Estimating depth from line drawing

ABSTRACT

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.

REFERENCES

• 1: H.G.Barrow, J.M.Tenenbaum, Interpreting Line Drawings as Three-Dimensional Surfaces, Artificial Intelligence, 75--116, 1981
• 2: R.P.Brent, Algorithms for Minimization without Derivatives, Prentice-Hall, 1973
• 3: Capital Aluminium Extrusions Ltd, Catalogue of Standard Profiles, 2000
• 4: M.B.Clowes, On Seeing Things, Artificial Intelligence 79--116, 1970
• 5: P.Company, J.M.Gomis, M.Contero, Geometrical Reconstruction from Single Line Drawings using Optimization-based Approaches, in ed. V.Skala, Proc. WSCG99 7th Int. Conf. in Central Europe on Computer Graphics, Visualization and Interactive Digital Media'99, University of West Bohemia, Plzen, 361--368, 1999
• 6: P.Company, J.M.Gomis, M.Contero, An Optimization-Based Algorithm to Reconstruct 3D Models from Single Line Drawings, II Seminario Italo-Spagnolo. 952--958, 1998
• 7: J.Conesa Pastor, P.Company Calleja, J.M.Gomis Marti, Initial Modeling Strategies for Geometrical Reconstruction---Optimization-Based Approaches, Proc. 11th Int. Conf. on Design Tools and Methods in Industrial Engineering, 161--171, 1999
• 8: I.J.Grimstead, Interactive Sketch Input of Boundary Representation Solid Models, PhD Thesis, Cardiff University, October 1997
• 9: D.A.Huffman, Impossible Objects as Nonsense Sentences, Machine Intelligence 295--323, 1971
• 10: T.Kanade, Recovery of the Three-Dimensional Shape of an Object from a Single View, Artificial Intelligence, 409--460, 1981
• 11: Yvan G. Leclerc , Martin A. Fischler, An optimization-based approach to the interpretation of single line drawings as 3D wire frames, International Journal of Computer Vision, v.9 n.2, p.113-136, Nov. 1992 [doi>10.1007/BF00129683]
• 12: H.Lipson, M.Shpitalni, Optimization-based Reconstruction of a 3D Object from a Single Freehand Line Drawing, Computer-Aided Design, 651--663, 1996
• 13: H. Lipson , M. Shpitalni, An interface for 3D conceptual design based on freehand sketching, Proceedings of the fifth IFIP TC5/WG5.2 international workshop on geometric modeling in computer aided design on Product modeling for computer integrated design and manufacture, p.139-148, January 1997, Airlie, Virginia, United States
• 14: Thomas Marill, Emulating the human interpretation of line-drawings as three-dimensional objects, International Journal of Computer Vision, v.6 n.2, p.147-161, June 1991 [doi>10.1007/BF00128154]
• 15: Helmut Mayer, Automatic object extraction from aerial imagery—a survey focusing on buildings, Computer Vision and Image Understanding, v.74 n.2, p.138-149, May 1999 [doi>10.1006/cviu.1999.0750]
• 16: S.Meeran, J.M.Taib, A Generic Approach to Recognising Isolated, Nested and Interacting Features from 2D Drawings, Computer-Aided Design, 891--910, 1999
• 17: I.V.Nagendra, U.G.Gujar, 3D Objects From 2D Orthographic Views, Computers & Graphics 111--114, 1988
• 18: D.N.Perkins, Cubic Corners, Quarterly Progress Report 89, 207--214, MIT Research Laboratory of Electronics, 1968
• 19: F.Pickup, M.A.Parker, Engineering Drawing with Worked Examples, 3rd Edition, Hutchison and Co, 1979
• 20: L.Ros, A Kinematic-Geometric Approach to Spatial Interpretation of Line Drawings, PhD Thesis, Universitat Politecnica de Catalunya, 2000
• 21: Yoshiaki Shirai, Three-dimensional computer vision, Springer-Verlag New York, Inc., New York, NY, 1987
• 22: Moshe Shpitalni , Hod Lipson, Identification of Faces in a 2D Line Drawing Projection of a Wireframe Object, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.18 n.10, p.1000-1012, October 1996 [doi>10.1109/34.541409]
• 23: Kokichi Sugihara, Machine interpretation of line drawings, MIT Press, Cambridge, MA, 1986
• 24: P. A. C. Varley , R. R. Martin, A System for Constructing Boundary Representation Solid Models from a Two-Dimensional Sketch, Proceedings of the Geometric Modeling and Processing 2000, p.13, April 10-12, 2000
• 25: P.A.C.Varley, R.R.Martin, Interpretation of Single Sketch Input for Mesh and Solid Models, Int. J. Shape Modelling, 207--241, 2000
• 26: P.A.C.Varley, R.R.Martin, The Junction Catalogue for Labelling Line Drawings of Polyhedra with Tetrahedral Vertices, Int. J. Shape Modelling, 23--44, 2001
• 27: P.A.C.Varley, R.R.Martin, Alternatives for Labelling Line Drawings, submitted to Int. J. Shape Modelling, 2000
• 28: P.A.C.Varley, Automatic Creation of Boundary-Representation Models from Single Line Drawings, PhD Thesis, Cardiff University, 2002
• 29: T.Vetter,T.Poggio, Symmetric 3D objects are an easy case for 2D object recognition, Human Symmetry Perception, ed C.W.Tyler, 349--359, 1996
• 30: Herbert W. Yankee, Engineering Graphics, PWS Publishing Co., Boston, MA, 1985

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.6 COMPUTER-AIDED ENGINEERING

General Terms:
Algorithms, Experimentation

Keywords:
B-rep models, sketch input