Abstract
This paper presents an algorithm for detecting, localizing and grouping instances of repeated scene elements. The grouping is represented by a graph where nodes correspond to individual elements and arcs join spatially neighboring elements. Associated with each arc is an affine map that best transforms the image patch at one location to the other. The approach we propose consists of 4 steps: (1) detecting “interesting” elements in the image; (2) matching elements with their neighbors and estimating the affine transform between them; (3) growing the element to form a more distinctive unit; and (4) grouping the elements. The idea is analogous to tracking in dynamic imagery. In our context, we “track” an element to spatially neighboring locations in one image, while in temporal tracking, one would perform the search in neighboring image frames.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
M. Armstrong, A. Zisserman, and P. Beardsley. “Euclidean Structure from Uncalibrated Images”. In Proc. British Machine Vision Conference, 1994.
M. Fleck, D. Forsyth, and C. Bregler. “Finding Naked People”. To appear in ECCV, 1996.
W. Förstner. “Image Matching”. In R. Haralic and L. Shapiro, “Computer and Robot Vision”, chapter 16. Addison-Wesley, 1993.
J. Gårding. “Surface orientation and curvature from differential texture distortion”. In Fifth Intl. Conf. Computer Vision, pages 733–739, 1995.
J. Gårding and T. Lindeberg. “Direct Estimation of Local Surface Shape in a Fixating Binocular Vision System”. In Proc. Euro. Conf. Computer Vision, 1994.
J. Liu, J. Mundy, and E. Walker. “Recognizing Arbitrary Objects from Multiple Projections”. In Proc. Asian Conf. Computer Vision, 1993.
J. Liu, J. Mundy, and A. Zisserman. “Grouping and Structure Recovery for Images of Objects with Finite Rotational Symmetry”. In Proc. Asian Conf. Computer Vision, 1995.
B.D. Lucas and T. Kanade. “An Iterative Image Registration Technique with an Application to Stereo Vision”. In Proc. 7th Intl. Joint Conf. on Art. Intell., 1981.
J. Malik and P. Perona. “Preattentive Texture Discrimination with Early Vision Mechanisms”. J. Opt. Soc. Am. A, 7(5):923–932, 1990.
J. Malik and R. Rosenholtz. “Recovering Surface Curvature and Orientation from Texture Distortion: a Least Squares Algorithm and Sensitivity Analysis”. Proc. Third Euro. Conf. Computer Vision, pages 353–364, Sweden, 1994.
J. Malik and R. Rosenholtz. “Computing Local Surface Orientation and Shape from Texture for Curved Surfaces”. To appear in the International Journal of Computer Vision, 1996.
J.L. Mundy and A. Zisserman. “Repeated structures: image correspondence constraints and 3D structure recovery.”. In J.L. Mundy, A. Zisserman, and D.A. Forsyth, editors, Applications of invariance in computer vision. 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leung, T., Malik, J. (1996). Detecting, localizing and grouping repeated scene elements from an image. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015565
Download citation
DOI: https://doi.org/10.1007/BFb0015565
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61122-6
Online ISBN: 978-3-540-49949-7
eBook Packages: Springer Book Archive