BAYESIAN SCENE SEGMENTATION INCORPORATING MOTION CONSTRAINTS AND CATEGORY-SPECIFIC INFORMATION

Alexander Bachmann, Irina Lulcheva

Abstract

In this paper we address the problem of detecting objects form a moving camera by jointly considering lowlevel image features and high-level object information. The proposed method partitions an image sequence into independently moving regions with similar 3-dimensional (3D) motion and distance to the observer. In the recognition stage category-specific information is integrated into the partitioning process. An object category is represented by a set of descriptors expressing the local appearance of salient object parts. To account for the geometric relationships among object parts a structural prior over part configurations is designed. This prior structure expresses the spatial dependencies of object parts observed in a training data set. To achieve global consistency in the recognition process, information about the scene is extracted from the entire image based on a set of global image features. These features are used to predict the scene context of the image from which characteristic spatial distributions and properties of an object category are derived. The scene context helps to resolve local ambiguities and achieves locally and globally consistent image segmentation. Our expectations on spatial continuity of objects are expressed in a Markov Random Field (MRF) model. Segmentation results are presented based on real image sequences.

References

  1. Bachmann, A. and Balthasar, M. (2008). Context-aware object priors. In IEEE IROS 2008; Workshop on Planning, Perception and Navigation for Intelligent Vehicles (PPNIV), Nice, France.
  2. Bachmann, A. and Dang, T. (2008). Improving motionbased object detection by incorporating objectspecific knowledge. International Journal of Intelligent Information and Database Systems (IJIIDS), 2(2):258-276.
  3. Besag, J. (1974). Spatial interaction and the statistical analysis of lattice systems. Journal of the Royal Statistical Society, Series B 36(2):192-236.
  4. Burl, M. C., Weber, M., and Perona, P. (1998). A probabilistic approach to object recognition using local photometry and global geometry. Lecture Notes in Computer Science, 1407:628ff.
  5. Crandall, D. and Huttenlocher, D. (2007). Composite models of objects and scenes for category recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition CVPR 7807, pages 1-8.
  6. Dang, T., Hoffmann, C., and Stiller, C. (2006). Selfcalibration for active automotive stereo vision. In Proceedings of the IEEE Intelligent Vehicles Symposium, Tokyo.
  7. Duchow, C., Hummel, B., Bachmann, A., Yang, Z., and Stiller, C. (2006). Akquisition, Repraesentation und Nutzung von Wissen in der Fahrerassistenz. In Informationsfusion in der Mess- und Regelungstechnik 2006, VDI/VDE-GMA. Eisenach, Germany.
  8. Fischler, M. and Elschlager, R. (1973). The representation and matching of pictorial structures. IEEE Trans. Comput., 22(1):67-92.
  9. Geman, S. and Geman, D. (1984). Stochstic relaxation, Gibbs distribution, and the Bayesian restoration of images. In IEEE Transaction on Pattern Analysis and Machine Intelligence, volume 6, pages 721-741.
  10. Harris, C. and Stephens, M. (1988). A combined corner and edge detector. In Fourth Alvey Vision Conference, Manchester, pages 147-151.
  11. He, X. and Yung, N. (2004). Curvature scale space corner detector with adaptive threshold and dynamic region of support. In 17th International Conference on Pattern Recognition, volume 2, pages 791-794, Washington, DC, USA. IEEE Computer Society.
  12. Ohm, J.-R. and Ma, P. (1997). Feature-Based cluster segmentation of image sequences. In ICIP 7897-Volume 3, pages 178-181, Washington, DC, USA. IEEE Computer Society.
  13. Rentschler, I., Juettner, M., Osmana, E., Mueller, A., and Caell, T. (2004). Development of configural 3D object recognition. Elsevier - Behavioural Brain Research, 149(149):107-111.
  14. Rockwell, T. (1972). Skills, judgment, and information acquisition in driving. Human Factors in Highway Traffic Safety Research, pages 133-164.
  15. Sivak, M. (1996). The information that drivers use: is it indeed 90% visual? Perception, 25(9):1081-1089.
Download


Paper Citation


in Harvard Style

Bachmann A. and Lulcheva I. (2009). BAYESIAN SCENE SEGMENTATION INCORPORATING MOTION CONSTRAINTS AND CATEGORY-SPECIFIC INFORMATION . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 291-298. DOI: 10.5220/0001653302910298


in Bibtex Style

@conference{visapp09,
author={Alexander Bachmann and Irina Lulcheva},
title={BAYESIAN SCENE SEGMENTATION INCORPORATING MOTION CONSTRAINTS AND CATEGORY-SPECIFIC INFORMATION},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={291-298},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001653302910298},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - BAYESIAN SCENE SEGMENTATION INCORPORATING MOTION CONSTRAINTS AND CATEGORY-SPECIFIC INFORMATION
SN - 978-989-8111-69-2
AU - Bachmann A.
AU - Lulcheva I.
PY - 2009
SP - 291
EP - 298
DO - 10.5220/0001653302910298