Probabilistic Modeling of Real-world Scenes in a Virtual Environment

Frank Dittrich, Stephan Irgenfried, Heinz Woern

Abstract

In this paper we present an approach for the automated creation of real-world scenes in an virtual environment. Here we focus on human-robot interaction and collaboration in the industrial domain, with corresponding virtual object classes and inter-class constellations. As the basis for the sample generation process, we probabilistically model essential discrete and continuous object parameters, by adapting a generic mixed joint density function to distinct scene classes, in order to capture the specific inter- and intra-class dependencies. To provide a convenient way to assert these object interactions, we use a Bayesian Network for the representation of the density function, where dependencies can directly be modeled by the network layout. For the conditioned and uncertain descriptions of object translations, we use hierarchical Gaussian Mixture Models as geometrical sampling primitives in the 3D space. In our paper, we show how the combination of a Bayesian Network with these sampling primitives can directly be used for the automated collision avoidance of objects, during the sampling process. For the illustration of the applicability and usefulness of our approach, we instantiate the generic and abstract concept using an example with reduced complexity.

References

  1. E. Rohmer, S. P. N. Singh, M. F. (2013). V-rep: a versatile and scalable robot simulation framework. In Proc. of The International Conference on Intelligent Robots and Systems (IROS).
  2. Frasch, J. V., Lodwich, A., Shafait, F., and Breuel, T. M. (2011). A bayes-true data generator for evaluation of supervised and unsupervised learning methods. Pattern Recognition Letters, 32(11):1523-1531.
  3. Geiger, A., Lenz, P., and Urtasun, R. (2012). Are we ready for autonomous driving? the kitti vision benchmark suite. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 3354- 3361.
  4. Haltakov, V., Unger, C., and Ilic, S. (2013). Framework for generation of synthetic ground truth data for driver assistance applications. In German Association for Pattern Recognition, editor, Proc. of the 35th German Conference on Pattern Recognition GCPR 2013.
  5. Jie, Y., Farin, D., Krueger, C., and Schiele, B. (2010). Improving person detection using synthetic training data. In Image Processing (ICIP), 2010 17th IEEE International Conference on, pages 3477-3480.
  6. Koller, D. and Friedman, N. (2009). Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning. The MIT Press.
  7. Kondermann, D. (2013). Ground truth design principles. In Spampinato, C., Boom, B., and Huet, B., editors, VIGTA 7813 Proceedings of the International Workshop on Video and Image Ground Truth in Computer Vision Applications, pages 1-4. ACM Press.
  8. Martin, D., Fowlkes, C. C., Tal, D., and Malik, J. (2001). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on, volume 2, pages 416-423.
  9. Meister, S., Jähne, B., and Kondermann, D. (2012). Outdoor stereo camera system for the generation of realworld benchmark data sets. Optical Engineering, 51(02):021107.
  10. Meister, S. and Kondermann, D. (2011). Real versus realistically rendered scenes for optical flow evaluation. In Electronic Media Technology (CEMT), 2011 14th ITG Conference on, pages 1-6.
  11. Neumann-Cosel, K. v., Roth, E., Lehmann, D., Speth, J., and Knoll, A. (2009). Testing of image processing algorithms on synthetic data. In Software Engineering Advances, 2009. ICSEA 7809. Fourth International Conference on, pages 169-172.
  12. Press, W. H., Teukolsky, S. A., Vetterling, W. T., and Flannery, B. P. (2007). Numerical Recipes 3rd Edition: The Art of Scientific Computing. Cambridge University Press.
  13. Rachkovskij, D. A. and Kussul, E. M. (1998). Datagen: a generator of datasets for evaluation of classification algorithms. Pattern Recognition Letters, 19(7):537- 544.
  14. Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., and Blake, A. (2011). Real-time human pose recognition in parts from single depth images. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on.
  15. Utasi, Í . and Benedek, C. (2012). A multi-view annotation tool for people detection evaluation. In Spampinato, C., editor, Proceedings of the 1st International Workshop on Visual Interfaces for Ground Truth Collection in Computer Vision Applications, pages 1-6, New York and NY. ACM.
Download


Paper Citation


in Harvard Style

Dittrich F., Irgenfried S. and Woern H. (2015). Probabilistic Modeling of Real-world Scenes in a Virtual Environment . In Proceedings of the 10th International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2015) ISBN 978-989-758-087-1, pages 165-173. DOI: 10.5220/0005313301650173


in Bibtex Style

@conference{grapp15,
author={Frank Dittrich and Stephan Irgenfried and Heinz Woern},
title={Probabilistic Modeling of Real-world Scenes in a Virtual Environment},
booktitle={Proceedings of the 10th International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2015)},
year={2015},
pages={165-173},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005313301650173},
isbn={978-989-758-087-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Graphics Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2015)
TI - Probabilistic Modeling of Real-world Scenes in a Virtual Environment
SN - 978-989-758-087-1
AU - Dittrich F.
AU - Irgenfried S.
AU - Woern H.
PY - 2015
SP - 165
EP - 173
DO - 10.5220/0005313301650173