Abstract
It is well known that there are no geometric invariants of a projection from 3D to 2D. However, given some modeling assumptions about the 3D object, such invariants can be found. The modeling assumptions should be sufficiently strong to enable us to find such invariants, but not stronger than necessary. In this paper we find such modeling assumptions for general 3D curves under affine projection. We show, for example, that if one of the two affine curvatures is known along the 3D curve, the other can be found from the curve's 2D image. We can also derive the point correspondence between the curve and its image. We also deal with point sets and direction vectors.
Similar content being viewed by others
References
Weiss, I., “Geometric invariants of shapes,” Proc. DARPA Image Understanding Workshop, Cambridge, MA, 1988, pp. 1125–1134.
Weiss, I., “Noise Resistant Invariants of Curves,” IEEE Transations on Pattern Analysis and Machine Intelligence, Vol. 15, pp. 943–948, 1993.
Rivlin, E. and Weiss, I., “Local invariants for recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 16, pp. 226–238, 1995.
J.B. Burns, R. Weiss, and E.M. Riseman, “View variation of point set and line segment features,” in Proceeding of DARPA Image Understanding Workshop, 1990, pp. 650–659.
Jacobs, D. “Space Efficient 3D Model Indexing,” Proc. CVPR, Champaign, June 1992.
P.F. Stiller, C.A. Asmuth, and C.S. Wan. “Invariant indexing and single view recognition,” In Proceedings of ARPA Image Understanding Workshop, 1994, pp. 1423–1428.
A. Zisserman, D.A. Forsyth, J.L. Mundy, C.A. Rothwell, J. Liu and N. Pillow. “3D object recognition using invariance”, Artif. Intell., Vol. 78, pp. 239–288, 1995.
J.P. Hopcroft, D.P. Huttenlocher, and P.C. Wayner. “Affine invariants for model-based recognition”, in Geometric Invariance in Machine Vision, eds. J.L. Mundy and A. Zisserman, MIT Press, Cambridge, MA, 1992.
H. Guggenheimer, Differential Geometry, Dover, New York, 1963.
A. Bruckstein, E. Rivlin, and I. Weiss. “Scale Space Invariants for Recognition,” Machine Vision and Applications, Vol. 15, No. 5, pp. 335–344, 1997.
T.O. Binford and T.S. Levitt. “Model-Based “Recognition of Objects in Complex Scenes,” Proc. DARPA Image Understanding Workshop, 1996, pp. 89–100.
M. Zerroug and R. Nevatia. “Using Invariance and Quasiinvariance for the Segmentation and Recovery of Curved Objects,” in Lecture Notes in Computer Science 825, Springer-Verlag, 1994.
P. Meer and I. Weiss. “Point/Line Correspondence under Projective Transformations,” In Proc. 11 Int. Conf. on Pattern Recognition: Computer Vision and Applications, The Hague, 1992, pp. 399–402.
D. Keren, R. Rivlin, I. Shimshoni, and I. Weiss. “Recognizing 3D Objects using Tactile Sensing and Curve Invariants,” University of Maryland Technical Report CS-TR-3812, July 1997.
C.E. Springer, Geometry and Analysis of Projective Spaces, Freeman, 1994.
E. Rivlin and I. Weiss. “Recognizing Objects Using Deformation Invariants,” Computer Vision and Image Understanding, Vol. 65, No. 1, pp. 95–108. 1997.
Weiss, I., “3D Curve Reconstruction from Uncalibrated Cameras.” University of Maryland CS-TR-3605. Also in Proc. ICPR-96, Vienna, 1996, pp. 323–327.
Weiss, I., “Geometric invariants and object recognition,” International Journal of Computer Vision, Vol. 10, pp. 207–231, 1993.
Weiss, I., “Local Projective and Affine Invariants,” Annals of Mathematics and Artificial Intelligence, Vol. 13, Nos. (3–4), pp. 203–225, 1995.
C.A. Rothwell, D.A. Forsyth, A. Zisserman, and J.L. Mundy. “Extracting Projective Structures from Single Perspective Views of 3D Point Sets”, Proc. 4th International Conference on Computer Vision, 1993, pp. 573–582.
R. Deriche, Z. Zhang, Q.T. Luong, and O.D. Faugeras, “Robust Recovery of the Epipolar Geometry for an Uncalibrated Stereo Rig,” Proc. of the European Conf. on Computer Vision 1994, Lecture Notes on Computer Science 800.
P. Beardsley, P. Torr, and A. Zisserman, “3D Model Aquisition from Ixtended Image Sequences,” ECCV 1996, Lecture notes on Computer Science, pp. 683–695, Springer-Verlag.
S.J. Maybank and O.D. Faugeras, “A Theory of Self Calibration of a Moving Camera,” IJCV, Vol. 8, No. 2, pp. 123–151, 1992.
B. Boufama and R. Mohr, “Epipole and Fundamental Matrix Estimation Using Virtual Parallax,” Proc. Int. Conf. Computer Vision, 1995, pp. 1030–1036.
Pauwels, E.J., Moons, T., Van Gool, L.J. and Oosterlinck, A., “Recognition of Planar Shapes Under Affine Distortion,” IJCV, Vol. 14, 1995.
B. Strumpel, Algorithms in Invariant Theory, Springer Verlag, New York, 1993.
Barret, E. Personal Communication.
C.A. Rothwell, Object Recognition through Invariant Indexing, Oxford University Press, Oxford, 1995.
J. Ben-Arie, Z. Wang, and R. Rao. “Iconic recognition with affine-invariant spectral signatures,” In Proc. ICPR A, Aug. 1996, pp. 672–676.
S. Carlsson. “Projectively invariant decomposition and recognition of planar shapes,” IJCV, Vol. 17, pp.193–209, 1996.
R.W. Curwen and J.L. Mundy. “Grouping planar projective symmetries,” In Proc. Image Understanding Workshop, May 1997, pp. 595–605.
L. Van Gool, T. Moons, E. Pauwels, and A. Oosterlinck. “Vision and lie' approach to invariance,” Image and Vision Computing, Vol. 13, pp. 259–277, 1995.
R.I. Hartley. “In defense of the eight-point model,” T-PAMI, Vol. 19, pp. 580–593, 1997.
D. Jacobs and R. Basri. “3–d to 2–d recognition with regions,” In Proc. CVPR, June 1997, pp. 547–553.
R. Kimmel. “Affine differential signatures for gray level images of planar shapes,” In ICPR A, pp. 45–49, 1996.
R. Mohr, L. Quan, and F. Veillon. “Relative 3D reconstruction using multiple uncalibrated images,” IJRR, Vol. 14, pp. 619–632, 1995.
P.J. Olver, G. Sapiro, and A. Tannenbaum. “Affine invariant detection: Edges, active contours, and segments,” In CVPR, pp. 520–525, 1996.
S. Peleg, A. Shashua, D. Weinshall, M. Werman, and M. Irani. “Multi-sensor representation of extended scenes using multi-view geometry,” In Image Understanding Workshop, May 1997, pp. 79–83.
A. Shashua and N. Navab. “Relative affine structure: Canonical model for 3D from 2D geometry and applications,” T-PAMI, Vol. 18, pp. 873–883, 1996.
T. Vieville, O. Faugeras, and Q.T. Luong. “Motion of points and lines in the uncalibrated case,” IJCV, Vol. 17, pp. 7–41, 1996.
T. Vieville and O.D. Faugeras. “The first order expansion of motion equations in the uncalibrated case,” CVIU, Vol. 64, pp. 128–146, 1997.
B. Vijayakumar, D.J. Kriegman, and J. Ponce. “Structure and motion of curved 3D objects from monocular silhouettes,” In CVPR, June 1996, pp. 327–334.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Weiss, I. Model-Based Recognition of 3D Curves From One View. Journal of Mathematical Imaging and Vision 10, 175–184 (1999). https://doi.org/10.1023/A:1008383224450
Issue Date:
DOI: https://doi.org/10.1023/A:1008383224450