What can two images tell us about a third one?
Tóm tắt
This paper discusses the problem of predicting image features in an image from image features in two other images and the epipolar geometry between the three images. We adopt the most general camera model of perspective projection and show that a point can be predicted in the third image as a bilinear function of its images in the first two cameras, that the tangents to three corresponding curves are related by a trilinear function, and that the curvature of a curve in the third image is a linear function of the curvatures at the corresponding points in the other two images. Our analysis relies heavily on the use of the fundamental matrix which has been recently introduced (Faugeras et al, 1992) and on the properties of a special plane which we call the trifocal plane. Though the trinocular geometry of points and lines has been very recently addressed, our use of the differential properties of curves for prediction is unique. We thus completely solve the following problem: given two views of an object, predict what a third view would look like. The problem and its solution bear upon several areas of computer vision, stereo, motion analysis, and model-based object recognition. Our answer is quite general since it assumes the general perspective projection model for image formation and requires only the knowledge of the epipolar geometry for the triple of views. We show that in the special case of orthographic projection our results for points reduce to those of Ullman and Basri (Ullman and Basri, 1991). We demonstrate on synthetic as well as on real data the applicability of our theory.
Tài liệu tham khảo
Ayache, N. and Lustman, F. 1987. Fast and reliable passive trinocular stereovision. In Proceedings ICCV'87, London, pages 422–427. IEEE.
Barrett, Eamon B., Brill, Michael H., Haag, Nils N. and Payton, Paul M. 1992. Invariant Linear Methods in Photogrammetry and Model-Matching. In Joseph L. Mundy and Andrew Zimmerman, editors, Geometric Invariance in Computer Vision, chapter 14. MIT Press.
Basri, Ronen. 1993. On the Uniqueness of Correspondence under Orthographic and perspective Projections. In Proc. of the Image Understanding Workshop, pages 875–884.
Deriche, R. 1987. Using canny's criteria to derive an optimal edge detector recursively implemented. In The International Journal of Computer Vision, volume 2, pages 15–20.
Faugeras, Olivier D. 1992. What can be seen in three dimensions with an uncalibrated stereo rig. In Giulio Sandini, editor, Proceedings of the 2nd European Conference on Computer Vision, pages 563–578. Springer-Verlag, Lecture Notes in Computer Science 588.
Faugeras, Olivier D. 1993. Three-Dimensional Computer Vision: a Geometric Viewpoint. MIT Press.
Faugeras, Olivier D., Luong, Tuan and Maybank, Steven. 1992. Camera self-calibration: theory and experiments. In Giulio Sandini, editor, Proceedings of the 2nd European Conference on Computer Vision, pages 321–334. Springer-Verlag, Lecture Notes in Computer Science 588.
Hartley, Richard. 1994. Lines and points in three views-an integrated approach. In Proc. Image Understanding Workshop Monterey, California.
Hartley, Richard, Gupta, Rajiv and Chang, Tom. 1992. Stereo from Uncalibrated Cameras. In Proceedings of CVPR92 Urbana-Champaign, Illinois, pages 761–764.
Ito, M. and Ishii, A. 1986 Three-View Stereo Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 8:524–532.
Kanatani, Kenichi. 1991. Computational Projective Geometry. CVGIP: Image Understanding, 54(3):333–348.
Kitamura, Yoshifumi and Yachida, Masahiko. 1990. Three dimensional data acquisition by trinocular vision. Advanced Robotics, 4(1):29–42. Robotics Society of Japan.
Luong, Quang-Tuan, Deriche, Rachid, Faugeras, Olivier and Papadopoulo, Théodore. 1993. On Determining the Fundamental Matrix: Analysis of Different Methods and Experimental Results. Technical Report 1894, INRIA.
Milenkovic, V.J. and Kanade, T. 1985. Trinocular Vision Using Photometric and Edge Orientation Constraints. In Proceedings of DARPA Image Understanding Workshop, pages 163–175.
Mohr, R. and Arbogast, E. 1990. It can be done without camera calibration. Pattern Recognition Letters, 12:39–43.
Mohr, Roger, Morin, Luce and Grosso, Enrico. 1992. Relative positioning with uncalibrated cameras. In J.L. Mundy and A. Zisserman, editors, Proceedings of DARPA-ESPRIT Workshop on Applications of Invariance in Computer Vision, Artificial Intelligence Series, chapter 22, pages 440–460. MIT Press.
Mundy, Joseph L.and Zimmerman, Andrew editors. 1992. Geometric Invariance in Computer Vision. MIT Press.
Pietikainen, M. and Harwood, D. 1986. Depth from three-camera stereo. In Proc. International Conference on Computer Vision and Pattern Recognition, pages 2–8. IEEE. Miami Beach, Florida.
Pietikainen, M. and Harwood, D. Progress in trinocular stereo. In Proceedings NATO Advanced Workshop on Real-time Object and Environment Measurement and classification, Maratea, Italy, August 31 – September 3 1987.
Quan, L. 1994. Invariants of 6 points from 3 uncalibrated images. In J-O.Eklundh, editor, Proceedings of the 3rd European Conference on Computer Vision, Stockholm, Sweden, pages 459–470, Berlin, Germany, Springer-Verlag.
Robert, L. 1993. Perception Stéréoscopique de Courbes et de Surfaces Tridimensionelles. Applications à la Robotique Mobile. PhD thesis, Ecole Polytechnique.
Robert, Luc and Faugeras, Olivier D. 1991. Curve-Based Stereo: Figural Continuity and Curvature. In CVPR91, pages 57–62. IEEE, Maui, Hawai.
Semple, J.G. and Kneebone, G.T. 1952. Algebraic Projective Geometry. Oxford: Clarendon Press, Reprinted 1979.
Shashua, A. 1993. On geometric and algebraic aspects of 3d affine and projective structures from perspective 2d views. Technical Report A.I. Memo No. 1405, MIT.
Shashua, Amnon. 1993. Projective Depth: A Geometric Invariant for 3D Reconstruction from Two Perspective\Orthographic Views and for Visual Recognition. In Proc. Fourth International Conference on Computer Vision, pages 583–590.
Shashua, Amnon. Algebraic Functions for Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994. To appear.
Ullman, Shimon and Basri, Ronen. 1991. Recognition by Linear Combinations of Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(10):992–1006.
Yachida, M. 1986. 3D Data Acquisition by Multiple Views. In O.D.Faugeras and G.Giralt, editors, Robotics Research: the Third International Symposium, pages 11–18. MIT Press, Cambridge, Mass.
Yang, D. and Illingworth, J. 1992. Line based trinocular stereo. In Proceedings of the British Machine Vision Conference, Leeds, UK, pages 327–336.