A THREE-LEVEL ARCHITECTURE FOR MODEL–FREE DETECTION AND TRACKING OF INDEPENDENTLY MOVING OBJECTS

Nicolas Pugeault, Karl Pauwels, Mark M. Van Hulle, Florian Pilz, Norbert Krüger

Abstract

We present a three–level architecture for detection and tracking of independently moving objects (IMOs) in sequences recorded from a moving vehicle. At the first stage, image pixels with an optical flow that is not entirely induced by the car’s motion are detected by combining dense optical flow, egomotion extracted from this optical flow, and dense stereo. These pixels are segmented and an attention mechanism is used to process them at finer resolution at the second level making use of sparse 2D and 3D edge descriptors. Based on the rich and precise information on the second level, the full rigid motion for the environment and for each IMO is computed. This motion information is then used for tracking, filtering and the building of a 3D model of the street structure as well as the IMO. This multi-level architecture allows us to combine the strength of both dense and sparse processing methods in terms of precision and computational complexity, and to dedicate more processing capacity to the important parts of the scene (the IMOs).

References

  1. Bar-Shalom, Y. (1978). Tracking methods in multitarget environment. IEEE trans. on Automatic Control, AC23:618-626.
  2. Bertozzi, M. and Broggi, A. (1998). Gold: A parallel realtime stereo vision system for generic obstacle and lane detection. IEEE TIP, 7(1):62-81.
  3. Betke, M., Haritaoglu, E., and Davis, L. S. (2000). Realtime multiple vehicle detection and tracking from a moving vehicle. Machine Vision and Applications, 12:69-83.
  4. Caputo, G. and Lombardi, L. (1995). Attention mechanisms in computer vision systems. Int. Workshop on Computer Architectures for Machine Perception.
  5. Comaniciu, D., Ramesh, V., and Meer, P. (2003). Kernelbased object tracking. IEEE TPAMI, 25(5):564-577.
  6. Cox, I. J. (1992). A review of statistical data association techniques for motion correspondence. IJCV, 10(1):53-66.
  7. Dissanayake, P., Newman, P., Durrant-Whyte, H., Clark, S., and Csorba, M. (2001). A solution to the simultaneous localisation and mapping (SLAM) problem. IEEE trans. in Robotics and Automation, 17(3):229-241.
  8. Fawcett, T. (2006). An introduction to ROC analysis. Pattern recognition letters, 27(8):861-874.
  9. Fischler, R. and Bolles, M. (1981). Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. of the ACM, 24(6):619-638.
  10. Hoiem, D., Efros, A. A., and Hebert, M. (2007). Recovering surface layout from an image. IJCV, 75(1):151-172.
  11. Hoiem, D., Efros, A. A., and Hebert, M. (2008). Putting objects in perspective. IJCV, 80(1):3-15.
  12. Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Jour. of Basic Engineering, 82-D:35-45.
  13. Krüger, N., Lappe, M., and Wörgötter, F. (2004). Biologically motivated multi-modal processing of visual primitives. AISB Jour., 1(5):417-427.
  14. Leibe, B., Schindler, K., Cornelis, N., and van Gool, L. (2008). Coupled object detection and tracking from static cameras and moving vehicles. IEEE TPAMI, 30(10):1683-1698.
  15. Lourakis, M., Argyros, A., and Orphanoudakis, S. (1998). Independent 3d motion detection using residual parallax normal flow fields. In ICCV, pages 1012-1017.
  16. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. IJCV, 1(1).
  17. Montemerlo, M., Thrun, S., Koller, D., and Wegbreit, B. (2002). Fastslam: A factored solution to the simultaneous localization and mapping problem. In AAAI.
  18. Pauwels, K. and Van Hulle, M. (2006). Optimal instantaneous rigid motion estimation insensitive to local minima. CVIU, 104(1):77-86.
  19. Pauwels, K. and Van Hulle, M. (2008). Realtime phasebased optical flow on the gpu. In CVPR Workshop on Computer Vision on the GPU.
  20. Pauwels, K. and Van Hulle, M. (2009). Optic flow from unstable sequences through local velocity constancy maximization. IVC, 27(5):579-587.
  21. Pilz, F., Pugeault, N., and Krüger, N. (2009). Comparison of point and line features and their combination for rigid body motion estimation. Visual Motion Analysis, Springer LNCS 5604.
  22. Pugeault, N. (2008). Early Cognitive Vision: Feedback Mechanisms for the Disambiguation of Early Visual Representation. VDM Verlag Dr. Müller.
  23. Reid, D. B. (1979). An algorithm for tracking multiple targets. IEEE trans. on Automatic Control, AC-24(6).
  24. Rosenhahn, B., Krüger, N., Rabsch, T., and Sommer, G. (2001). Automatic tracking with a novel pose estimation algorithm. Robot Vision.
  25. Rushton, S., Bradshaw, M., and Warren, P. (2007). The pop out of scene-relative object movement against retinal motion due to self-movement. Cognition, 105(1):237- 245.
  26. Sabatini, S., Gastaldi, G., Solari, F., Pauwels, K., Van Hulle, M., Diaz, J., Ros, E., Pugeault, N., and Krueger, N. (2007). Compact (and accurate) early vision processing in the harmonic space. In VISAPP, pages 213-220.
  27. Sawhney, H., Guo, Y., and Kumar, R. (2000). Independent motion detection in 3d scenes. IEEE TPAMI, 22(10).
  28. Thompson, W. B. and Pong, T. C. (1990). moving-objects. IJCV, 4:39-57.
  29. Thrun, S., Liu, Y., Koller, D., Ng, A., Ghahramani, Z., and Durrant-Whyte, H. (2004). Simultaneous Localization and Mapping with Sparse Extended Information Filters. IJRR, 23(7-8):693-716.
Download


Paper Citation


in Harvard Style

Pugeault N., Pauwels K., M. Van Hulle M., Pilz F. and Krüger N. (2010). A THREE-LEVEL ARCHITECTURE FOR MODEL–FREE DETECTION AND TRACKING OF INDEPENDENTLY MOVING OBJECTS . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 237-244. DOI: 10.5220/0002838002370244


in Bibtex Style

@conference{visapp10,
author={Nicolas Pugeault and Karl Pauwels and Mark M. Van Hulle and Florian Pilz and Norbert Krüger},
title={A THREE-LEVEL ARCHITECTURE FOR MODEL–FREE DETECTION AND TRACKING OF INDEPENDENTLY MOVING OBJECTS},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={237-244},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002838002370244},
isbn={978-989-674-028-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - A THREE-LEVEL ARCHITECTURE FOR MODEL–FREE DETECTION AND TRACKING OF INDEPENDENTLY MOVING OBJECTS
SN - 978-989-674-028-3
AU - Pugeault N.
AU - Pauwels K.
AU - M. Van Hulle M.
AU - Pilz F.
AU - Krüger N.
PY - 2010
SP - 237
EP - 244
DO - 10.5220/0002838002370244