ESTIMATION OF CAMERA 3D-POSITION TO MINIMIZE OCCLUSIONS

Oscar Reinoso

2007

Abstract

Occlusions are almost always seen as undesirable singularities that pose difficult challenges to recognition processes of objects which have to be manipulated by a robot. Often, the occlusions are perceived because the viewpoint with which a scene is observed is not adapted. In this paper, a strategy to determine the location, orientation and position, more suitable so that a camera has the best viewpoint to capture a scene composed by several objects is presented. The estimation for the best location of the camera is based on minimizing the zones of occlusion by the analysis of a virtual image sequence in which is represented the virtual projection of the objects. These virtual projections represent the images as if they were captured by a camera with different viewpoints without moving it.

References

  1. Boshra, M., Ismail, M.A., 2000. Recognition of occluded polyhedra from range images. Pattern Recognition. Vol. 3, No. 8, 1351-1367.
  2. Chan, C.J., Chen S.Y., 2002. Recognition Partially Occluded Objects Using Markov Model. Int. J. Pattern Recognition and Artificial Intelligence. Vol. 16, No. 2, 161-191.
  3. El-Sonbaty, Y., Ismael, M.A, 2003. Matching Occluded Objects Invariant to Rotations, Translations, Reflections, and Scale Changes. Lecture Notes in Computer Science. Vol. 2749, 836-843.
  4. Fiala, M., 2005. Structure From Motion Using SIFT Features and PH Transform with Panoramic Imagery. Second Canadian Conference on Computer and Robot Vision. Victoria, BC, Canada.
  5. Gil, P., Torres, F., Ortiz, F.G., Reinoso, O., 2006. Detection of partial occlusions of assembled components to simplify the disassembly tasks. International Journal of Advanced Manufacturing Technology. No. 30, 530-539.
  6. Gruen, A., Huang, T.S., 2001. Springer Series in Information Sciences. Calibration and Orientation of Cameras in Computer Vision. Springer-Verlag Berling Heidelberg New York.
  7. Hartley, R., Zisserman, A., 2000. Multiple View Geometry in Computer Vision. Cambridge University Press.
  8. Ma, Y., Soato S., Kosecka J., Shankar S., 2004. An Invitation to 3-D Vision from Images to Geometric Models. Springer-Verlag, New York Berlin Heidelberg.
  9. Ohba, K., Sato, Y., Ikeuchi, K., 2000. Appearance-based visual learning and object recognition wirh illumination invariance. Machine Vision and Appplications 12, 189-196.
  10. Ohayon, S., Rivlin, E., 2006. Robust 3D Head Tracking Using Camera Pose Estimation. 18th International Conference on Pattern Recognition. Hong Kong.
  11. Park, B.G., Lee K.Y., Lee S.U., Lee J.H., 2003. Recognition of partially occluded objects using probabilistic ARG (attributed relational graph)-based matching. Computer Vision and Image Understanding 90, 217-241.
  12. Pomares, J., Gil, P., Garcia, G.J., Torres, F., 2006. Visualforce control and structured Light fusion improve object discontinuities recognition. 11th IEEE International Conference on Emerging Technologies and Factory Automation. Praga.
  13. Silva, C., Victor, J.S., 2001. Motion from Occlusions. Robotics and Autonomous Systems 35, 153-162.
  14. Ying, Z., Castañon, D., 2000. Partially Occluded Object Recognition Using Statical Models. Int. J. Computer Vision. Vol. 49, No. 1, 57-78.
  15. Wunsch, P., Winkler S., Hirzinger, G., 1997. Real-Time Pose Estimation of 3-D Objects from Camera Images Using Neural Networks. IEEE International Conference on Robotics and Automation.Albuquerque, New Mexico, USA.
  16. Zhang, Z., 2000. A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 22. No. 11, 1330-1334.
Download


Paper Citation


in Harvard Style

Reinoso O. (2007). ESTIMATION OF CAMERA 3D-POSITION TO MINIMIZE OCCLUSIONS . In Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO, ISBN 978-972-8865-83-2, pages 311-317. DOI: 10.5220/0001646703110317


in Bibtex Style

@conference{icinco07,
author={Oscar Reinoso},
title={ESTIMATION OF CAMERA 3D-POSITION TO MINIMIZE OCCLUSIONS},
booktitle={Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,},
year={2007},
pages={311-317},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001646703110317},
isbn={978-972-8865-83-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,
TI - ESTIMATION OF CAMERA 3D-POSITION TO MINIMIZE OCCLUSIONS
SN - 978-972-8865-83-2
AU - Reinoso O.
PY - 2007
SP - 311
EP - 317
DO - 10.5220/0001646703110317