Abstract
Previous researchers have described several different approaches to 3-D object recognition based on using an iterative technique to control the matching of features from the 2-D projection of a 3-D model to observed image features. The major problem encountered with such approaches is how to automatically choose starting parameter estimates in a manner which both avoids recognition errors due to local minima and is still reasonably efficient. This paper investigates the use of theaspect graph to address this problem. The basic idea is quite simple — an iterative solution is generated for each of a set of candidate aspects and the best of these is chosen as the recognized view. Two assumptions are required in order for this approach to be valid: (1) the iterative search for the correct candidate aspect must converge to the correct answer, and (2) the solution found for the correct aspect must be better than that found for any of the incorrect candidate aspects. In order to explore the validity of these assumptions, a simple aspect graph-based recognition system was implemented. Experiments were carried out using both real and simulated data. The results indicate that the underlying assumptions are generally valid, and that this approach has advantages over previous techniques which incorporated an iterative search.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
J. Ben-Arie, Probabilistic models of observed features and aspects with an application to weighted aspect graphs, Pattern Recognition Lett. 11(1990)421–427.
K.W. Bowyer, M.Y. Sallam, D.E. Eggert and J.S. Stewman, Computing the generalized aspect graph for objects with moving parts, IEEE Trans. Pattern Anal. Machine Intellig. 15(1993)605–610.
H. Brusset, D. Depeyre, J. Petit and F. Haffner, On the convergence of standard and damped least squares methods, J. Comput. Phys. 22(1976)534–542.
C. Chen and A. Kak, A robot vision system for recognizing 3-D objects in low-order polynomial time, IEEE Trans. Syst., Man, and Cybern. 19(1989)1535–1563.
S.J. Dickinson, A.P. Pentland and A. Rosenfeld, 3-D shape recovery using distributed aspect matching, IEEE Trans. Pattern Anal. Machine Intellig. 14(1992)174–198.
H. Edelsbrunner, J. O'Rourke and R. Scidel, Constructing arrangements of lines and hyperplanes with applications, SIAM J. Comput. 15(1986)341–363.
D. Eggert and K. Bowyer, Matching the complete edge structure of the 2-D projection of an object using Fourier descriptors, in:Advances in Artificial Intelligence Research, Vol. 1 (JAI Press, Greenwich, Connecticut, 1989) pp. 225–250.
D. Eggert and K. Bowyer, Computing the perspective projection aspect graph of solids of revolution, IEEE Trans. Pattern Anal. Machine Intellig. 15(1993)109–128.
D.E. Eggert, K.W. Bowyer and C.R. Dyer, Aspect graphs: State-of-the-art and applications in digital photogrammetry,Proc. ISPRS 17th Congress: International Archives of Photogrammetry and Remote Sensing, Part B5 (1992) pp. 633–645.
D. Eggert, K. Bowyer, C. Dyer, H. Christensen and D. Goldgof, The scale space aspect graph, IEEE Trans. Pattern Anal. Machine Intellig. 15(1993)1114–1130.
Z. Gigus, J. Canny and R. Scidel, Efficiently computing and representing aspect graphs of polyhedral objects, IEEE Trans. Pattern Anal. Machine Intellig. 13(1991)542–551.
C. Goad, Special purpose automatic programming for 3-D model-based vision,Proc. ARPA Image Understanding Workshop, 1983, pp. 94–104.
J.A. Gualtieri, S. Baugher and M. Werman, The visual potential: One convex polygon, Computer Vision, Graphics, and Image Processing 46(1989)96–130.
C. Hansen and T. Henderson, CAGD-based computer vision, IEEE Trans. Pattern Anal. Machine Intellig. 11(1989)1181–1193.
M. Hebert and T. Kanade, The 3D-profile method for object recognition,Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 1985, pp. 458–463.
H. Hemami, F.C. Weimer and J.G. Advani, Identification of three-dimensional objects by sequential image matching,Proc. IEEE Conf. on Computer Graphics, Pattern Recognition, and Data Structures, 1975, pp. 273–278.
S.A. Hutchinson and A. Kak, Planning sensing strategies in a robust work cell with multi-sensor capabilities, IEEE Trans. Robotics and Autom. 5(1989)765–783.
K. Ikeuchi, Generating an interpretation tree froma CAD model for 3-D object recognition in bin-picking tasks, Int. J. Computer Vision 1(1987)145–165.
