Hide and Seek - An Active Binocular Object Tracking System

Pramod Chandrashekhariah, Jochen Triesch

2014

Abstract

We introduce a novel active stereo vison-based object tracking system for a humanoid robot. The system tracks a moving object that is dynamically changing its appearance and scale. The system features an inbuilt learning process that simultaneously learns short term models for the object and potential distractors. These models evolve over time, rectifying the inaccuracies of the tracking in a cluttered scene and allowing the system to identify unusual events such as sudden displacement, hiding behind or being masked by an occluder, and sudden disappearance from the scene. The system deals with these through different response modes such as active search when the object is lost, intentional waiting for reappearance when the object is hidden, and reinitialization of the track when the object is suddenly displaced by the user. We demonstrate our system on the iCub robot in an indoor environment and evaluate its performance. Our experiments show a performance enhancement for long occlusions through the learning of distractor models.

References

  1. Chandrashekhariah, P., Spina, G., and Triesch, J. (2013). Let it learn: A curious vision system for autonomous object learning. In VISAPP.
  2. Erdem, C., Sankur, B., and Tekalp, A. (2004). Performance measures for video object segmentation and tracking. Image Processing, IEEE Transactions on, 13(7):937- 951.
  3. Falotico, E. and Laschi, C. (2009). Predictive tracking across occlusions in the icub robot. In Humanoid Robots, 2009, pages 486-491.
  4. Ginhoux, R. and Gutmann, S. (2001). Model-based object tracking using stereo vision. In ICRA, Volume: 2, cole Nationale Suprieure de Physique de.
  5. Kalal, Z., Mikolajczyk, K., and Matas, J. (2012). Trackinglearning-detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 34(7):1409-1422.
  6. Nelson, R. C. and Green, I. A. (2002). Tracking objects using recognition. In In International Conference on Pattern Recogntion, pages 1025-1030. Prentice Hall.
  7. Pattacini, U. (2010). Modular Cartesian Controllers for Humanoid Robots: Design and Implementation on the iCub. Ph.D. dissertation, RBCS, IIT, Genova.
  8. Rosten, E. and Drummond, T. (2006). Machine learning for high-speed corner detection. In ECCV, pages 430- 443.
  9. Ta, D., Chen, W., Gelfand, N., and Pulli, K. (2009). Surftrac: Efficient tracking and continuous object recognition using local feature descriptors. In CVPR09.
  10. Triesch, J., Ballard, D. H., and Jacobs, R. A. (2002). Fast temporal dynamics of visual cue integration. Perception, 31(4):421-434.
  11. Wiskott, L., Fellous, J., Krüger, N., and v.d. Malsburg, C. (1997). Face recognition by elastic bunch graph matching. IEEE Trans. Pattern Anal. Mach. Intell.
  12. Yin, F., Makris, D., and Velastin, S. A. (2007). Performance Evaluation of Object Tracking Algorithms. In PETS2007.
Download


Paper Citation


in Harvard Style

Chandrashekhariah P. and Triesch J. (2014). Hide and Seek - An Active Binocular Object Tracking System . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 584-591. DOI: 10.5220/0004690705840591


in Bibtex Style

@conference{visapp14,
author={Pramod Chandrashekhariah and Jochen Triesch},
title={Hide and Seek - An Active Binocular Object Tracking System},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={584-591},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004690705840591},
isbn={978-989-758-009-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - Hide and Seek - An Active Binocular Object Tracking System
SN - 978-989-758-009-3
AU - Chandrashekhariah P.
AU - Triesch J.
PY - 2014
SP - 584
EP - 591
DO - 10.5220/0004690705840591