Exploiting spatial descriptions in visual scene analysis

Ziegler L, Johannsen K, Swadzba A, de Ruiter J, Wachsmuth S (2012)
Cognitive Processing 13(S1): 369-374.

Download
Campus/VPN
Journal Article | Published | English
Abstract
The reliable automatic visual recognition of indoor scenes with complex object constellations using only sensor data is a nontrivial problem. In order to improve the construction of an accurate semantic 3D model of an indoor scene, we exploit human-produced verbal descriptions of the relative location of pairs of objects. This requires the ability to deal with different spatial reference frames (RF) that humans use interchangeably. In German, both the intrinsic and relative RF are used frequently, which often leads to ambiguities in referential communication. We assume that there are certain regularities that help in specific contexts. In a first experiment, we investigated how speakers of German describe spatial relationships between different pieces of furniture. This gave us important information about the distribution of the RFs used for furniture-predicate combinations, and by implication also about the preferred spatial predicate. The results of this experiment are compiled into a computational model that extracts partial orderings of spatial arrangements between furniture items from verbal descriptions. In the implemented system, the visual scene is initially scanned by a 3D camera system. From the 3D point cloud, we extract point clusters that suggest the presence of certain furniture objects. We then integrate the partial orderings extracted from the verbal utterances incrementally and cumulatively with the estimated probabilities about the identity and location of objects in the scene, and also estimate the probable orientation of the objects. This allows the system to significantly improve both the accuracy and richness of its visual scene representation.
Publishing Year
ISSN
eISSN
PUB-ID

Cite this

Ziegler L, Johannsen K, Swadzba A, de Ruiter J, Wachsmuth S. Exploiting spatial descriptions in visual scene analysis. Cognitive Processing. 2012;13(S1):369-374.
Ziegler, L., Johannsen, K., Swadzba, A., de Ruiter, J., & Wachsmuth, S. (2012). Exploiting spatial descriptions in visual scene analysis. Cognitive Processing, 13(S1), 369-374.
Ziegler, L., Johannsen, K., Swadzba, A., de Ruiter, J., and Wachsmuth, S. (2012). Exploiting spatial descriptions in visual scene analysis. Cognitive Processing 13, 369-374.
Ziegler, L., et al., 2012. Exploiting spatial descriptions in visual scene analysis. Cognitive Processing, 13(S1), p 369-374.
L. Ziegler, et al., “Exploiting spatial descriptions in visual scene analysis”, Cognitive Processing, vol. 13, 2012, pp. 369-374.
Ziegler, L., Johannsen, K., Swadzba, A., de Ruiter, J., Wachsmuth, S.: Exploiting spatial descriptions in visual scene analysis. Cognitive Processing. 13, 369-374 (2012).
Ziegler, Leon, Johannsen, Katrin, Swadzba, Agnes, de Ruiter, Jan, and Wachsmuth, Sven. “Exploiting spatial descriptions in visual scene analysis”. Cognitive Processing 13.S1 (2012): 369-374.
Main File(s)
Access Level
Campus/VPN UniBi Only
Last Uploaded
2012-09-26 12:25:01

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

1 Citation in Europe PMC

Data provided by Europe PubMed Central.

Reference frame selection in dialog: priming or preference?
Johannsen K, Ruiter JP., Front Hum Neurosci 7(), 2013
PMID: 24137122

14 References

Data provided by Europe PubMed Central.


AUTHOR UNKNOWN, 0

AUTHOR UNKNOWN, 0

LA, Spatial Cogn Comput 1(4), 1999
Frames of reference in vision and language: where is above?
Carlson-Radvansky LA, Irwin DE., Cognition 46(3), 1993
PMID: 8462273

A, 2007

MA, Commun ACM 24(), 1981

AUTHOR UNKNOWN, 0

AE, Image Vis Comput 16(), 1998

SC, 2003

GD, 1996

G, 1976

A, 1998

R, 2011

AUTHOR UNKNOWN, 0

Export

0 Marked Publications

Open Data PUB

Web of Science

View record in Web of Science®

Sources

PMID: 22806654
PubMed | Europe PMC

Search this title in

Google Scholar