Skip to main content

Exploiting spatial descriptions in visual scene analysis

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.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. Bates D, Maechler M, Bolker B (2011) lme4: linear mixed-effects models using S4 classes. R package version 0.999375-42. http://CRAN.R-project.org/package=lme4. Accessed 6 June 2012

  2. Baum M (2011) Using spinImages for 3D object classification. Bachelor Thesis, Faculty of Technology, Bielefeld University

  3. Carlson LA (1999) Selecting a reference frame. Spatial Cogn Comput 1(4):365–379. doi:10.1023/A:1010071109785

    Article  Google Scholar 

  4. Carlson-Radvansky LA, Irwin DA (1993) Frames of reference in vision and language: where is above? Cognition 46:223–244. doi:10.1016/j.bbr.2011.03.031

    PubMed  Article  CAS  Google Scholar 

  5. Cohn A, Renz J (2007) Qualitative spatial representation and reasoning. In: Harmelen F, Lifschitz V, Porter B (eds) Handbook of knowledge representation. Elsevier, Amsterdam, pp 1–47

    Google Scholar 

  6. Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24:381–395. doi:10.1145/358669.358692

    Article  Google Scholar 

  7. Graf R, Herrmann T (1989) Zur sekundären Raumreferenz: Gegenüberobjekte bei nicht-kanonischer Betrachterposition. Arbeiten aus dem SFB 245 “Sprechen und Sprachverstehen im sozialen Kontext”. Heidelberg/Mannheim

  8. Johnson AE, Hebert M (1998) Surface matching for object recognition in complex 3D scenes. Image Vis Comput 16:635–651. doi:10.1016/S0262-8856(98)00074-2

    Article  Google Scholar 

  9. Levinson SC (2003) Space in language and cognition. Explorations in cognitive diversity. University Press, Cambridge

    Book  Google Scholar 

  10. Logan GD, Sadler DD (1996) A computational analysis of the apprehension of spatial relations. In: Bloom P, Peterson MA, Nadel L, Garrett M (eds) Language and space. MIT Press, Cambridge, pp 493–529

    Google Scholar 

  11. Miller G, Johnson-Laird P (1976) Language and perception. Belknap Press, Cambridge

    Google Scholar 

  12. Mukerjee A (1998) Neat versus scruffy: a review of computational models for spatial expressions. In: Oliver P, Gapp KP (eds) Representation and processing of spatial expressions. L. Erlbaum Associates Inc, Hillsdale, NJ, pp 1–35

    Google Scholar 

  13. R Development Core Team (2011) R: A language and environment for statistical computing. R foundation for statistical computing, Vienna

    Google Scholar 

  14. Rusu RB, Cousins S (2011) 3D is here: point cloud library (PCL). IEEE Int Conf Robot Autom (ICRA). doi:10.1109/ICRA.2011.5980567

Download references

Acknowledgments

This work was funded by the German Research Foundation (DFG) within the Collaborative Research Center 673 “Alignment in Communication”.

Conflict of interest

This supplement was not sponsored by outside commercial interests. It was funded entirely by ECONA, Via dei Marsi, 78, 00185 Roma, Italy.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Leon Ziegler.

Additional information

Leon Ziegler and Katrin Johannsen have equally contributed to this work.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Ziegler, L., Johannsen, K., Swadzba, A. et al. Exploiting spatial descriptions in visual scene analysis. Cogn Process 13, 369–374 (2012). https://doi.org/10.1007/s10339-012-0460-1

Download citation

Keywords

  • Spatial cognition
  • Reference frames
  • Spatial language
  • 3D perception
  • Speech perception
  • Scene interpretation