Real-time geometric fitting and pose estimation for surface of revolution

Abstract This paper presents a novel ellipse fitting method to simultaneously estimate the Euclidean pose and structure of a surface of revolution (SOR) by minimizing the geometric reprojection error of the visible cross sections in image space. This geometric error function and its Jacobian matrix are explicitly derived to enable Levenberg-Marquardt (LM) optimization. With the obtained pose and structure, the Euclidean shape of a SOR can be reconstructed by generating the ellipse tangency to the apparent contour of the SOR. Given the real size of several visible cross sections, this approach can be extended to perform a real-time 3D tracking of the SOR. Additionally, this technique can be also generalized to fitting for imaged parallel circles. Sufficient experiments validate the accuracy and the real-time performance of the proposed method.

[1]  Michel Dhome,et al.  Finding the Pose of an Object of Revolution , 1992, ECCV.

[2]  Kenichi Kanatani,et al.  Compact algorithm for strictly ML ellipse fitting , 2008, 2008 19th International Conference on Pattern Recognition.

[3]  Paulo R. S. Mendonça,et al.  Reconstruction of surfaces of revolution from single uncalibrated views , 2004, Image Vis. Comput..

[4]  I-Ming Chen,et al.  Accurate detection of ellipses with false detection control at video rates using a gradient analysis , 2018, Pattern Recognit..

[5]  J. G. Semple,et al.  Algebraic Projective Geometry , 1953 .

[6]  Fei Wang,et al.  A Robust Real-Time Vision System for Autonomous Cargo Transfer by an Unmanned Helicopter , 2015, IEEE Transactions on Industrial Electronics.

[7]  Ming Zhang,et al.  Using silhouette for pose estimation of object with surface of revolution , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[8]  Andrew P. Paplinski,et al.  Orthogonal Distance Least Squares Fitting: A Novel Approach , 2009, VISIGRAPP.

[9]  Chang Liu,et al.  Ellipse fitting for imaged cross sections of a surface of revolution , 2015, Pattern Recognit..

[10]  Tingting Lu,et al.  Relative pose estimation of a lander using crater detection and matching , 2016 .

[11]  Kostas Daniilidis,et al.  Absolute Pose and Structure from Motion for Surfaces of Revolution: Minimal Problems Using Apparent Contours , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[12]  Chandra Sekhar Seelamantula,et al.  Ellipse Fitting Using the Finite Rate of Innovation Sampling Principle , 2016, IEEE Transactions on Image Processing.

[13]  Wojciech Chojnacki,et al.  On the Fitting of Surfaces to Data with Covariances , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Pau Gargallo,et al.  Conic Fitting Using the Geometric Distance , 2007, ACCV.

[15]  Hiok Chai Quek,et al.  ElliFit: An unconstrained, non-iterative, least squares based geometric Ellipse Fitting method , 2013, Pattern Recognit..

[16]  Kostas Daniilidis,et al.  Seeing Glassware: from Edge Detection to Pose Estimation and Shape Recovery , 2016, Robotics: Science and Systems.

[17]  Peter Meer,et al.  Reduction of bias in maximum likelihood ellipse fitting , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[18]  Bing Li,et al.  A universal on-orbit servicing system used in the geostationary orbit , 2011 .

[19]  Alberto Del Bimbo,et al.  Metric 3D reconstruction and texture acquisition of surfaces of revolution from a single uncalibrated view , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  John Porrill.  Fitting ellipses and predicting confidence envelopes using a bias corrected Kalman filter , 1990, Image Vis. Comput..

[21]  Vijay Kumar,et al.  Visual Servoing of Quadrotors for Perching by Hanging From Cylindrical Objects , 2016, IEEE Robotics and Automation Letters.

[22]  Hans-Jürgen Warnecke,et al.  Least-squares orthogonal distances fitting of circle, sphere, ellipse, hyperbola, and parabola , 2001, Pattern Recognit..

[23]  Éric Marchand,et al.  Real-time markerless tracking for augmented reality: the virtual visual servoing framework , 2006, IEEE Transactions on Visualization and Computer Graphics.

