Single Camera Stereo with Planar Mirrors

Article Preview

Abstract:

This paper presents a new system for rapidly acquiring stereo images using a single camera and a pair of planar mirrors (catadioptric stereo). Firstly, the camera used to capture images is calibrated with matlab toolbox. Secondly, the position and pose of the planar mirrors relative to the fixed, calibrated camera is estimated, and this procedure is accomplished by calculating the symmetry plane of the real and reflected image corners of a chessboard. Thirdly, the relative orientation of two reflected virtual cameras is obtained. Finally, Gaussian noise is added to the image corners of the chessboard to verify the performance of the established stereo system. Experimental results show the effectiveness and robustness of our system.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

447-450

Citation:

Online since:

April 2013

Authors:

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] A. Goshtasby, W. A. Gruver: Design of a single-lens stereo camera system. Pattern Recognition 26 (1993) 923-936.

DOI: 10.1016/0031-3203(93)90058-5

Google Scholar

[2] J. Gluckman, S. K. Nayar: Catadioptric stereo using planar mirrors, International Journal of Computer Vision 44(1) (2001) 65-79.

Google Scholar

[3] H. Mitsumoto, S. Tamura, K. Okazaki, N. Kajimi, Y. Fukui: 3D reconstruction using mirror images based on a plane symmetry recovery method, IEEE Transactions on Pattern Analysis and Machine Intelligence 14(9) (1992)941-945.

DOI: 10.1109/34.161352

Google Scholar

[4] M. Inaba, T. Hara, H. Inoue: A stereo viewer based on a single camera with view-control mechanism, Proceedings of International Conference on Robots and Systems, vol. 3, 1993, pp.26-30.

DOI: 10.1109/iros.1993.583888

Google Scholar

[5] Zhengyou Zhang: A flexible new technique for camera calibration, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(11): 1330-1334, (2002).

DOI: 10.1109/34.888718

Google Scholar

[6] Information on http: /www. vision. caltech. edu/bouguetj/calib_doc.

Google Scholar