Pose Estimation in Conformal Geometric Algebra Part II: Real-Time Pose Estimation Using Extended Feature Concepts

Part II uses the foundations of Part I [35] to define constraint equations for 2D-3D pose estimation of different corresponding entities. Most articles on pose estimation concentrate on specific types of correspondences, mostly between points, and only rarely use line correspondences. The first aim of this part is to extend pose estimation scenarios to correspondences of an extended set of geometric entities. In this context we are interested to relate the following (2D) image and (3D) model types: 2D point/3D point, 2D line/3D point, 2D line/3D line, 2D conic/3D circle, 2D conic/3D sphere. Furthermore, to handle articulated objects, we describe kinematic chains in this context in a similar manner. We ensure that all constraint equations end up in a distance measure in the Euclidean space, which is well posed in the context of noisy data. We also discuss the numerical estimation of the pose. We propose to use linearized twist transformations which result in well conditioned and fast solvable systems of equations. The key idea is not to search for the representation of the Lie group, describing the rigid body motion, but for the representation of their generating Lie algebra. This leads to real-time capable algorithms.

[1]  Homer H. Chen.  Pose Determination from Line-to-Plane Correspondences: Existence Condition and Closed-Form Solutions , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Gerald Sommer,et al.  Geometric Computing with Clifford Algebras , 2001, Springer Berlin Heidelberg.

[3]  G. Sommer.  Geometric computing with Clifford algebras: theoretical foundations and applications in computer vision and robotics , 2001 .

[4]  Jean Gallier,et al.  Geometric Methods and Applications: For Computer Science and Engineering , 2000 .

[5]  Jan J. Koenderink,et al.  Algebraic Frames for the Perception-Action Cycle , 1997, Lecture Notes in Computer Science.

[6]  Richard M. Murray,et al.  A Mathematical Introduction to Robotic Manipulation , 1994 .

[7]  J. Beveridge.  Local search algorithms for geometric object recognition: optimal correspondence and pose , 1993 .

[8]  J. Denavit,et al.  A kinematic notation for lower pair mechanisms based on matrices , 1955 .

[9]  Eduardo Bayro-Corrochano,et al.  Kinematics of robot manipulators in the motor algebra , 2001 .

[10]  David Hestenes,et al.  Generalized homogeneous coordinates for computational geometry , 2001 .

[11]  Gerald Sommer,et al.  Algebraic Aspects of Designing Behaviour Based Systems , 1997, AFPAC.

[12]  Wilhelm Blaschke,et al.  Kinematik und Quaternionen , 1960 .

[13]  Robert B. Fisher,et al.  A Comparison of Four Algorithms for Estimating 3-D Rigid Transformations , 1995, BMVC.

[14]  Robert J. Holt,et al.  Uniqueness of Solutions to Structure and Motion from Combinations of Point and Line Correspondences , 1996, J. Vis. Commun. Image Represent..

[15]  Michael Felsberg,et al.  The Multidimensional Isotropic Generalization of Quadrature Filters in Geometric Algebra , 2000, AFPAC.

[16]  Joan Lasenby,et al.  A novel axiomatic derivation of geometric algebra , 1999 .

[17]  Michael Werman,et al.  Pose Estimation by Fusing Noisy Data of Di � erent Dimensions , 2007 .

[18]  Bodo Rosenhahn,et al.  Pose Estimation of 3D Free-Form Contours , 2005, International Journal of Computer Vision.

[19]  Bodo Rosenhahn,et al.  Pose Estimation Using Geometric Constraints , 2000, Theoretical Foundations of Computer Vision.

[20]  Radu Horaud,et al.  Object pose from 2-D to 3-D point and line correspondences , 1995, International Journal of Computer Vision.

[21]  Richard A. Volz,et al.  Estimating 3-D location parameters using dual number quaternions , 1991, CVGIP Image Underst..

[22]  Bodo Rosenhahn,et al.  Constraint Equations for 2D-3D Pose Estimation in Conformal Geometric Algebra , 2000 .

[23]  H. Brauner.  W. Blaschke, Kinematik und Quaternionen. (Mathematische Monographien) VIII + 84 S. Berlin 1960. Deutscher Verlag der Wissenschaften. Preis geb. DM 20,40 , 1962 .

[24]  Alessandro Chiuso,et al.  Visual tracking of points as estimation on the unit sphere , 1997, Block Island Workshop on Vision and Control.

[25]  O. Faugeras.  Stratification of three-dimensional vision: projective, affine, and metric representations , 1995 .

[26]  D. Hestenes,et al.  Projective geometry with Clifford algebra , 1991 .

[27]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[28]  Bodo Rosenhahn,et al.  Pose Estimation in Conformal Geometric Algebra Part I: The Stratification of Mathematical Spaces , 2005, Journal of Mathematical Imaging and Vision.

[29]  Sebastian Weik,et al.  Hierarchical 3D Pose Estimation for Articulated Human Body Models from a Sequence of Volume Data , 2001, RobVis.

[30]  Tristan Needham,et al.  Visual Complex Analysis , 1997 .

[31]  Bodo Rosenhahn,et al.  Monocular Pose Estimation of Kinematic Chains , 2002 .

[32]  William H. Press,et al.  Numerical recipes , 1990 .

[33]  Jitendra Malik,et al.  Tracking people with twists and exponential maps , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[34]  David Hestenes,et al.  New algebraic tools for classical geometry , 2001 .

[35]  Kostas Daniilidis,et al.  Hand-Eye Calibration Using Dual Quaternions , 1999, Int. J. Robotics Res..

[36]  Leo Dorst,et al.  Honing geometric algebra for its use in the computer sciences , 2001 .

[37]  Robert B. Fisher,et al.  Estimating 3-D rigid body transformations: a comparison of four major algorithms , 1997, Machine Vision and Applications.

[38]  Alexa Hauck,et al.  Hierarchical recognition of articulated objects from single perspective views , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[39]  Bodo Rosenhahn,et al.  Tracking with a Novel Pose Estimation Algorithm , 2001, RobVis.

[40]  Fergal Shevlin,et al.  Analysis of orientation problems using Plucker lines , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[41]  Ales Ude,et al.  Filtering in a unit quaternion space for model-based object tracking , 1999, Robotics Auton. Syst..

[42]  Gerald Sommer,et al.  Algebraic Frames for the Perception-Action Cycle , 2000, Lecture Notes in Computer Science.

[43]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .