Abstract
This work aims at building a 3D graphics model of an object using multiple visual cues. Different materials and shapes may yield different visual cues such as corner, pattern, highlight, and contour on objects. These cues may appear as similar edges, peaks and intensities in the images. To obtain a correct shape, different shape recovery methods must be applied separately. The key problem is how to identify features for different shape recovery methods. We rotate an object and take a dense image sequence. In each Epipolar Plane Image of the rotation plane, we classify visual cues based on not only based on their image characteristics but also their motion behavior. Then we integrate shapes from different algorithms.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
J.Y. Zheng, “Acquiring 3D models from sequences of contours”, IEEE PAMI, Vo1.16, No.2, Feb. pp. 163–178, 1994.
J. Y. Zheng, Y. Fukagawa, T. Ohtsuka, N. Abe, “Acquiring 3D models from rotation and a highlight”, 12th ICPR, Vol. 1, pp. 331–336, 1994.
J. Y. Zheng, Y. Fukagawa, N. Abe, Shape and Model from Specular Motion, 5th ICCV, pp.92–97, 1995.
J. Y. Zheng, and F. Kishino, “Verifying and combining different visual cues into a complete 3D model”, CVPR92, pp. 777–780,1992.
J. Y. Zheng, H. Kakinoki, K. Tanaka, and N. Abe, “Acquiring 3D models from fixed point during rotation”, 3th ICARCV, Vol. 1, pp.459–463, 1994.
K. P. Horn and M. J. Brooks, “Shape from shading”, MIT Press, Cambridge, MA, 1989.
A. Pentland, “Local shading analysis”, IEEE PAMI, 6:170–187, 1984.
R. J. Woodham, “Gradient and curvature from photometric stereo including local confidence estimation”, J. Opt. Soc. Amer., Vol. 11, no. 11, 3050–3068, 1994.
J. Aloimonos and A. Bandyopadhyay, “Active vision”, 1st ICCV, pp.35–55, 1987.
J. Y. Zheng, Y. Fukagawa, and N. Abe, “3D shape estimation and model construction from specular motion in the images”, IEEE PAMI, Vol. no. 5, pp. 1997.
R. Vaillant and O. D. Faugeras, “Using extremal boundaries for 3D object modeling”, IEEE PAMI, Vol. 14, No. 2, pp. 157–173. Feb. 1992.
H. Baker, and R. Bolles, “Generalizing epipolar-plane image analysis on the spatiotemporal surface”, CVPR-88, pp.2–9, 1988.
J. Y. Zheng, H. Kakinoki, K. Tanaka and N. Abe “Computing 3D Models of Rotating Objects from Moving Shading”, ICPR96, Vol. 1, 800–804, 1996.
J. Lu and J. Little, “Reflectance function estimation and shape recovery from image sequence of a rotating object”, 5th ICCV, pp. 80–86, 1995.
M. Oren, S. K. Nayar, “A theory of specular surface geometry”, 5th ICCV, pp. 740–747, 1995.
P. Giblin, R. Weiss, “Reconstruction of surface from profiles”, 1st ICCV, pp. 136–144, 1987.
J. Y. Zheng, A. Murata, N. Abe, “Reconstruction of 3D Models from Specular Motion Using Circular Lights”, 13th ICPR, Vol. 1, pp. 869–873, (1996).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zheng, J.Y., Murata, A., Abe, N. (1997). Generating 3D models of objects using multiple visual cues in image sequences. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63931-4_253
Download citation
DOI: https://doi.org/10.1007/3-540-63931-4_253
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63931-2
Online ISBN: 978-3-540-69670-4
eBook Packages: Springer Book Archive