Abstract
In this paper, an original framework for grammar-based image understanding handling uncertainty is presented. The method takes as input an over-segmented image, every segment of which has been annotated during a first stage of image classification. Moreover, we assume that for every segment, the output class may be uncertain and represented by a belief function over all the possible classes. Production rules are also supposed to be provided by experts to define the decomposition of a scene into objects, as well as the decomposition of every object into its components. The originality of our framework is to make it possible to deal with uncertainty in the decomposition, which is particularly useful when the relative frequencies of the production rules cannot be estimated properly. As in traditional visual grammar approaches, the goal is to build the “parse graph” of a test image, which is its hierarchical decomposition from the scene, to objects and parts of objects while taking into account the spatial layout. In this paper, we show that the parse graph of an image can be modelled as an evidential network, and we detail a method to apply a bottom-up inference in this network. A consistency criterion is defined for any parse tree, and the search of the optimal interpretation of an image formulated as an optimization problem. The work was validated on real and publicly available urban driving scene data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Brehar, R., Fortuna, C., Bota, S., Mladenic, D., Nedevschi, S.: Spatio-temporal reasoning for traffic scene understanding. In: Proc. of ICCP, Pittsburgh, pp. 377–384 (2011)
Chomsky, N.: Syntactic Structures. The Hague, Mouton (1957)
Ess, A., Leibe, B., Schindler, K., Gool, L.V.: Moving obstacle detection in highly dynamic scenes. In: Proc. of ICRA, Kobe, pp. 4451–4458 (2009)
Ess, A., Mueller, T., Grabner, H., Van Gool, L.J.: Segmentation-based urban traffic scene understanding. In: Proc. of BMVC, London, pp. 84.1–84.11 (2009)
Gavrila, D.M., Munder, S.: Multi-cue pedestrian detection and tracking from a moving vehicle. IJCV 73(1), 41–59 (2007)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? In: Proc. of CVPR, Providence, USA, pp. 3354–3361 (June 2012)
Julesz, B.: Textons, the elements of texture perception, and their interaction. Nature 290 (1981)
Marszałek, M., Schmid, C.: Semantic hierarchies for visual object recognition. In: Proc. of CVPR, Minneapolis, pp. 1–7 (2007)
Shafer, G.: A mathematical theory of evidence. Princeton University Press (1976)
Wojek, C., Schiele, B.: A dynamic conditional random field model for joint labeling of object and scene classes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 733–747. Springer, Heidelberg (2008)
Xu, P., Davoine, F., Bordes, J.-B., Zhao, H., Denœux, T.: Information fusion on oversegmented images: An application for urban scene understanding. In: Proc. of MVA, Kyoto (2013)
Yao, B., Yang, X., Zhu, S.-C.: Introduction to a large-scale general purpose ground truth database: Methodology, annotation tool and benchmarks. In: Yuille, A.L., Zhu, S.-C., Cremers, D., Wang, Y. (eds.) EMMCVPR 2007. LNCS, vol. 4679, pp. 169–183. Springer, Heidelberg (2007)
Zhu, S.-C., Mumford, D.: A stochastic grammar of images. Found. Trends. Comput. Graph. Vis. 2(4), 259–362 (2006)
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
Bordes, JB., Davoine, F., Xu, P., Denœux, T. (2013). Evidential Grammars for Image Interpretation – Application to Multimodal Traffic Scene Understanding. In: Qin, Z., Huynh, VN. (eds) Integrated Uncertainty in Knowledge Modelling and Decision Making. IUKM 2013. Lecture Notes in Computer Science(), vol 8032. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39515-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-39515-4_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39514-7
Online ISBN: 978-3-642-39515-4
eBook Packages: Computer ScienceComputer Science (R0)