This article describes a method to generate 3D-object recognition algorithms from a geometrical model for bin-picking tasks. Given a 3D solid model of an object, we first generate apparent shapes of an object under various viewer directions. Those apparent shapes are then classified into groups (representative attitudes) based on dominant visible faces and other features. Based on the grouping, recognition algorithms are generated in the form of an interpretation tree. The interpretation tree consists of two parts: the first part for classifying a target region in an image into one of the shape groups, and the second part for determining the precise attitude of the object within that group. We have developed a set of rules to find out what appropriate features are to be used in what order to generate an efficient and reliable interpretation tree. Features used in the interpretation tree include inertia of a region, relationship to the neighboring regions, position and orientation of edges, and extended Gaussian images.
This method has been applied in a task for bin-picking objects that include both planar and cylindrical surfaces. As sensory data, we have used surface orientations from photometric stereo, depth from binocular stereo using oriented-region matching, and edges from an intensity image.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
S. Tsuji and A. Nakamura, “Recognition of an object in a stack of industrial parts”, in PROC. 4TH INT. JOINT CONF. ARTIF. INTELL., 1975, pp. 881–818.
S. Tsuji and F. Matsumoto, “Detection of elliptic and linear edges by searching two parameter space”, in PROC. 5TH INT. JOINT CONF. ARTIF. INTELL., 1977, pp. 569–575.
M. Yachida and S. Tsuji, “A machine learning capability”, in PROC. 4TH INT. JOINT CONF. ARTIF. INTELL., 1975, pp. 819–826.
M.L. Baird, “Image segmentation technique for locating automotive parts on belt conveyers”, in PROC. 5TH INT. CONF. ARTIF. INTELL., 1977, pp. 694–695.
W.A. Perkins, “Model-based vision system for scene containing multiple parts”, in PROC. 5TH INT. JOINT CONF. ARTIF. INTELL., 1977, pp. 678–684.
R. Bolles and R.A. Cain, “Recognizing and locating partially visible objects: the local-feature-focus method”, INT. J. ROBOTICS RES. vol. 1, no. 3, pp. 57–82, 1982.
Y. Fukada, “Recognition of struetural industrial parts stacked in bin”. ROBOTICA vol. 2, 147–154, 1984.
C. Goad, “Special purpose automatic programming for 3D model-based vision”, in PROC. IMAGE UNDER-STANDING WORKSHOP, 1983, pp. 94–104.
N. Ayache, B. Faverjon, J. Boissonnat, and B. Bollack, “Automatic handling of overlapping workpieces”, in PROC. INT. CONF. PATTERN RECOGNITION 84, 1984, pp. 837–839.
W.E.L. Grimson and T. Lozano-Pérez, “Model-based recognition and localization from sparse range or tactile data”, INT. J. ROBOTICS RES. vol. 3, no. 3, pp. 3–35, 1984.
J.R. Birk, R.B. Kelly, and H.A.S. Martines, “An orienting robot for feeding workpieces stored in bins”, IEEE TRANS. SMC vol. SMC-11, no. 2, pp. 151–160, 1981.
K. Ikeuchi, B.K.P. Horn, S. Nagata, T. Callahan, and O. Feingold, “Picking up an object from a pile of objects”, in PROC. FIRST INT. SYMP. ROBOTICS RES., M. Brady and R. Paul (eds.), M.I.T. Press: Cambridge, MA, 1984.
K. Ikeuchi, H.K. Nishihara, B.K.P. Horn, P. Sobalvarro, and S. Nagata, “Determining grasp points using photometric stereo and theprism binocular stereo system”, INT. J. ROBOTICS RES. vol. 5, no. 1, pp. 46–65, 1986.
B.K.P. Horn and K. Ikeuchi, “The mechanical manipulation of randomly oriented parts”, SCIENTIFIC AMERICAN vol. 251, no. 2, pp. 100–111, 1984.
K. Koshikawa,Solver REFERENCE MANUAL, RM-85-33J [in Japanese]. Computer Vision Section, Electrotechnical Lab., 1984.
K. Koshikawa and Y. Shirai, “A 3-D modeler for vision research”, in PROC. '85 INT. CONF. ADVANCED ROBOT, Robotics Society of Japan, 1985, pp. 185–190.
M. Oshima and Y. Shirai, “A model based vision for scenes with stacked polyhedra using 3D data”, in PROC. '85 INT. CONF. ADVANCED ROBOT, Robotics Society of Japan, 1985, pp. 191–198.
F. Kimura and M. Hosaka, PROGRAM PACKAGEgeomap REFERENCE MANUAL, Computer Vision Section, Electrotechnical Lab., 1977.
B.G. Baumgart, “Winged edge polyhedron representation”, Stanford Univ. A.I. Lab., STAN-CS-320, 1972.
