Abstract
We propose a method for semantic parsing of images with regular structure. The structured objects are modeled in a densely connected CRF. The paper describes how to embody specific spatial relations in a representation called Spatial Pattern Templates (SPT), which allows us to capture regularity constraints of alignment and equal spacing in pairwise and ternary potentials.
Assuming the input image is pre-segmented to salient regions the SPT describe which segments could interact in the structured graphical model. The model parameters are learnt to describe the formal language of semantic labelings. Given an input image, a consistent labeling over its segments linked in the CRF is recognized as a word from this language.
The CRF framework allows us to apply efficient algorithms for both recognition and learning. We demonstrate the approach on the problem of facade image parsing and show that results comparable with state of the art methods are achieved without introducing additional manually designed detectors for specific terminal objects.
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
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Čech, J., Šára, R.: Languages for constrained binary segmentation based on maximum a posteriori probability labeling. IJIST 19(2), 69–79 (2009)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59(2), 167–181 (2004)
Galleguillos, C., Rabinovich, A., Belongie, S.: Object categorization using co-occurrence, location and appearance. In: Proc. CVPR (2008)
Gould, S., Rodgers, J., Cohen, D., Elidan, G., Koller, D.: Multi-class segmentation with relative location prior. IJCV 80(3), 300–316 (2008)
Kohli, P., Ladicky, L., Torr, P.: Robust higher order potentials for enforcing label consistency. IJCV 82(3), 302–324 (2009)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. Trans. PAMI 28(10), 1568–1583 (2006)
Korč, F., Förstner, W.: eTRIMS image database for interpreting images of man-made scenes. Tech. Rep. TR-IGG-P-2009-01 (2009)
Ladicky, L., Russell, C., Kohli, P., Torr, P.: Associative hierarchical CRFs for object class image segmentation. In: Proc. ICCV, pp. 739–746 (2009)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proc. ICML (2001)
Martinović, A., Mathias, M., Weissenberg, J., Van Gool, L.: A three-layered approach to facade parsing. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 416–429. Springer, Heidelberg (2012)
Nowozin, S., Gehler, P.V., Lampert, C.H.: On parameter learning in CRF-based approaches to object class image segmentation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 98–111. Springer, Heidelberg (2010)
Schmidt, M., Murphy, K., Fung, G., Rosales, R.: Structure learning in random fields for heart motion abnormality detection. In: Proc. CVPR (2008)
Schmidt, M., Murphy, K.: Convex structure learning in log-linear models: Beyond pairwise potentials. In: Proc. AISTATS (2010)
Simon, L., Teboul, O., Koutsourakis, P., Paragios, N.: Random exploration of the procedural space for single-view 3D modeling of buildings. IJCV 93(2) (2011)
Tighe, J., Lazebnik, S.: Understanding scenes on many levels. In: Proc. ICCV, pp. 335–342 (2011)
Tyleček, R.: The CMP facade database. Research Report CTU–CMP–2012–24. Czech Technical University (2012), http://cmp.felk.cvut.cz/~tylecr1/facade
Tyleček, R., Šára, R.: Modeling symmetries for stochastic structural recognition. In: Proc. ICCV Workshops, pp. 632–639 (2011)
Tyleček, R., Šára, R.: Stochastic recognition of regular structures in facade images. IPSJ Trans. Computer Vision and Applications 4, 12–21 (2012)
Yang, M., Förstner, W.: A hierarchical conditional random field model for labeling and classifying images of man-made scenes. In: Proc. ICCV Workshops (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tyleček, R., Šára, R. (2013). Spatial Pattern Templates for Recognition of Objects with Regular Structure. In: Weickert, J., Hein, M., Schiele, B. (eds) Pattern Recognition. GCPR 2013. Lecture Notes in Computer Science, vol 8142. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40602-7_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-40602-7_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40601-0
Online ISBN: 978-3-642-40602-7
eBook Packages: Computer ScienceComputer Science (R0)