Minimal Solvers for Indoor UAV Positioning

In this paper we consider a collection of relative pose problems which arise naturally in applications for visual indoor UAV navigation. We focus on cases where additional information from an onboard IMU is available and thus provides a partial extrinsic calibration through the gravitational vector. The solvers are designed for a partially calibrated camera, for a variety of realistic indoor scenarios, which makes it possible to navigate using images of the ground floor. Current state-of-the-art solvers use more general assumptions, such as using arbitrary planar structures; however, these solvers do not yield adequate reconstructions for real scenes, nor do they perform fast enough to be incorporated in real-time systems. We show that the proposed solvers enjoy better numerical stability, are faster, and require fewer point correspondences, compared to state-of-the-art solvers. These properties are vital components for robust navigation in real-time systems, and we demonstrate on both synthetic and real data that our method outperforms other methods, and yields superior motion estimation.

[1]  Zuzana Kukelova,et al.  Radially-Distorted Conjugate Translations , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Frederik Schaffalitzky,et al.  How hard is 3-view triangulation really? , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[3]  M. Pollefeys,et al.  Homography based visual odometry with known vertical direction and weak Manhattan world assumption , 2012 .

[4]  Amir Hashemi,et al.  A New Solution to the Relative Orientation Problem Using Only 3 Points and the Vertical Direction , 2009, Journal of Mathematical Imaging and Vision.

[5]  Richard I. Hartley,et al.  Estimation of Relative Camera Positions for Uncalibrated Cameras , 1992, ECCV.

[6]  Martin Byröd Numerical Methods for Geometric Vision: From Minimal to Large Scale Problems , 2010 .

[7]  Kalle Åström,et al.  Absolute pose for cameras under flat refractive interfaces , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Pascal Vasseur,et al.  Homography Based Egomotion Estimation with a Common Direction , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  S. Bougnoux,et al.  From projective to Euclidean space under any practical situation, a criticism of self-calibration , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[10]  Martin Byröd,et al.  A Column-Pivoting Based Strategy for Monomial Ordering in Numerical Gröbner Basis Calculations , 2008, ECCV.

[11]  Jean Ponce,et al.  An Efficient Solution to the Homography-Based Relative Pose Problem With a Common Reference Direction , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[13]  Hongdong Li,et al.  Five-Point Motion Estimation Made Easy , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[14]  Zuzana Kukelova,et al.  Making Minimal Solvers for Absolute Pose Estimation Compact and Robust , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[15]  Zuzana Kukelova,et al.  Automatic Generator of Minimal Problem Solvers , 2008, ECCV.

[16]  Jan-Michael Frahm,et al.  The Misty Three Point Algorithm for Relative Pose , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Zuzana Kukelova,et al.  Radial distortion homography , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Dario Floreano,et al.  Learning Vision-Based Flight in Drone Swarms by Imitation , 2019, IEEE Robotics and Automation Letters.

[19]  Zuzana Kukelova,et al.  Camera Pose Estimation with Unknown Principal Point , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  Yubin Kuang,et al.  Minimal Solvers for Relative Pose with a Single Unknown Radial Distortion , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Martin Byröd,et al.  Fast and Stable Polynomial Equation Solving and Its Application to Computer Vision , 2009, International Journal of Computer Vision.

[22]  Viktor Larsson,et al.  Polynomial Solvers for Saturated Ideals , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[23]  Martin Byröd,et al.  Fast Optimal Three View Triangulation , 2007, ACCV.

[24]  Viktor Larsson,et al.  Uncovering Symmetries in Polynomial Systems , 2016, ECCV.

[25]  Zuzana Kukelova,et al.  Fast and robust numerical solutions to minimal problems for cameras with radial distortion , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Kostas Daniilidis,et al.  Optimizing polynomial solvers for minimal geometry problems , 2011, 2011 International Conference on Computer Vision.

[27]  Zuzana Kukelova,et al.  A Clever Elimination Strategy for Efficient Minimal Solvers , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  H. C. Longuet-Higgins,et al.  A computer algorithm for reconstructing a scene from two projections , 1981, Nature.

[29]  David Nister,et al.  Recent developments on direct relative orientation , 2006 .

[30]  Yubin Kuang,et al.  Numerically Stable Optimization of Polynomial Solvers for Minimal Problems , 2012, ECCV.

[31]  Richard I. Hartley,et al.  Projective Reconstruction and Invariants from Multiple Images , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  H. M. Möller,et al.  Multivariate polynomial equations with multiple zeros solved by matrix eigenproblems , 1995 .

[33]  Changchang Wu,et al.  P3.5P: Pose estimation with unknown focal length , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Zuzana Kukelova,et al.  Beyond Grobner Bases: Basis Selection for Minimal Solvers , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[35]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Hongdong Li A Simple Solution to the Six-Point Two-View Focal-Length Problem , 2006, ECCV.

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

[38]  Viktor Larsson,et al.  Efficient Solvers for Minimal Problems by Syzygy-Based Reduction , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Zuzana Kukelova,et al.  Fast and Stable Algebraic Solution to L2 Three-View Triangulation , 2013, 2013 International Conference on 3D Vision.