Linear and Incremental Acquisition of Invariant Shape Models From Image Sequences
|
Abstract—We show how to automatically acquire Euclidian shape representations of objects from noisy image sequences under weak perspective. The proposed method is linear and incremental, requiring no more than pseudoinverse. A nonlinear, but numerically sound preprocessing stage is added to improve the accuracy of the results even further. Experiments show that attention to noise and computational techniques improves the shape results substantially with respect to previous methods proposed for ideal images.
[1] 512 R. C. Bolles,H. H. Baker,, and D. H. Marimont,“Epipolar-plane image analysis: An approachto determining structure from motion,” Int’l J. of Computer Vision, vol. 1, no. 1, pp. 7-55, 1987.
[2] W.E.L. Grimson,D.P. Huttenlocher,, and D.W. Jacobs,“A study of affine matching with bounded sensor error,” Proc. European Conf. Computer Vision, pp. 291-306, 1992.
[3] B.K.P. Horn,H.M. Hilden,, and S. Negahdaripour,“Closed-form solution of absolute orientation using orthonormal matrices,” J. Optical Soc. Am. A, vol. 5, no. 7, pp. 1,127-1,135, July 1988.
[4] B.K.P. Horn, “Relative Orientation,” Int'l J. Computer Vision, vol. 4, pp. 59-78, 1990.
[5] D.J. Heeger and A. Jepson,“Visual perception of three-dimensional motion,” Technical Report 124. MIT Media Laboratory, Cambridge, MA: Dec. 1989.
[6] R. Kumar and A.R. Hanson, “Sensitivity of the Pose Refinement Problem to Accurate Estimation of Camera Parameters,” Proc. Int'l Conf. Computer Vision, pp. 365 369, 1990.
[7] J.J. Koenderink and A.J. van Doorn,“Affine structure from motion,” J. Optical Soc. Am., vol. 8, no. 2, pp. 377-385, 1991.
[8] D. T. Lawton,“Processing translational motion sequences,” Computer Graphics and Image Processing, vol. 22, pp. 116-144, 1983.
[9] H.C. Longuet-Higgins,“A computer algorithm for reconstructing a scene fromtwo projections,” Nature, vol. 293, pp. 133-135, Sept. 1981.
[10] H.S. Sawhney,J. Oliensis,, and A.R. Hanson,“Description and reconstruction from image trajectoriesof rotational motion,” Proc. Third Int’l Conf. Computer Vision, Osaka, Japan, IEEE, Washington, D.C., pp. 494-498, 1990.
[11] C. Tomasi and T. Kanade,“Shape and motion from image streams: Afactorization method-3 detection and tracking of point features,” Technical Report CMU-CS-91-132. Carnegie Mellon Univ. Pittsburgh, Pa.: April 1991.
[12] C. Tomasi and T. Kanade, "Shape and Motion From Image Streams Under Orthography: A Factorization Method," Int'l J. Computer Vision, vol. 9, no. 2, pp. 137-154, 1992.
[13] S. Ullman and R. Basri, "Recognition by Linear Combinations of Models," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, pp. 992-1006, 1991.
[14] S. Ullman,The Interpretation of Visual Motion.Cambridge, Mass.: The MIT Press, 1979.
[15] D. Weinshall,“Model based invariants for 3D vision,” Int’l J. Computer Vision, vol. 10, no. 1, pp. 27-42, 1993.
[16] D. Weinshall and C. Tomasi,“Linear and incremental acquisition ofinvariant shape models from image sequences,” RC 18549 (81133), IBM T. J. Watson Research Center, 1992.
Index Terms:
Structure from motion, linear reconstruction, factorization method, affine shape, Euclidean shape, weak perspective, Gramian, affine coordinates.
Citation:
Daphna Weinshall, Carlo Tomasi, "Linear and Incremental Acquisition of Invariant Shape Models From Image Sequences," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 5, pp. 512-517, May 1995, doi:10.1109/34.391392
PURCHASE ARTICLE: $19
IEEE Xplore Subscribers
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb