Abstract
A new technique to recognise 3D free-form objects via registration is proposed. This technique attempts to register a free-form surface, represented by a set of % MathType!MTEF!2!1!+-% feaafeart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaaGOmamaala% aabaGaaGymaaqaaiaaikdaaaGaamiraaaa!38F8!\[2\frac{1}{2}D\] sensed data points, to the model surface, represented by another set of % MathType!MTEF!2!1!+-% feaafeart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaaGOmamaala% aabaGaaGymaaqaaiaaikdaaaGaamiraaaa!38F8!\[2\frac{1}{2}D\] model data points, without prior knowledge of correspondence or view points between the two point sets. With an initial assumption that the sensed surface be part of a more complete model surface, the algorithm begins by selecting three dispersed, reliable points on the sensed surface. To find the three corresponding model points, the method uses the principal curvatures and the Darboux frames to restrict the search over the model space. Invariably, many possible model 3-typles will be found. For each hypothesized model 3-tuple, the transformation to match the sensed 3-tuple to the model 3-tuple can be determined. A heuristic search is proposed to single out the optimal transformation in low order time. For realistic object recognition or registration, where the two range images are often extracted from different view points of the model, the earlier assumption that the sensed surface be part of a more complete model surface cannot be relied on. With this, the sensed 3-tuple must be chosen such that the three sensed points lie on the common region visible to both the sensed and model views. We propose an algorithm to select a minimal non-redundant set of 3-tuples such that at least one of the 3-tuples will lie on the overlap. Applying the previous algorithm to each 3-tuple within this set, the optimal transformation can be determined. Experiments using data obtained from a range finder have indicated fast registration for relatively complex test cases. If the optimal registrations between the sensed data (candidate) and each of a set of model data are found, then, for 3D object recognition purposes, the minimal best fit error can be used as the decision rule.
Similar content being viewed by others
References
Arman, F. and Aggarwal, J.K. 1993. Model-Based Object Recognition in Dense-Range Images—A Review. ACM Computing Surveys, 25(1):5–43.
Arun, K.S., Huang, T.S., and Blostein, S.D. 1987. Least-Squares Fitting of Two 3-D Point Sets. IEEE Trans. Patt. Anal. Machine Intell., 9(5):698–700.
Basri, R. and Ullman, S. 1993. The Alignment of Objects with Smooth Surfaces. CVGIP: Image Understanding, 57(3):331–345.
Bergevin, R., Laurendeau, D., and Poussart, D. 1992. Estimating The 3D Rigid Transformation Between Two Range Views of a Complex Object. 11th IAPR, Int'l Conf. Patt. Recog., The Hague, The Netherlands, Aug. 30–Sep. 3, 1992, pp. 478–482.
Besl, P.J. and Jain, R.C. 1985. Three-Dimensional Object Recognition. ACM Computing Surveys, 17(1):75–145.
Besl, P.J. and Jain, R.C. 1986. Invariant Surface Characteristics for 3D Object Recognition in Range Images. Comput. Vision, Graphics, Image Processing, 33:33–80.
Besl, P.J. and McKay, N.D. 1992. A Method for Registration of 3-D Shapes. IEEE Trans. Patt. Anal. Machine Intell., 14(2):239–256.
Brou, P. 1984. Using The Gaussian Image to find the Orientation of Objects. Int'l Journal of Robotics Research, 3(4):89–125.
Chen, C.H. and Kak, A.C. 1989. A Robot Vision System for Recognizing 3-D Objects in Low Order Polynomial Time. IEEE Trans. Syst., Man Cybernetics, 19(6):1535–1563.
Chen, Y. and Medioni, G. 1992. Object Modelling by Registration of Multiple Range Images. Image Vision Computing, 10(3):145–155.
Delingette, H., Hebert, M., and Ikeuchi, K. 1993. A Spherical Representation for the Recognition of Curved Objects. 4th Int'l Conf. Comput. Vision, Berlin, Germany, 11–14 May, 1993, pp. 103–112.
Dun, J. 1990. Shape Measurement Using a Puma 500. Technical Report GIRD 16011-7.
Faugeras, O.D. and Hebert, M. 1986. The Representation, Recognition, and Locating of 3-D Objects. Int'l Journal of Robotics Research, 5(3):27–52.
Flynn, P.J. and Jain, A.K. 1991. BONSAI: 3-D Object Recognition Using Constrained Search. IEEE Trans. Patt. Anal. Machine Intell., 13(10):1066–1075.
Grimson, W.E.L. and Lozano-Perez, T. 1984. Model-based Recognition and Localization from Sparse Range or Tactile Data. Int'l Journal of Robotics Research, 3(3):3–35.
Gueziec, A. and Ayache, N. 1994. Smoothing and Matching of 3D Space Curves. Int. Journal of Computer Vision, 12(1):79–104.
Hall, E.L. and McPherson, C.A. 1982. Measuring Curved Surfaces for Robot Vision. Computer, 15(12):42–54.
Higuchi, K., Hebert, M., and Ikeuchi, K. 1994. Building 3-D Models from Unregistered Range Images. Int'l Conf. Robotics and Automation, San Diego.
Horn, B.K.P. 1984. Extended Gaussian Images. Proc. IEEE, 72:1656–1678.
Huttenlocher, D.P. and Ullman, S. 1990. Recognizing Solid Objects by Aligning with an Image. Int. Journal of Computer Vision, 5(2):195–212.
Ikeuchi, K. 1981. Recognition of 3-D Objects Using the Extended Gaussian Image. Proc. 7th Int. Joint Conf. Artificial Intelligence, Vancouver, B.C., Canada, Aug. 24–28, 1981, pp. 595–500.
Li, S.Z. 1992. Object Recognition from Range Data Prior to Segmentation. Image Vision Computing, 10(8):566–576.
Liang, P. and Todhunter, J.S. 1990. Representation and Recognition of Surface Shapes in Range Images: A Differential Geometry Approach. CVGIP, 52:78–109.
Lipschutz, M.M. 1969. Differential Geometry. McGraw-Hill: New York.
Nilsson, N.J. 1971. Problem-Solving Methods in Artificial Intelligence, McGraw-Hill: New-York.
Oshima, M. and Shirai, Y. 1983. Object Recognition Using Three-Dimensional Information. IEEE Trans. Patt. Anal. Machine Intell., 5(4):353–361.
Potmesil, M. 1983. Generating Models of Solid Objects by Matching 3D Surface Segments. Proc. 8th Int'l Joint Conf. Artificial Intell., Karlsruhe, West Germany, pp. 1089–1093.
Stein, F. and Medioni, G. 1992. Structural Indexing: Efficient 3-D Object Recognition. IEEE Trans. Patt. Anal. Machine Intell., 14(2):125–145.
Ullman, S. 1989. Aligning Pictorial Descriptions: An Approach to Object Recognition. Cognition, 32:193–254.
Vefnuri, B.C. and Aggarwal, J.K. 1988. Localization of Objects from Range Data. IEEE Conf. Comput. Vision Patt. Recog., pp. 893–898.
Yokoya, N. and Levine, M.D. 1989. Range Image Segmentation Based on Differential Geometry: A Hybrid Approach. IEEE Trans. Patt. Anal. Machine Intell., 11(6):643–649.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chua, C.S., Jarvis, R. 3D free-form surface registration and object recognition. Int J Comput Vision 17, 77–99 (1996). https://doi.org/10.1007/BF00127819
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF00127819