Globally Optimal 2D-3D Registration from Points or Lines without Correspondences

We present a novel approach to 2D-3D registration from points or lines without correspondences. While there exist established solutions in the case where correspondences are known, there are many situations where it is not possible to reliably extract such correspondences across modalities, thus requiring the use of a correspondence-free registration algorithm. Existing correspondence-free methods rely on local search strategies and consequently have no guarantee of finding the optimal solution. In contrast, we present the first globally optimal approach to 2D-3D registration without correspondences, achieved by a Branch-and-Bound algorithm. Furthermore, a deterministic annealing procedure is proposed to speed up the nested branch-and-bound algorithm used. The theoretical and practical advantages this brings are demonstrated on a range of synthetic and real data where it is observed that the proposed approach is significantly more robust to high proportions of outliers compared to existing approaches.

[1]  Allen R. Hanson,et al.  Robust methods for estimating pose and a sensitivity analysis , 1994 .

[2]  William J. Christmas,et al.  Structural Matching in Computer Vision Using Probabilistic Relaxation , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  J. Beveridge,et al.  Optimal geometric model matching under full 3D perspective , 1995, Proceedings of 1994 IEEE 2nd CAD-Based Vision Workshop.

[4]  David Windridge,et al.  A saliency-based framework for 2D-3D registration , 2014, 2014 International Conference on Computer Vision Theory and Applications (VISAPP).

[5]  Behrooz Kamgar-Parsi,et al.  Matching 2D image lines to 3D models: Two improvements and a new algorithm , 2011, CVPR 2011.

[6]  Vincent Lepetit,et al.  Pose Priors for Simultaneously Solving Alignment and Correspondence , 2008, ECCV.

[7]  Rafael Grompone von Gioi,et al.  LSD: A Fast Line Segment Detector with a False Detection Control , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Kostas Daniilidis,et al.  Linear Pose Estimation from Points or Lines , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Clark F. Olson,et al.  A General Method for Geometric Feature Matching and Model Extraction , 2001, International Journal of Computer Vision.

[10]  V. Lepetit,et al.  EPnP: An Accurate O(n) Solution to the PnP Problem , 2009, International Journal of Computer Vision.

[11]  Jiaolong Yang,et al.  Go-ICP: Solving 3D Registration Efficiently and Globally Optimally , 2013, 2013 IEEE International Conference on Computer Vision.

[12]  Adrian Hilton,et al.  Influence of Colour and Feature Geometry on Multi-modal 3D Point Clouds Data Registration , 2014, 2014 2nd International Conference on 3D Vision.

[13]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[14]  Richard I. Hartley,et al.  Global Optimization through Rotation Space Search , 2009, International Journal of Computer Vision.

[15]  Frédéric Jurie,et al.  Solution of the Simultaneous Pose and Correspondence Problem Using Gaussian Error Model , 1999, Comput. Vis. Image Underst..

[16]  Janne Heikkilä,et al.  Line Matching and Pose Estimation for Unconstrained Model-to-Image Alignment , 2014, 2014 2nd International Conference on 3D Vision.

[17]  Ioannis Stamos,et al.  3-D model construction using range and image data , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

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

[19]  Thomas M. Breuel,et al.  Implementation techniques for geometric branch-and-bound matching methods , 2003, Comput. Vis. Image Underst..

[20]  Philip David,et al.  Simultaneous pose and correspondence determination using line features , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[21]  H Kim.  IMPART multi-modal dataset , 2015 .

[22]  Philip David,et al.  SoftPOSIT: Simultaneous Pose and Correspondence Determination , 2002, ECCV.

[23]  Carl Olsson,et al.  Branch-and-Bound Methods for Euclidean Registration Problems , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Horst Bischof,et al.  Incremental Line-based 3D Reconstruction using Geometric Constraints , 2013, BMVC.

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

[26]  Philip David,et al.  Object recognition in high clutter images using line features , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[27]  Pascal Vasseur,et al.  A Branch-and-Bound Approach to Correspondence and Grouping Problems , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Dirk Kraft,et al.  Extended 3D Line Segments from RGB-D Data for Pose Estimation , 2013, SCIA.