Representation and recognition of surface shapes in range images: A differential geometry approach

Theory and matching algorithms are developed for accurate orientation determination and recognition of 3D surface shapes in range images. Two corollaries to the fundamental theory of surface theory are proved. The first corollary proves the invariance of the fundamental coefficients when lines of curvature are used as the intrinsic parameter curves. The second corollary proves that a diffeomorphism which preserves the intrinsic distance along the principal directions, in addition to preserving the eigenvectors and eigenvalues of the shape operator (Weingarten map), is necessarily an isometry. Based on these two corollaries, a set of geometric descriptors which satisfy the uniqueness and invariance requirements are theoretically identified for all classes of surfaces, namely, hyperbolic, elliptic, and developable surfaces. Theunit normal and shape descriptors list array (UNSDLA) representation and the corresponding matching algorithm are developed. The UNSDLA is a generalization of the extended Gaussian image (EGI). The EGI has a fundamental limitation; that is, it can only uniquely represent convex shapes. The new representation overcomes this limitation of the EGI and extends the scope of unique representation to all classes of surfaces. Moreover, it still has all the advantages of the EGI. This is achieved by preserving the connectivity of the original data. Connectivity here should include not only the adjacency relation of points or patches on a surface, but also the direction and order in which the points or patches are traversed in a connected path. The importance of the direction and order of connectivity is emphasized. Surface matching can be performed more accurately using the UNSDLA than the EGI. Based on the UNSDLA representations, surfaces can be matched via the Gaussian map by optimization over all possible rotations of a surface shape. The representation and matching algorithm can deal with hyperbolic and elliptic surfaces whose Gaussian maps are not one-to-one. Developable surfaces whose Gaussian maps of lines of curvature with nonzero principal curvature are not one-to-one can also be accommodated. Two theorems on developable surfaces are proved.

[1]  Ramakant Nevatia,et al.  Description and Recognition of Curved Objects , 1977, Artif. Intell..

[2]  T. Okada Development of an Optical Distance Sensor for Robots , 1982 .

[3]  Ray A. Jarvis,et al.  A Laser Time-of-Flight Range Scanner for Robotic Vision , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  A. R. Johnston,et al.  A Scanning Laser Rangefinder for a Robotic Vechicle , 1977, IJCAI.

[5]  Jake K. Aggarwal,et al.  Curvature-based representation of objects from range data , 1986, Image Vis. Comput..

[6]  M. Brady,et al.  Smoothed Local Symmetries and Their Implementation , 1984 .

[7]  Jake K. Aggarwal,et al.  Detection of Edges Using Range Information , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  A. V. Pogorelov Extrinsic geometry of convex surfaces , 1973 .

[9]  C. S. G. Lee,et al.  Robotics: Control, Sensing, Vision, and Intelligence , 1987 .

[10]  J. Little Recovering shape and determining attitude from extended gaussian images , 1985 .

[11]  Thomas C. Henderson Efficient 3-D Object Representations for Industrial Vision Systems , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Jeffrey L. Posdamer,et al.  Surface measurement by space-encoded projected beam systems , 1982, Comput. Graph. Image Process..

[13]  J. Koenderink,et al.  The Shape of Smooth Objects and the Way Contours End , 1982, Perception.

[14]  Robert J. Drazovich,et al.  Model Based Interpretation of 3-D Range Data , 1986 .

[15]  Berthold K. P. Horn,et al.  The Mechanical Manipulation of Randomly Oriented Parts , 1984 .

[16]  James C. Bezdek,et al.  Curvature and Tangential Deflection of Discrete Arcs: A Theory Based on the Commutator of Scatter Matrix Pairs and Its Application to Vertex Detection in Planar Shape Data , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  P. M. Will,et al.  Grid coding: A novel technique for image processing , 1972 .

[18]  Tomas Lozano-Perez,et al.  Model-Based Recognition and Localization from Sparse Range Data , 1986 .

[19]  B. O'neill Elementary Differential Geometry , 1966 .

[20]  Jean Ponce,et al.  Describing surfaces , 1985, Comput. Vis. Graph. Image Process..

[21]  P. Liang Measurement, orientation determination and recognition of surface shapes in range images , 1987 .

[22]  Jake K. Aggarwal,et al.  Experiments in Intensity Guided Range Sensing Recognition of Three-Dimensional Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Kokichi Sugihara,et al.  Range-Data Analysis Guided by a Junction Dictionary , 1979, Artif. Intell..

[24]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

[25]  M. Hebert,et al.  The Representation, Recognition, and Positioning of 3-D Shapes from Range Data , 1987 .

[26]  Thomas O. Binford,et al.  Computer Description of Curved Objects , 1973, IEEE Transactions on Computers.

[27]  Robert J. Woodham,et al.  Photometric method for determining surface orientation from multiple images , 1980 .

[28]  Philip E. Brou Using the Gaussian Image to Find the Orientation of Objects , 1984 .

[29]  A. E. Brain,et al.  The measurement and use of registered reflectance and range data in scene analysis , 1977, Proceedings of the IEEE.

[30]  Ramesh C. Jain,et al.  Invariant surface characteristics for 3D object recognition in range images , 1985, Comput. Vis. Graph. Image Process..

[31]  Yoshiaki Shirai,et al.  Object Recognition Using Three-Dimensional Information , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Jean Ponce,et al.  Object Representation, Identification and Positioning from Range Data , 1984 .

[33]  Ray A. Jarvis,et al.  A Perspective on Range Finding Techniques for Computer Vision , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Yoram Yakimovsky,et al.  A system for extracting three-dimensional measurements from a stereo pair of TV cameras , 1976 .

[35]  M. Spivak A comprehensive introduction to differential geometry , 1979 .

[36]  Paul J. Besl,et al.  Segmentation through symbolic surface descriptions , 1986 .

[37]  H. K. Nishihara,et al.  Practical Real-Time Imaging Stereo Matcher , 1984 .

[38]  J. Thorpe Elementary Topics in Differential Geometry , 1979 .

[39]  Berthold K. P. Horn Extended Gaussian images , 1984, Proceedings of the IEEE.

[40]  Katsushi Ikeuchi,et al.  Picking up an Object from a Pile of Objects. , 1983 .