[24]  Andrew W. Fitzgibbon,et al.  Direct Least Square Fitting of Ellipses , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Xi Zhang,et al.  A study on automatic on-machine inspection system for 3D modeling and measurement of cutting tools , 2013, J. Intell. Manuf..

[26]  Roberto Cipolla,et al.  Real-Time Visual Tracking of Complex Structures , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Long Quan,et al.  Circular motion geometry using minimal data , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  PAUL D. SAMPSON,et al.  Fitting conic sections to "very scattered" data: An iterative refinement of the bookstein algorithm , 1982, Comput. Graph. Image Process..

[29]  Ding Liu,et al.  Robust Ellipse Fitting Based on Sparse Combination of Data Points , 2013, IEEE Transactions on Image Processing.

[30]  Vincenzo Caglioti,et al.  Shape and orientation of revolution surfaces from contours and reflections , 2002, Pattern Recognit..

[31]  Peter Meer,et al.  Unbiased Estimation of Ellipses by Bootstrapping , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Jörg Matthes,et al.  Constrained Ellipse Fitting with Center on a Line , 2015, Journal of Mathematical Imaging and Vision.

[33]  Vijay Kumar,et al.  System for deployment of groups of unmanned micro aerial vehicles in GPS-denied environments using onboard visual relative localization , 2017, Auton. Robots.

[34]  Andrew Zisserman,et al.  Robust Object Tracking , 2001 .

[35]  David Wokes,et al.  Surveying and Pose Estimation of a Lander Using Approximative Crater Modelling , 2010 .

[36]  Erkki Oja,et al.  Randomized Hough transform (RHT) , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[37]  Geoff A. W. West,et al.  Perceptual grouping of circular arcs under projection , 1990, BMVC.

[38]  Vincent Lepetit,et al.  Robust 3D Object Tracking from Monocular Images Using Stable Parts , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  Chang Liu,et al.  Relative pose estimation for cylinder-shaped spacecrafts using single image , 2014, IEEE Transactions on Aerospace and Electronic Systems.

[40]  D. Shane Barwick,et al.  Very Fast Best-Fit Circular and Elliptical Boundaries by Chord Data , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Zygmunt L. Szpak,et al.  Guaranteed Ellipse Fitting with a Confidence Region and an Uncertainty Measure for Centre, Axes, and Orientation , 2015, Journal of Mathematical Imaging and Vision.

[42]  Kenichi Kanatani,et al.  Renormalization Returns: Hyper-renormalization and Its Applications , 2012, ECCV.

[43]  Alberto Del Bimbo,et al.  Accurate Automatic Localization of Surfaces of Revolution for Self-Calibration and Metric Reconstruction , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[44]  Junli Liang,et al.  Robust Ellipse Fitting via Half-Quadratic and Semidefinite Relaxation Optimization , 2015, IEEE Transactions on Image Processing.

[45]  Leejay Wu,et al.  3D Interpretation of Conics and Or-thogonality , 1993 .

[46]  Beno Benhabib,et al.  Three-dimensional location estimation of circular features for machine vision , 1992, IEEE Trans. Robotics Autom..

[47]  Pierre Gurdjos,et al.  Euclidean Structure from N geq 2 Parallel Circles: Theory and Algorithms , 2006, ECCV.

[48]  Long Quan,et al.  Geometry of Single Axis Motions Using Conic Fitting , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[49]  Chandra Sekhar Seelamantula,et al.  Ellipse fitting using finite rate of innovation principles , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[50]  Jinhai Cai,et al.  Improved ellipse fitting by considering the eccentricity of data point sets , 2013, 2013 IEEE International Conference on Image Processing.

[51]  Rozenn Dahyot,et al.  Robust ellipse detection with Gaussian mixture models , 2016, Pattern Recognit..

[52]  Kostas Daniilidis,et al.  Grasping surfaces of revolution: Simultaneous pose and shape recovery from two views , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[53]  David G. Lowe,et al.  Fitting Parameterized Three-Dimensional Models to Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[54]  Paul L. Rosin.  Ellipse fitting by accumulating five-point fits , 1993, Pattern Recognit. Lett..

[55]  Giorgio Panin,et al.  Vision-based localization for on-orbit servicing of a partially cooperative satellite , 2015 .