Estimating depth from line drawing

Our goal is unassisted machine interpretation of a single line drawing of an engineering object (with hidden lines removed) as a B-rep model. As part of this process, we seek to deduce a frontal geometry of the object, a 3D geometric realisation of that part of the object visible in the drawing. Inflation takes a drawing in which all lines have been line-labelled, and creates the frontal geometry by adding a z-coordinate to the x- and y-coordinates of each junction. This depth information comes from compliance functions, interpretations of drawing features expressed as equations in junction z-coordinates. We examine several compliance functions, and assessing their use in interpretation of engineering objects. We also describe a compliance function based on junction labels, and remove its previous restriction to trihedral vertices. We give a comparative analysis of applying combinations of compliance functions to a set of test drawings. As a result, we recommend using edge parallelism in combination with either corner orthogonality or junction label pairs, the latter being more reliable in general. Additional use of face planarity compliance is often beneficial and even necessary.

[1]  Thomas Marill,et al.  Emulating the human interpretation of line-drawings as three-dimensional objects , 1991, International Journal of Computer Vision.

[2]  Helmut Mayer,et al.  Automatic Object Extraction from Aerial Imagery - A Survey Focusing on Buildings , 1999, Comput. Vis. Image Underst..

[3]  Ralph R. Martin,et al.  Interpretation of Single Sketch Input for Mesh and solid Models , 2000, Int. J. Shape Model..

[4]  Herbert W. Yankee,et al.  Engineering Graphics , 1970 .

[5]  Takeo Kanade,et al.  Recovery of the Three-Dimensional Shape of an Object from a Single View , 1981, Artif. Intell..

[6]  Yoshiaki Shirai.  Interpretation of Line Drawings , 1987 .

[7]  Sheik Meeran,et al.  A generic approach to recognising isolated, nested and interacting features from 2D drawings , 1999, Comput. Aided Des..

[8]  Conesa Pastor.  Initial modeling strategies for geometrical reconstruction optimization-based approaches , 1999 .

[9]  Ralph R. Martin,et al.  The Junction Catalogue for Labelling Line Drawings of Polyhedra with Tetrahedral vertices , 2001, Int. J. Shape Model..

[10]  Ralph R. Martin,et al.  A system for constructing boundary representation solid models from a two-dimensional sketch , 2000, Proceedings Geometric Modeling and Processing 2000. Theory and Applications.

[11]  Yoshiaki Shirai,et al.  Three-Dimensional Computer Vision , 1987, Symbolic Computation.

[12]  Hod Lipson,et al.  Identification of Faces in a 2D Line Drawing Projection of a Wireframe Object , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Peter Ashley Clifford Varley,et al.  Automatic creation of boundary-representation models from single line drawings , 2003 .

[14]  Hod Lipson,et al.  An interface for 3D conceptual design based on freehand sketching , 1997 .

[15]  D. Anderson,et al.  Algorithms for minimization without derivatives , 1974 .

[16]  I. V. Nagendra,et al.  3D objects from 2D orthographic views: a survey , 1988 .

[17]  Uday G. Gujar,et al.  3-D objects from 2-D orthographic views--A survey , 1988, Comput. Graph..

[18]  S. Sutherland.  Seeing things , 1989, Nature.

[19]  Harry G. Barrow,et al.  Interpreting Line Drawings as Three-Dimensional Surfaces , 1980, Artif. Intell..

[20]  Jaume I. Dept.  GEOMETRICAL RECONSTRUCTION FROM SINGLE LINE DRAWINGS USING OPTIMIZATION-BASED APPROACHES , 1999 .

[21]  T. Poggio,et al.  Symmetric 3D objects are an easy case for 2D object recognition. , 1994, Spatial vision.

[22]  K. Sugihara.  Machine interpretation of line drawings , 1986, MIT Press series in artificial intelligence.

[23]  Martin A. Fischler,et al.  An optimization-based approach to the interpretation of single line drawings as 3D wire frames , 1992, International Journal of Computer Vision.

[24]  L. Giralt,et al.  A kinematic-geometric approach to spatial interpretation of line drawings , 2000 .