Abstract
In this paper we present a new filter based on Gaussian functions for the extraction of local 3D orientation information. Compared with current 3D steerability approaches our method achieves higher orientation resolution with lower complexity. This property enables us to solve challenging problems like complex surface analysis and multiple motion estimation. This new method decomposes a sphere with a set of overlap** basis filters which are isotropic in the feature space. We study the problem of non-uniform distribution of the spherical coordinates and discuss the application of a weighting compensation function in the computation of the 3D orientation signature. Comparisons show that our method is more efficient and robust than the SD Hough transform.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
E.H. Adelsonand J.R. Bergen. Spatiotemporal energy models for the perception of motion. Journal of the Optical Society of America, 1(2)284–299, 1985.
M.T. Andersson. Controllable Multidimensional Filters and Models in Low Level Computer Vision. PhD thesis, Department of Electrical Engineering, Linkoe** University, Linkoe**, Sweden, 1992.
W.Yu, K. Daniilidis, S. Beauchemin, and G. Sommer. Detection and characterization of multiple motion points. In IEEE Conf. Computer Vision and Pattern Recognition, volume I, pages 171-177, Fort Collins, CO, June 23-25, 1999.
J.G. Daugman. Uncertainty relation for resolution in space, spatial frequency and orientation optimized by two-dimensional Visual cortical filters. Journal of the Optical Society of America, 2(7)1160–1169, 1985.
W.T. Freeman and E.H. Adelson. The design and use of steerable filters. IEEE Trans. Pattern Analysis and Machine Intelligence, 13:891–906, 1991.
J. Bigün, G.H. Granlund and J. Wiklund. Multidimensional orientation estimation with application to texture analysis and optical flow. IEEE Trans. Pattern Analysis and Machine Intelligence, 13(8)775–790, 1991.
B.K.P. Horn. Robot Vision. MIT Press, 1986.
Chung-Lin Huang and Yng-Tsang Chen. Motion estimation method using a 3d steerable filter. Image and Vision Computing, 13:21–32, 1995.
M. Michaelis and G. Sommer. A Lie group approach to steerable filters. Pattern Recognition Letters, 16:1165–1174, 1995.
P. Perona. Deformable kernels for early vision. IEEE Trans. Pattern Analysis and Machine Intelligence, 17(5)488–499, 1995.
M. Irani, B. Rousso, and S. Peleg. Computing occluding and transparent motions. International Journal of Computer Vision, 12:5–16, 1994.
P. Schröder and W. Sweldens. Spherical wavelets: Efficiently representing functions on the sphere. Computer Graphics Proceedings (SIGGRAPH 95), pages 161-172, 1995.
M. Shizawa and K. Mase. A unified computational theory for motion transparency and motion boundaries based on eigenenergy analysis. In IEEE Conf. Computer Vision and Pattern Recognition, pages 289-295, Maui, Hawaii, June 3-6, 1991.
E.P. Simoncelli and H. Farid. Steerable wedge filters for local orientation analysis. IEEE Trans. Image Processing, 5(9)1377–1382, 1996.
Y. Weiss and E.H. Adelson. A unified mixture framework for motion segmentation: Incorporating spatial coherence and estimating the number of models. In IEEE Conf. Computer Vision and Pattern Recognition, pages 321-326, San Fransisco, CA, June 18-20, 1996.
W. Yu. Local Orientation Analysis in Images and Image Sequences Using Steerable Filters. PhD thesis, Institute of Computer Science, University Kiel, Germany, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yu, W., Daniilidis, K., Sommer, G. (2000). A New 3D Orientation Steerable Filter. In: Sommer, G., Krüger, N., Perwass, C. (eds) Mustererkennung 2000. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-59802-9_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-59802-9_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67886-1
Online ISBN: 978-3-642-59802-9
eBook Packages: Springer Book Archive