Abstract
Junctions play an important role in motion analysis. Approaches based on the structure tensor have become the standard for junction detection. However, the structure tensor is not able to classify junctions into different types (L, T, Y, X etc.). We propose to solve this problem by the wedge channel representation. It is based on the same computational steps as used for the (anisotropic) structure tensor, but stores results into channel vectors rather than tensors. Due to one-sided channel smoothing, these channel vectors not only represent edge orientation (as existing channel approaches do) but edge direction. Thus junctions cannot only be detected, but also fully characterized.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bigün, J., Granlund, G.: Optimal Orientation Detection of Linear Symmetry. In: Proc. 1st Intl. Conf. on Computer Vision. ICCV 87, pp. 433–438 (1987)
Felsberg, M., Forssen, P.-E., Scharr, H.: Efficient Robust Smoothing of Low-Level Signal Features, Linköping University, Computer Vision Laboratory, Technical Report LiTH-ISY-R-2619 (2004)
Felsberg, M., Granlund, G.H.: Anisotropic Channel Filtering. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 755–762. Springer, Heidelberg (2003)
Granlund, G.: An Associative Perception-Action Structure Using a Localized Space Invariant Information Representation. In: Sommer, G., Zeevi, Y.Y. (eds.) AFPAC 2000. LNCS, vol. 1888, Springer, Heidelberg (2000)
Förstner, W.: A Feature Based Correspondence Algorithm for Image Matching. Intl. Arch. of Photogrammetry and Remote Sensing 26, 150–166 (1986)
Harris, C.G., Stevens, M.J.: A Combined Corner and Edge Detector. In: Proc. of 4th Alvey Vision Conference (1988)
Köthe, U.: Edge and Junction Detection with an Improved Structure Tensor. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 25–32. Springer, Heidelberg (2003)
Michaelis, M.: Low Level Image Processing Using Steerable Filters, PhD Thesis, GSF-BEricht 30/95, Christian-ALbrechts-Universität Kiel (1995)
Nagel, H.-H., Gehrke, A.: Spatiotemporally Adaptive Estimation and Segmentation of OF-fields. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 86–102. Springer, Heidelberg (1998)
Snippe, H.P., Koenderink, J.J.: Discrimination Thresholds for Channel-Coded Systems. Biological Cybernetics 66, 543–551 (1992)
Spies, H., Johansson, B.: Directional Channel Representation for Multiple Line-Endings and Intensity Levels. In: Proc. IEEE Intl. Conf. on Image Processing. ICIP 03, IEEE Computer Society Press, Los Alamitos (2003)
Yu, W.: Local Orientation Analysis in Images and Image Sequences Using Sterrable Filters, PhD Thesis, Bericht Nr. 2012, Christian-Albrechts-Universität Kiel (2000)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Köthe, U. (2007). Boundary Characterization Within the Wedge-Channel Representation. In: Jähne, B., Mester, R., Barth, E., Scharr, H. (eds) Complex Motion. IWCM 2004. Lecture Notes in Computer Science, vol 3417. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69866-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-69866-1_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69864-7
Online ISBN: 978-3-540-69866-1
eBook Packages: Computer ScienceComputer Science (R0)