On Sampling Focal Length Values to Solve the Absolute Pose Problem

Estimating the absolute pose of a camera relative to a 3D representation of a scene is a fundamental step in many geometric Computer Vision applications. When the camera is calibrated, the pose can be computed very efficiently. If the calibration is unknown, the problem becomes much harder, resulting in slower solvers or solvers requiring more samples and thus significantly longer run-times for RANSAC. In this paper, we challenge the notion that using minimal solvers is always optimal and propose to compute the pose for a camera with unknown focal length by randomly sampling a focal length value and using an efficient pose solver for the now calibrated camera. Our main contribution is a novel sampling scheme that enables us to guide the sampling process towards promising focal length values and avoids considering all possible values once a good pose is found. The resulting RANSAC variant is significantly faster than current state-of-the-art pose solvers, especially for low inlier ratios, while achieving a similar or better pose accuracy.

[1]  Hongbin Zha,et al.  Computer Vision - ACCV 2009, 9th Asian Conference on Computer Vision, Xi'an, China, September 23-27, 2009, Revised Selected Papers, Part III , 2010, Asian Conference on Computer Vision.

[2]  Zuzana Kukelova,et al.  Robust Focal Length Estimation by Voting in Multi-view Scene Reconstruction , 2009, ACCV.

[3]  Roland Siegwart,et al.  A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation , 2011, CVPR 2011.

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

[5]  Matthieu Guillaumin,et al.  Segmentation Propagation in ImageNet , 2012, ECCV.

[6]  Zuzana Kukelova,et al.  Making minimal solvers fast , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[8]  Thomas Deselaers,et al.  ClassCut for Unsupervised Class Segmentation , 2010, ECCV.

[9]  Jan-Michael Frahm,et al.  From structure-from-motion point clouds to fast location recognition , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Steven M. Seitz,et al.  Photo tourism: exploring photo collections in 3D , 2006, ACM Trans. Graph..

[11]  Daniel P. Huttenlocher,et al.  Location Recognition Using Prioritized Feature Matching , 2010, ECCV.

[12]  PollefeysMarc,et al.  Camera Network Calibration and Synchronization from Silhouettes in Archived Video , 2010 .

[13]  Jan-Michael Frahm,et al.  Building Rome on a Cloudless Day , 2010, ECCV.

[14]  Jiri Matas,et al.  Randomized RANSAC with Td, d test , 2004, Image Vis. Comput..

[15]  Jiri Matas,et al.  Randomized RANSAC with T(d, d) test , 2002, BMVC.

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

[17]  Robert M. Haralick,et al.  Review and analysis of solutions of the three point perspective pose estimation problem , 1994, International Journal of Computer Vision.

[18]  Zuzana Kukelova,et al.  A general solution to the P4P problem for camera with unknown focal length , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[20]  Torsten Sattler,et al.  Improving Image-Based Localization by Active Correspondence Search , 2012, ECCV.

[21]  Jiri Matas,et al.  Optimal Randomized RANSAC , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[23]  Zuzana Kukelova,et al.  Real-Time Solution to the Absolute Pose Problem with Unknown Radial Distortion and Focal Length , 2013, 2013 IEEE International Conference on Computer Vision.

[24]  Zuzana Kukelova,et al.  New Efficient Solution to the Absolute Pose Problem for Camera with Unknown Focal Length and Radial Distortion , 2010, ACCV.

[25]  Pascal Fua,et al.  Worldwide Pose Estimation Using 3D Point Clouds , 2012, ECCV.

[26]  Mongi A. Abidi,et al.  A New Efficient and Direct Solution for Pose Estimation Using Quadrangular Targets: Algorithm and Evaluation , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Bill Triggs,et al.  Camera pose and calibration from 4 or 5 known 3D points , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[28]  Changchang Wu,et al.  Towards Linear-Time Incremental Structure from Motion , 2013, 2013 International Conference on 3D Vision.

[29]  Marc Pollefeys,et al.  Camera Network Calibration and Synchronization from Silhouettes in Archived Video , 2010, International Journal of Computer Vision.

[30]  Zuzana Kukelova,et al.  Closed-Form Solutions to Minimal Absolute Pose Problems with Known Vertical Direction , 2010, ACCV.

[31]  Andrew Zisserman,et al.  Multiple View Geometry , 1999 .

[32]  Radim Sára,et al.  A Weak Structure Model for Regular Pattern Recognition Applied to Facade Images , 2010, ACCV.

[33]  Klas Josephson,et al.  Pose estimation with radial distortion and unknown focal length , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.