I. Chakravarty and H. Freeman, “Characteristic views as a basis for three-dimensional object recognition”, in PROC. SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS CONF ROBOT VISION, vol. 336. SPIE: Bellingham, WA, 1982, pp. 37–45.
J.J. Koenderink and A.J.Van Doorn, “Internal representation of solid shape with respect to vision”, BIOL. CYBERNETICS, vol. 32, no. 4, pp. 211–216, 1979.
K. Sugihara, “Automatic construction of junction dictionaries and their exploitation for analysis for range data”, in PROC. 6TH INT. JOINT CONF. ARTIF. INTELL., 1979, pp. 859–864.
C. Thorpe and S. Shafer, “Correspondence in Line Drawings of Multiple Views”, in PROC. 8TH INT. JOINT CONF. ARTIF. INTELL., 1983, pp. 959–965.
M. Herman, “Matching three-dimensional symbolic description obtained from multiple views”, in PROC. IEEE COMPUT. SOC. CONF. COMPUT. VISION AND PATTERN RECOGNITION, San Francisco, June 1985.
M. Hebert and T. Kanade, “The 3D profile method for object recognition”, in PROC. IEEE COMPUT. SOC. CONF. COMPUT. VISION AND PATTERN RECOGNITION, San Francisco, June 1985.
C.M. Brown, “Fast display of well-tessellated surface”, COMPUT. GRAPHICS. vol. 4, no. 2, pp. 77–85, 1979.
D. Smith, “Using enhanced spherical images”, M.I.T. Artif. Intell. Lab., Cambridge, MA. A.I. Memo. 451, 1979.
B.K.P. Horn, “Extended Gaussian images”, PROC. IEEE, vol. 72, no. 12, pp. 1671–1686, 1984.
K. Ikeuchi, “Recognition of 3-D objects using the extended Gaussian image”, in PROC. 7TH INT. JOINT CONF. ARTIF. INTELL., 1981, pp. 595–600.
K. Ikeuchi, “Determining attitude of object from needle map using extended Gaussian image”, M.I.T. Artif. Intell. Lab., Cambridge, MA, A.I. Memo 714, 1983.
P. Brou, “Using the Gaussian image to find the orientation of object”, INT. J. ROBOTICS RES. vol. 3, no. 4, pp. 89–125, 1983.
J.J. Little, “Determining object attitude from extended Gaussian images”, in PROC. 9TH INT. JOINT CONF. ARTIF. INTELL., 1985, pp. 960–963.
M. Brady, J. Ponce, A. Yuille, and H. Asada, “Describing surfaces”, in PROC. 2ND INTERNATIONAL SYMPOSIUM ON ROBOTICS RESEARCH, H. Hanafusa and H. Inoue (eds) M.I.T. Press: Cambridge, MA, 1985.
P.J. Besl and R.C. Jain, “Intrinsic and extrinsic surface characteristics”, in PROC. COMPUTER VISION AND PATTERN RECOGNITION CONFERENCE. IEEE: San Francisco, 1985, pp. 226–233.
K. Ikeuchi, “Determining a depth map using a dual photometric stereo”, INT. J. ROBOTICS RES. vol. 6, no. 1, pp. 15–31, 1987.
T.O. Binford, “Visual perception by computer”, in PROC. IEEE SYSTEMS SCIENCE CYBERNETICS CONF., 1971.
R.A. Brooks, “Symbolic reasoning among 3-D models and 2-D images”, ARTIF. INTELL. vol. 17, nos. 1–3, pp. 285–348, 1981.
S.A. Shafer and T. Kanade, “The theory of straight homogeneous generalized cylinder and a taxonomy of generalized cylinders”, Carnegie Mellon University Computer Science Department, Pittsburgh, PA, CMU-CS-83–105, 1983.
M. Herman, and T. Kanade, “The 3D MOSAIC scene understanding system: incremental reconstruction of 3D scene from complex images”, CMU-CS Report, CMU-CS-84-102, 1984.
T. Lozano-Pérez, “Automatic planning of manipulator transfer movements”, IEEE TRANS. SYS. MAN. CYBERNETICS vol. SMC-1, no. 10, pp. 681–689, 1981.
R.J. Woodham, “Reflectance map techniques for analyzing surface defects in metal castings”, M.I.T. Artif. Intell. Lab., Cambridge, MA, A.I.-TR-457, 1978.
Author information
Authors and Affiliations
Additional information
This research was sponsored by the Defensc Advanced Research Projects Agency, DOD, through ARPA Order No. 4976, and monitored by the Air Force Avionics Laboratory under contract F33615-84-K-1520. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Defense Advanced Research Projects Agency or of the U.S. Government.
Rights and permissions
About this article
Cite this article
Ikeuchi, K. Generating an interpretation tree from a CAD model for 3D-object recognition in bin-picking tasks. Int J Comput Vision 1, 145–165 (1987). https://doi.org/10.1007/BF00123163
Issue Date:
DOI: https://doi.org/10.1007/BF00123163