on these planar patches describe the coarse spatial layouts of different indoor room types in such a way that a holistic classification scheme can be provided.
Publishing Year
PUB-ID

Cite this

Wachsmuth S, Swadzba A. Probabilistic Scene Modeling for Situated Computer Vision. In: Cohn AG, Hogg DC, Möller R, Neumann B, eds. Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings. Vol 8091. Dagstuhl, Germany: Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany; 2008.
Wachsmuth, S., & Swadzba, A. (2008). Probabilistic Scene Modeling for Situated Computer Vision. In A. G. Cohn, D. C. Hogg, R. Möller, & B. Neumann (Eds.), Dagstuhl Seminar Proceedings: Vol. 8091. Logic and Probability for Scene Interpretation Dagstuhl, Germany: Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany.
Wachsmuth, S., and Swadzba, A. (2008). “Probabilistic Scene Modeling for Situated Computer Vision” in Logic and Probability for Scene Interpretation, ed. A. G. Cohn, D. C. Hogg, R. Möller, and B. Neumann Dagstuhl Seminar Proceedings, vol. 8091, (Dagstuhl, Germany: Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany).
Wachsmuth, S., & Swadzba, A., 2008. Probabilistic Scene Modeling for Situated Computer Vision. In A. G. Cohn, et al., eds. Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings. no.8091 Dagstuhl, Germany: Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany.
S. Wachsmuth and A. Swadzba, “Probabilistic Scene Modeling for Situated Computer Vision”, Logic and Probability for Scene Interpretation, A.G. Cohn, et al., eds., Dagstuhl Seminar Proceedings, vol. 8091, Dagstuhl, Germany: Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany, 2008.
Wachsmuth, S., Swadzba, A.: Probabilistic Scene Modeling for Situated Computer Vision. In: Cohn, A.G., Hogg, D.C., Möller, R., and Neumann, B. (eds.) Logic and Probability for Scene Interpretation. Dagstuhl Seminar Proceedings. 8091, Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany, Dagstuhl, Germany (2008).
Wachsmuth, Sven, and Swadzba, Agnes. “Probabilistic Scene Modeling for Situated Computer Vision”. Logic and Probability for Scene Interpretation. Ed. Anthony G. Cohn, David C. Hogg, Ralf Möller, and Bernd Neumann. Dagstuhl, Germany: Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany, 2008.Vol. 8091. Dagstuhl Seminar Proceedings.
Main File(s)
Access Level
Restricted Closed Access
Last Uploaded
2012-03-30 13:20:12

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar