Monocular 3D Pose Tracking of a Specular Object

Nassir W. Oumer

Abstract

A space object such as a satellite consists of highly specular surface, and when exposed to directional source of light, it is very difficult for visual tracking. However, camera-based tracking provides an inexpensive solution to the problem of on-orbit servicing of a satellite, such as orbital-life extension by repairing and refuelling, and debris removal. In this paper we present a real time pose tracking method applied to a such object under direct Sunlight, by adapting keypoint and edge-based approach, with known simple geometry. The implemented algorithm is relatively accurate and robust to specular reflection. We show the results which are based on real images from a simulation system of on-orbit servicing, consisting of two six degree of freedom robots, the Sun simulator and a full scale satellite mock-up.

References

  1. Oren Michael and Nayar Shree K. (1995). A Theory of Specular Surface Geometry. In IJCV'95, International Journal of Computer vision, volume 24, page. 740- 747.
  2. Lagger Pascal, Salzmann Mathieu, Lepetit Vincet and Fua pascal (2008). 3D Pose Refinement from Reflections. In CVPR'08, IEEE Conference on Computer vision ans Pattern Recognition, pages 1-8, Anchorage, AK.
  3. Yu Tianli, Xu Ning and Ahuja Narendra, (2004). Recovering Shape and Reflectance Model of Non-lambertian Objects from Multiple Views. In CVPR'04, Proceedings of IEEE Computer Sosciety Conference on Computer vision ans Pattern Recognition, volume 2, pages II-226 - II-233.
  4. Roth Stefan and Black Michael J., (2006). Specular Flow and the Recovery of Surface Structure. In CVPR'06, Proceedings of IEEE Computer Sosciety Conference on Computer vision and Pattern Recognition, volume 2.
  5. Vasilyev Yuriy, Adato Yair, Zickler Todd and Ben-Shahar Ohad, (2008). Dense Specular Shape from Multiple Specular Flows. In CVPR'08, Proceedings of IEEE Computer Sosciety Conference on Computer vision ans Pattern Recognition.
  6. Adato Yair, zickeler Todd and Benn-Shahr Ohad, (2010) Toward robust Estimation of Specular Flow. In BMVC'10, Proceedings of the British Machine Vision Conference, pages 22.1-22.11.
  7. Gouiffès Michèle, Collewet Christophe, FernandezMaloigne Christine, Trémeau Alain, (2006) Feature Points Tracking: Robustness to Specular Highlights and Lighting Changes. In ECCV'06, 9th European Conference on Computer Vision, volume 4. pages 82-93.
  8. Shi Jianbo and Tomasi Carlo, (1994) Good Features to Track. In CVPR'94, IEEE Computer Soc. Conference Computer Vision and Pattern Recognition, pages 593- 600.
  9. Chang Ju Yong, Raskar Ramesh and Agrawal Amit K., (2009) 3D Pose Estimation and Segmentation using Specular Cues. In CVPR'09, IEEE Computer Soc. Conference Computer Vision and Pattern Recognition, pages 1706-1713.
  10. Vacchetti Luca, Lepetit Vincent, Fua Pascal, (2004) Combining Edge and Texture Information for Real-Time Accurate 3D Camera Tracking. In ISMAR 7804, Proceedings of the 3rd IEEE/ACM International Symposium on Mixed and Augmented Reality Pages 48-57.
  11. Kyrki Ville, Kragic Danica (2005) Integration of modelbased and model-free cues for visual object tracking. In ICRA05, Proc. of the IEEE Int. Conf on Robotics and Automation, pages 1554-1560.
  12. Pressigout Muriel and Marchand Eric, (2007) Real-time Hybrid Tracking using Edge and Texture Information. In Proc. of International Journal of Robotics Research, volume 26, no.7, pages 689-713.
  13. Drummond Tom and Cipolla Robert, (2002) Real-time visual tracking of complex structures. In PAMI'02 Proc. of IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 27, issue 7, pages 932 - 946 .
  14. Comport A.I. and Marchand Eric, (2004) Robust modelbased tracking for robot vision. In IROS'04 Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, volume 1, pages 692 - 697.
  15. Comport Andrew.I., Kragic Danica, Marchand Eric and Chaumette Francois, (2005) Robust Real-Time Visual Tracking: Comparison, Theoretical Analysis and Performance Evaluation. In ICRA'05 Proc. IEEE International Conference on Robotics and Automation, pages 2841 - 2846.
  16. Comport Andrew I., Marchand Eric and Chaumette Francois, (2006) Statistically Robust 2D Visual Servoing. In IEEE Transactions on Robotics volume 22, no.2, pages 415-421.
  17. Drummond Tom and Cipolla Robert, (1999) Visual Tracking and Control using Lie Algebras. In CVPR'99, IEEE Computer Society, Computer Vision and Pattern Recognition, volume 2, pages 2652-2659.
Download


Paper Citation


in Harvard Style

Oumer N. (2014). Monocular 3D Pose Tracking of a Specular Object . 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 458-465. DOI: 10.5220/0004667304580465


in Bibtex Style

@conference{visapp14,
author={Nassir W. Oumer},
title={Monocular 3D Pose Tracking of a Specular Object},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={458-465},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004667304580465},
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 - Monocular 3D Pose Tracking of a Specular Object
SN - 978-989-758-009-3
AU - Oumer N.
PY - 2014
SP - 458
EP - 465
DO - 10.5220/0004667304580465