Invariant Descriptors for 3D Object Recognition and Pose

Invariant descriptors are shape descriptors that are unaffected by object pose, by perspective projection, or by the intrinsic parameters of the camera. These descriptors can be constructed using the methods of invariant theory, which are briefly surveyed. A range of applications of invariant descriptors in 3D model-based vision is demonstrated. First, a model-based vision system that recognizes curved plane objects irrespective of their pose is demonstrated. Curves are not reduced to polyhedral approximations but are handled as objects in their own right. Models are generated directly from image data. Once objects have been recognized, their pose can be computed. Invariant descriptors for 3D objects with plane faces are described. All these ideas are demonstrated using images of real scenes. The stability of a range of invariant descriptors to measurement error is treated in detail. >

[1]  C. E. Springer,et al.  Geometry and Analysis of Projective Spaces , 1967 .

[2]  R. Hartshorne.  Foundations of projective geometry , 1967 .

[3]  J. Dieudonne,et al.  Invariant theory, old and new , 1971 .

[4]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[5]  W. Boothby.  An introduction to differentiable manifolds and Riemannian geometry , 1975 .

[6]  J. Canny.  Finding Edges and Lines in Images , 1983 .

[7]  Rodney A. Brooks,et al.  Model-Based Three-Dimensional Interpretations of Two-Dimensional Images , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Sundaram Ganapathy,et al.  Decomposition of transformation matrices for robot vision , 1984, Pattern Recognit. Lett..

[9]  Michael Brady,et al.  The Curvature Primal Sketch , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  P. Olver.  Applications of lie groups to differential equations , 1986 .

[11]  R. Y. Tsai,et al.  An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision , 1986, CVPR 1986.

[12]  Yehezkel Lamdan,et al.  Object recognition by affine invariant matching , 2011, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Takeo Kanade,et al.  Applying Sensor Models To Automatic Generation Of Object Recognition Programs , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[14]  Gil J. Ettinger,et al.  Large hierarchical object recognition using libraries of parameterized model sub-parts , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Takeo Kanade,et al.  Modeling sensors and applying sensor model to automatic generation of object recognition program , 1988 .

[16]  Isaac Weiss,et al.  Projective invariants of shapes , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Larry S. Davis,et al.  Pose Determination of a Three-Dimensional Object Using Triangle Pairs , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Lars Nielsen,et al.  Automated guidance of vehicles using vision and projective invariant marking , 1988, Autom..

[19]  D. Kriegman,et al.  On recognizing and positioning curved 3D objects from image contours , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

[20]  Stefano Masciangelo.  3-D cues from a single view: detection of elliptical arcs and model-based perspective backprojection , 1990, BMVC.

[21]  Johan Wagemans,et al.  Similarity extraction and modeling , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[22]  David A. Forsyth,et al.  Projectively invariant representations using implicit algebraic curves , 1990, Image Vis. Comput..

[23]  K. Kanatani.  Group-Theoretical Methods in Image Understanding , 1990 .

[24]  Michel Dhome,et al.  Spatial Localization Of Modelled Objects Of Revolution In Monocular Perspective Vision , 1990, ECCV.

[25]  David J. Kriegman,et al.  On Recognizing and Positioning Curved 3-D Objects from Image Contours , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  David A. Forsyth,et al.  Transformational invariance - a primer , 1990, BMVC.

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

[28]  Eamon B. Barrett,et al.  General methods for determining projective invariants in imagery , 1991, CVGIP Image Underst..

[29]  Luce Morin,et al.  Geometric Solutions to some 3D Vision Problems , 1991, Geometric Reasoning for Perception and Action.

[30]  Lars Nielsen,et al.  Projective area-invariants as an extension of the cross-ratio , 1991, CVGIP Image Underst..

[31]  J. Mundy,et al.  Fitting affine invariant conics to curves , 1992 .

[32]  David J. Kriegman,et al.  On using CAD models to compute the pose of curved 3D objects , 1992, CVGIP Image Underst..

[33]  David A. Forsyth,et al.  Relative motion and pose from arbitrary plane curves , 1992, Image Vis. Comput..

[34]  S. Maybank.  The projection of two non-coplanar conics , 1992 .