Abstract
In our paper we investigate the use of qualitative spatial representations (QSR) about relative direction and distance for shape representation. Our new approach has the advantage that we can generate prototypical shapes from our abstract representation in first-order predicate calculus. Using the conceptual neighborhood which is an established concept in QSR we can directly establish a conceptual neighborhood between shapes that translates into a similarity metric for shapes. We apply this similarity measure to a challenging computer vision problem and achieve promising first results.
R. Moratz—The Principal Investigator and responsible lab author.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Material in this section is presented as an abridged summary of previous work by Moratz and Wallgrün [22].
- 2.
Note that while this analogy makes use of three-dimensional space, our model refers to the 2D plane.
- 3.
The first three letters of the symbol \(e\mathcal {OPRA}_m\) stand for elevated oriented point.
- 4.
Note, that our parameters are elements of a cyclic group so that no modulo operation is required.
- 5.
The stop parameter can also be defined with respect to the number of desired vertices, i.e., some pre-specified resolution. This is the approach taken in this paper to enable comparison between polylines with the same number of vertices.
- 6.
For the first edge, the last edge is used as the control.
- 7.
In 6.2, we present a more detailed look at the \(e\mathcal {OPRA}_m\) direction matrix comparison metric.
- 8.
Currently, this is defined as \(gap\le 10\,\%\) of the shortest hull edge length.
- 9.
Given the cyclic property of direction intervals in \(e\mathcal {OPRA}_m\), we are interested in the shortest-path distance from one interval to another instead of the raw absolute difference. I.e., any error greater than 2m can be expressed as \(4m-error\).
References
Barkowsky, T., Latecki, L.J., Richter, K.-F.: Schematizing maps: simplification of geographic shape by discrete curve evolution. In: Habel, C., Brauer, W., Freksa, C., Wender, K.F. (eds.) Spatial Cognition 2000. LNCS (LNAI), vol. 1849, pp. 41–53. Springer, Heidelberg (2000)
Berendt, B.: Modelling subjective distances. In: Brewka, G., Habel, C., Nebel, B. (eds.) KI 1997. LNCS, vol. 1303, pp. 195–206. Springer, Heidelberg (1997)
Clementini, E., Felice, P.D., Hernández, D.: Qualitative representation of positional information. Artif. intell. 95(2), 317–356 (1997)
Cohn, A.G.: Qualitative spatial representation and reasoning techniques. In: Brewka, G., Habel, C., Nebel, B. (eds.) KI 1997. LNCS, vol. 1303, pp. 1–30. Springer, Heidelberg (1997)
Dubba, K., Cohn, A., Hogg, D., Bhatt, M., Dylla, F.: Learning relational event models from video. J. Artif. Intell. Res. (JAIR) (to appear)
Dylla, F., Wallgrün, J.O.: Qualitative spatial reasoning with conceptual neighborhoods for agent control. J. Intell. Robot. Syst. 48(1), 55–78 (2007)
Freksa, C.: Using orientation information for qualitative spatial reasoning. In: Frank, A.U., Formentini, U., Campari, I. (eds.) GIS 1992. LNCS, vol. 639, pp. 162–178. Springer, Heidelberg (1992). doi:10.1007/3-540-55966-3_10
Gibson, J.: The Ecological Approach to Visual Perception. Houghton Mifflin, Boston (1979)
Gottfried, B.: Tripartite line tracks. In: International Conference on Computer Vision and Graphics, pp. 288–293 (2002)
Isli, A., Moratz, R.: Qualitative spatial representation and reasoning: algebraic models for relative position. Univ, Bibliothek des Fachbereichs Informatik (1999)
Latecki, L.J., DeMenthon, D., Rosenfeld, A.: Automatic extraction of relevant frames from videos by polygon simplification. In: Sommer, G., Krüger, N., Perwass, C. (eds.) Mustererkennung, pp. 412–419. Springer, Heidelberg (2000)
Latecki, L.J., Lakämper, R.: Discrete approach to curve evolution. In: Levi, P., Schanz, M., Ahlers, R.-J., May, F. (eds.) Mustererkennung. Heidelberg, pp. 85–92. Springer, 1998 (1998)
Latecki, L.J., Lakämper, R.: Convexity rule for shape decomposition based on discrete contour evolution. Comput. Vis. Image Underst. 73(3), 441–454 (1999)
Latecki, L.J., Lakämper, R.: Polygon evolution by vertex deletion. In: Nielsen, M., Johansen, P., Fogh Olsen, O., Weickert, J. (eds.) Scale-Space 1999. LNCS, vol. 1682, pp. 398–409. Springer, Heidelberg (1999)
Latecki, L.J., Lakamper, R.: Shape similarity measure based on correspondence of visual parts. IEEE Trans. Pattern Anal. Mach. Intell. 22(10), 1185–1190 (2000)
Ligozat, G.: Qualitative triangulation for spatial reasoning. In: Campari, I., Frank, A.U. (eds.) COSIT 1993. LNCS, vol. 716, pp. 54–68. Springer, Heidelberg (1993)
Lovett, A., Forbus, K.D.: Shape is like space: modeling shape representation as a set of qualitative spatial relations. In: AAAI Spring Symposium: Cognitive Shape Processing (2010)
Moratz, R.: Representing Relative Direction as a Binary Relation of Oriented Points. In: Brewka, G., Coradeschi, S., Perini, A., Traverso, P. (eds.) Proceedings of ECAI-06. Frontiers in Artificial Intelligence and Applications, vol. 141, pp. 407–411. IOS Press, The Netherlands (2006)
Moratz, R., Renz, J., Wolter, D.: Qualitative spatial reasoning about line segments. In: Proceedings of ECAI 2000, pp. 234–238 (2000)
Moratz, R., Lücke, D., Mossakowski, T.: A condensed semantics for qualitative spatial reasoning about oriented straight line segments. Artif. Intell. 175(16–17), 2099–2127 (2011). doi:10.1016/j.artint.2011.07.004
Moratz, R., Tenbrink, T.: Affordance-based human-robot interaction. In: Rome, E., Hertzberg, J., Dorffner, G. (eds.) Towards Affordance-Based Robot Control. LNCS (LNAI), vol. 4760, pp. 63–76. Springer, Heidelberg (2008)
Moratz, R., Wallgrün, J.O.: Spatial reasoning with augmented points: extending cardinal directions with local distances. J. Spat. Inf. Sci. 5, 1–30 (2014)
Mossakowski, T., Moratz, R.: Qualitative reasoning about relative direction of oriented points. Artif. Intell. 180–181, 34–45 (2012). doi:10.1016/j.artint.2011.10.003
Prince, S.J.: Computer vision: models, learning, and inference. Cambridge University Press, New York (2012)
Randell, D.A., Cui, Z., Cohn, A.G.: A spatial logic based on regions and connection. In: KR 1992, pp. 165–176 (1992)
Raubal, M., Moratz, R.: A functional model for affordance-based agents. In: Rome, E., Hertzberg, J., Dorffner, G. (eds.) Towards Affordance-Based Robot Control. LNCS (LNAI), vol. 4760, pp. 91–105. Springer, Heidelberg (2008)
Renz, J., Nebel, B.: On the complexity of qualitative spatial reasoning: a maximal tractable fragment of the region connection calculus. Artif. Intell. 108(1), 69–123 (1999)
Schlieder, C.: Reasoning about ordering. In: Kuhn, W., Frank, A.U. (eds.) COSIT 1995. LNCS, vol. 988. Springer, Heidelberg (1995)
Schlieder, C.: Qualitative shape representation. Geogr. Objects Indeterminate Boundaries 2, 123–140 (1996)
Scivos, A., Nebel, B.: The finest of its class: The practical natural point-based ternary calculus lr for qualitative spatial reasoning. In: Freksa, C., Knauff, M., Krieg-Brückner, B., Nebel, B., Barkowsky, T. (eds.) Spatial Cognition IV. LNCS (LNAI), vol. 3343. Springer, Heidelberg (2005)
Worboys, M.F., Clementini, E.: Integration of imperfect spatial information. J. Vis. Lang. Comput. 12(1), 61–80 (2001)
Wunstel, M., Moratz, R.: Automatic object recognition within an office environment. In: Proceedings of the First Canadian Conference on Computer and Robot Vision, pp. 104–109. IEEE (2004)
Zimmermann, K., Freksa, C.: Qualitative spatial reasoning using orientation, distance, and path knowledge. Appl. Intell. 6(1), 49–58 (1996)
Acknowledgment
The authors would like to thank Jan Oliver Wallgrün for helpful discussions related to the topic of this paper. Our work was supported in part by the National Science Foundation under Grant Nos. CDI-1028895, OIA-1027897 and IIS-1302164. The information, data, or work presented herein was funded in part by the Office of Energy Efficiency and Renewable Energy (EERE), U.S. Department of Energy, under Award Number DE-EE0006803. (Disclaimer: This report was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor any agency thereof, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Dorr, C.H., Latecki, L.J., Moratz, R. (2015). Shape Similarity Based on the Qualitative Spatial Reasoning Calculus eOPRAm. In: Fabrikant, S., Raubal, M., Bertolotto, M., Davies, C., Freundschuh, S., Bell, S. (eds) Spatial Information Theory. COSIT 2015. Lecture Notes in Computer Science(), vol 9368. Springer, Cham. https://doi.org/10.1007/978-3-319-23374-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-23374-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23373-4
Online ISBN: 978-3-319-23374-1
eBook Packages: Computer ScienceComputer Science (R0)