Abstract
We present a method to obtain dense 3D maps for a mobile robot that is equipped with a novel omnidirectional stereo vision sensor. The vision sensor is composed of a perspective camera and two hyperbolic mirrors. Once the system has been calibrated and two image points respectively projected by upper and nether mirrors are matched, the 3D coordinate of the space point can be acquired by means of triangulation. To satisfy the reliability requirement by mobile robot navigation, we use high-quality stereo matching algorithm – the graph cut method. An initial depth map can be calculated using efficient dynamic programming technique. With a relatively good initial map, the process of graph cut converges quickly. We also show the necessary modification to handle panoramic images, including deformed matching template, adaptable template scale. Experiment shows that this proposed vision system is feasible as a practical stereo sensor for accurate 3D map generation.
This work is supported by National Science Foundation of P.R. China under granted number 60575024.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Nayar, S.K.: Catadioptric Omnidirectional Camera. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 482–488. IEEE Computer Society Press, Los Alamitos (1997)
Gluckman, J., Nayar, S.K., Thoresz, K.J.: Real-time Omnidirectional and Panoramic Stereo. In: Proc. DARPA Image Understanding Workshop, pp. 299–303 (1998)
Koyasu, H., Miura, J., Shirai, Y.: Recognizing Moving Obstacles for Robot Navigation Using Real-time Omnidirectional Stereo Vision. Journal of Robotics and Mechatronics 14(2), 147–156 (2002)
Southwell, M.F.D., Basu, A., Reyda, J.: Panoramic Stereo. In: Proc. International Conf. on Pattern Recognition, pp. 378–382 (1996)
Conroy, T.L., Moore, J.B.: Resolution Invariant Surfaces for Panoramic Vision Systems. In: Proc. IEEE International Conf. on Computer Vision, pp. 392–397. IEEE Computer Society Press, Los Alamitos (1999)
Eduardo, L., Cabral José, L., de C. Jr., S., Marcos, C.H.: Omnidirectional Stereo Vision with a Hyperbolic Double Lobed Mirror. In: Proc. International Conf. on Pattern Recognition, pp. 1–4 (2004)
Devernay, F., Faugeras, O.: Computing Differential Properties of 3-D Shapes from Stereoscopic Images without 3-D Models. In: Proc. CVPR, pp. 208–213 (1994)
Sara, R.: Finding the Largest Unambiguous Component of Stereo Matching. In: Proc. 7th European Conf. on Computer Vision, vol. 2, pp. 900–914 (2002)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient Belief Propagation for Early Vision. International Journal of Computer Vision 70(1) (2006)
Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusion using graph cuts. In: International Conference on Computer Vision (2001)
Luo, C., Su, L., Zhu, F., Shi, Z.: A Versatile Method for Omnidirectional Stereo Camera Calibration Based on BP Algorithm. In: ISNN 2006, pp. 383–389 (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
He, L., Luo, C., Geng, Y., Zhu, F., Hao, Y. (2007). Reliable Depth Map Regeneration Via a Novel Omnidirectional Stereo Sensor. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2007. Lecture Notes in Computer Science, vol 4841. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76858-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-540-76858-6_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76857-9
Online ISBN: 978-3-540-76858-6
eBook Packages: Computer ScienceComputer Science (R0)