View Synthesis for Virtual Walk through in Real Scene Based on Catadioptric Omnidirectional Images

This paper proposes an approach to more conveniently and efficiently create virtual walk through in real scene from catadioptric omni directional images via view synthesis. Acquisition and unwarping process of omnidirectional image are discussed firstly, then, according to the speciality of cylindrical panoramic image, we utilize the advantage of epiline-sampling method for cylindrical image, which samples reference images along epilines as much as possible grounding on epipolar geometry. As to novel view generation after image rectification, a corresponding interpolation algorithm based on rectified images is developed. Results of proposed approach applied to both synthetic and real scene are given at the end of this paper. Experiments show that our method can reduce distortion and pixel information losing from image rectification obviously meanwhile maintain scene information well.

[1]  Kostas Daniilidis,et al.  Conformal Rectification of Omnidirectional Stereo Pairs , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[2]  Ryad Benosman,et al.  Hybrid Stereo Configurations Through a Cylindrical Sensor Calibration , 2006, Machine Vision and Applications.

[3]  Ben J. A. Kröse,et al.  3D scene reconstruction from cylindrical panoramic images , 2002, Robotics Auton. Syst..

[4]  Liu Shao-hua.  Reduce Look-up Table Space in Panorama Unrolling of Catadioptric Omni-directional Images by Eight Direction Symmetry Reuse Strategy , 2007 .

[5]  Leonard McMillan,et al.  Plenoptic modeling: an image-based rendering system , 1995, SIGGRAPH.

[6]  Margrit Gelautz,et al.  Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions , 2007, Signal Process. Image Commun..

[7]  Yang Bi-wu.  Minimizing deformation geometric rectification of non-calibration stereovision , 2007 .

[8]  Ben J. A. Kröse,et al.  Range estimation from a pair of omnidirectional images , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[9]  H.-H.P. Wu,et al.  Projective rectification based on relative modification and size extension for stereo image pairs , 2005 .

[10]  Ingemar J. Cox,et al.  Cylindrical rectification to minimize epipolar distortion , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Shree K. Nayar,et al.  Catadioptric omnidirectional camera , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Daniel Oram.  Rectification for any epipolar geometry , 2001, BMVC.

[13]  Hideo Saito,et al.  3D Reconstruction Based on Epipolar Geometry , 2000, MVA.

[14]  Tomas Pajdla,et al.  3D Metric Reconstruction from Uncalibrated Omnidirectional Images , 2004 .

[15]  Lei Lei,et al.  A Deformation-minimized Reprojection Method Based on Generalized Planar Rectification , 2006, 2006 8th international Conference on Signal Processing.

[16]  Yi Deng,et al.  Stereo Correspondence with Occlusion Handling in a Symmetric Patch-Based Graph-Cuts Model , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Kostas Daniilidis,et al.  Mirrors in motion: epipolar geometry and motion estimation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[18]  Simon Lacroix,et al.  Fast Dense Panoramic Stereovision , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.