Large-baseline matching and reconstruction from symmetry cells

In this paper, we study how the presence of symmetry in man-made environments may significantly facilitate the task of automatic matching features and recovering 3-D camera pose and scene structure from multiple perspective images. While conventional methods typically rely on small-motion tracking or robust statistic techniques to resolve the coupling between feature matching and 3-D recovery, we here propose a new symmetry-based approach which allows automatic feature matching between images taken with arbitrary (both large and small) camera motions. To this end, we develop the multiple-view geometry of symmetry cells. To resolve possible ambiguities that may arise in matching symmetry cells and camera pose recovery, we find a consistent solution by finding the maximal complete subgraph of a matching graph; we also use a topological check to avoid mismatches. As our experiments shows, the resulting algorithms are simple, accurate and easy to implement.

[1]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[2]  Ian D. Reid,et al.  Single View Metrology , 2000, International Journal of Computer Vision.

[3]  Yutaka Fukui,et al.  3-D Reconstruction Using Mirror Images Based on a Plane Symmetry Recovering Method , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  David A. Forsyth,et al.  Extracting projective structure from single perspective views of 3D point sets , 1993, 1993 (4th) International Conference on Computer Vision.

[5]  Gérard G. Medioni,et al.  Reconstructing mirror symmetric scenes from a single view using 2-view stereo geometry , 2002, Object recognition supported by user interaction for service robots.

[6]  Allen Y. Yang,et al.  Geometric segmentation of perspective images based on symmetry groups , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  C. Bron,et al.  Algorithm 457: finding all cliques of an undirected graph , 1973 .

[8]  Hans Knutsson,et al.  Detecting rotational symmetries using normalized convolution , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[9]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[10]  Jana Kosecka,et al.  Qualitative image based localization in indoors environments , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[11]  Rachid Deriche,et al.  A Robust Technique for Matching two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry , 1995, Artif. Intell..

[12]  Luc Van Gool,et al.  Wide-baseline multiple-view correspondences , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[13]  Daphna Weinshall,et al.  Using Bilateral Symmetry to Improve 3D Reconstruction from Image Sequences , 1997, Comput. Vis. Image Underst..

[14]  Hagit Hel-Or,et al.  Symmetry as a Continuous Feature , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Luc Van Gool,et al.  Mirror and point symmetry under perspective skewing , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Allen Y. Yang,et al.  On Symmetry and Multiple-View Geometry: Structure, Pose, and Calibration from a Single Image , 2004, International Journal of Computer Vision.

[17]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[18]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Stefan Carlsson,et al.  Symmetry in Perspective , 1998, ECCV.

[20]  Stefan Carlsson,et al.  Calibration, pose and novel views from single images of constrained scenes , 2000, Pattern Recognit. Lett..

[21]  Yanxi Liu,et al.  A Group Theoretic Formalization of Surface Contact , 1994, Int. J. Robotics Res..

[22]  Allen Y. Yang,et al.  Structure and pose from single images of symmetric objects with applications to robot navigation , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).