Similar articles

Abstract: Omnidirectional imaging sensors have been used in more and more applications when a very large field of view is required. In this paper, we investigate the unwrapping, epipolar geometry and stereo rectification issues for omnidirectional vision when the particular mirror model and the camera parameters are unknown in priori. First, the omnidirectional camera is calibrated under the Taylor model, and the parameters related to this model are obtained. In order to make the classical computer vision algorithms of conventional perspective cameras applicable, the ring omnidirectional image is unwrapped into two kinds of panoramas: cylinder and cuboid. Then the epipolar geometry of arbitrary camera configuration is analyzed and the essential matrix is deduced with its properties being indicated for ring images. After that, a simple stereo rectification method based on the essential matrix and the conformal mapping is proposed. Simulations and real data experimental results illustrate that our methods are effective for the omnidirectional camera under the constraint of a single view point.

[1] Agarwala, A., Agrawala, M., Cohen, M., Salesin, D., Szeliski, R., 2006. Photographing Long Scenes with Multi-viewpoint Panoramas. Proc. SIGGRAPH, p.853-861.

[2] Baker, S., Nayar, S.K., 1999. A theory of single-viewpoint catadioptic image formation. Int. J. Comput. Vis., 35(2):175-196.

[3] Barreto, J.P., Araujo, H., 2005. Geometric properties of central catadioptric line images and their application in calibration. IEEE Trans. Pattern Anal. Mach. Intell., 27(8):1327-1333.

[4] Benosman, R., Kang, S.B., 2001. Panoramic Vision: Sensors, Theory and Applications. Monographs in Computer Science. Springer-Verlag, New York.

[5] Geyer, C., Daniilidis, K., 2001. Catadioptric projective geometry. Int. J. Comput. Vis., 45(3):223-243.

[6] Geyer, C., Daniilidis, K., 2002a. Paracatadioptric camera calibration. IEEE Trans. Pattern Anal. Mach. Intell., 24(5):687-695.

[7] Geyer, C., Daniilidis, K., 2002b. Properties of the Catadioptric Fundamental Matrix. Proc. European Conf. on Computer Vision, p.140-154.

[8] Geyer, C., Daniilidis, K., 2003a. Conformal Rectification of Omnidirectional Stereo Pairs. Computer Vision and Pattern Recognition Workshop, 7:73-78.

[9] Geyer, C., Daniilidis, K., 2003b. Mirror in Motion: Epipolar Geometry and Motion Estimation. Proc. Ninth IEEE Int. Conf. on Computer Vision, 2:766-773.

[10] Gluckman, J.M., Nayar, S.K., 2000. Rectified Catadioptric Stereo Sensors. IEEE Conf. on Computer Vision and Pattern Recognition, 2:224-236.

[11] Gluckman, J.M., Thoresz, K., Nayar, S.K., 1998. Real Time Panorama Stereo. DARPA Image Understanding Workshop, p.299-303.

[12] Hartley, R., Zisserman, A., 2000. Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge, UK.

[13] Kang, S.B., 2000. Catadioptric Self-calibration. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 1:201-207.

[14] Lin, S.S., Bajcsy, R., 2003. High Resolution Catadioptric Omni-directional Stereo Sensor for Robot Vision. IEEE Int. Conf. on Robotics and Automation, p.1694-1699.

[15] Lin, S.S., Bajcsy, R., 2006. Single-view-point omnidirectional catadioptric cone mirror imager. IEEE Trans. Pattern Anal. Mach. Intell., 28(5):840-845.

[16] Lockwood, E.H., 1967. A Book of Curves. Cambridge University Press, Cambridge, England, p.186-190.

[17] Ma, Y., Soatto, S., Kosecka, J., Sastry, S.S., 2003. An Invitation to 3-D Vision: From Images to Geometric Models. Springer-Verlag, New York, USA.

[18] McMillan, L., Bishop, G., 1995. Plenoptic Modeling: An Image-based Rendering System. Proc. SIGGRAPH, p.39-46.

[19] Mei, C., Rives, P., 2007. Single View Point Omnidirectional Camera Calibration from Planar Grids. Proc. IEEE Int. Conf. on Robotics and Automation, p.3945-3950.

[20] Micusik, B., 2004. Two-view Geometry of Omnidirectional Cameras. PhD Thesis, Czech Technical University, Prague, Czech Republic.

[21] Scaramuzza, D., Martinelli, A., Siegwart, R., 2006. A Toolbox for Easy Calibrating Omnidirectional Cameras. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, p.5695-5701.

[22] Scharstein, D., Szeliski, R., 2002. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis., 47:7-42.

[23] Shum, H.Y., He, L.W., 1999. Rendering with Concentric Mosaics. Proc. SIGGRAPH, p.299-306.

[24] Shum, H.Y., Szeliski, R., 1995. Stereo Reconstruction from Multiperspective Panoramas. Proc. Int. Conf. on Computer Vision, p.14-21.

[25] Spacek, L., 2005. A catadioptric sensor with multiple viewpoints. Rob. Auton. Syst., 51(1):3-15.

[26] Svoboda, T., Pajdla, T., 2002. Epipolar gometry for central catadioptric cameras. Int. J. Comput. Vis., 49(1):23-37.

[27] Yagi, Y., Nishii, W., Yamazawa, K., Yachida, M., 1996. Rolling Motion Estimation for Mobile Robot by Using Omnidirectional Image Sensor HyperOmniVision. Proc. 13th Int. Conf. on Pattern Recognition, 1:946-950.

[28] Yamazawa, K., Yagi, Y., Yachida, M., 1993. Omnidirectional Imaging with Hyperboloidal Projection. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, 2:1029-1034.

[29] Ying, X.H., Hu, Z.Y., 2004. Catadioptric camera calibration using geometric invariants. IEEE Trans. Pattern Anal. Mach. Intell., 26(10):1260-1271.

[30] Ying, X.H., Zha, H.B., 2008. Identical projective geometric properties of central catadioptric line images and sphere images with applications to calibration. Int. J. Comput. Vis., 78(1):89-105.