J.R. Kender and D.G. Freudenstein, What is a “degenerate” view?,Proc. ARPA Image Understanding Workshop, 1987, pp. 589–598.
J.J. Koenderink and A.J. van Doorn, The interbal representation of solid shape with respect to vision, Biolog. Cybern. 32(1979)211–216.
M.R. Korn and C.R. Dyer, 3-D multiview object representations for model-based object recognition, Pattern Recognition 20(1987)91–103.
D. Kriegman and D. Ponce, Computing exact aspect graphs of curved objects: Solids of revolution, Int. J. Computer Vision 5(1990)119–135.
D. Kriegman, B. Vijayakumar and J. Ponce, Strategies and constraints for recognizing and locating curved 3-D objects from monocular image features,Proc. 2nd European Conf. on Computer Vision, 1992, to appear.
D.G. Lowe, Solving for the parameters of object models from image descriptions,Proc. DARPA Image Understanding Workshop, 1980, pp. 121–127.
D.G. Lowe,Perceptual Organization and Visual Recognition (Kluwer Academic, Boston, MA, 1985).
D.G. Lowe, Fitting parameterized three-dimensional models to images, IEEE Trans. Pattern Anal. Machine Intellig. 13(1991)441–450.
J. Malik, Interpreting line drawings of curved objects, Int. J. Computer Vision 1(1987)73–103.
E. Persoon and K.S. Fu, Shape discrimination using Fourier descriptors, IEEE Trans. Syst., Man, and Cybern. 7(1974)170–179.
H. Plantinga and C.R. Dyer, Visibility, occlusion and the aspect graph, Int. J. Computer Vision 5(1990)137–160.
J. Ponce and D.J. Kriegman, On recognizing and positioning curved 3D objects from image contours,Proc. DARPA Image Understanding Workshop, 1989, pp. 461–470.
J. Ponce, S. Petitjean and K. Kriegman, Computing exact aspect graphs of curved objects: Algebraic surfaces,Proc. European Conf. on Computer Vision, 1992, pp. 599–614.
J. Rieger, Global bifurcation sets and stable projections of nonsingular algebraic surfaces, Int. J. Computer Vision 7(1992)171–194.
W.B. Scales and C.R. Dyer, Modeling the rim appearance,Proc. 3rd Int. Conf. on Computer Vision, 1990, pp. 698–701.
L.G. Shapiro, A CAD-model-based system for object localization, Proc. SPIE: Digital and Optical Shape Representation 938(1988)408–418.
T.M. Silberberg, L. Davis and D. Harwood, An iterative rough procedure for three-dimensional object recognition, Pattern Recognition 17(1984)621–629.
T. Sripradisvarakul and R. Jain, Generating aspect graphs for curved objects,Proc. IEEE Workshop on Interpretation of 3D Scenes, 1989, pp. 109–115.
J. Stewman and K.W. Bowyer, Direct construction of perspective projection aspect graphs for planar-face convex objects, Computer Vision, Graphics and Image Processing 51(1990)20–37.
J.H. Stewman and K.W. Bowyer, Creating the perspective projection aspect graph of convex polyhedra,Proc. 2nd Int. Conf. on Computer Vision, 1988, pp. 494–500.
J.H. Stewman, L. Stark and K.E. Bowyer, Restructuring aspect graphs into aspect- and cell-equivalence classes for use in computer vision,Proc. 13th Int. Workshop on Graph-Theoretic Concepts in Computer Science, 1987, pp. 230–241.
L.T. Watson and L.G. Shapiro, Identification of space curves from two-dimensional perspective views, IEEE Trans. Pattern Anal. Machine Intellig. 4(1982)469–475.
A.D. Worrall, K.D. Baker and G.D. Sullivan, Model based perspective inversion, Image and Vision Comput. 7(1989)17–23.
Author information
Authors and Affiliations
Additional information
This work was supported by Air Force Office of Scientific Research grants AFOSR-87-0316 and AFOSR-89-0036 and by National Science Foundation grants IRI-8817776.
Rights and permissions
About this article
Cite this article
Eggert, D., Stark, L. & Bowyer, K. Aspect graphs and their use in object recognition. Ann Math Artif Intell 13, 347–375 (1995). https://doi.org/10.1007/BF01530835
Issue Date:
DOI: https://doi.org/10.1007/BF01530835