Abstract
Features like junctions and corners are a rich source of information for image understanding. We present a novel theoretical framework for the analysis of such 2D features in scalar and multispectral images. We model the features as occluding superpositions of two different orientations and derive a new constraint equation based on the tensor product of two directional derivatives. The eigensystem analysis of a 3 × 3-tensor then provides the so-called mixed-orientation parameters (MOP) vector that encodes the two orientations uniquely, but only implicitly. We then show how to separate the MOP vector into the two orientations by .nding the roots of a second-order polynomial. Based on the orientations, the occluding boundary and the center of the junction are easily determined. The results con.rm the validity, robustness, and accuracy of the approach.
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
Aach, T., Stuke, I., Mota, C., Barth, E.: Estimation of multiple local orientations in image signals. In: Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, Montreal, Canada, May 17-21, vol. III, pp. 553–556 (2004)
Adelson, E.H.: Lightness perception and lightness illusions. In: Gazzaniga, M. (ed.) The New Cognitive Neurosciences, pp. 339–351. MIT Press, Cambridge (2000)
Barth, E.: The minors of the structure tensor. In: Sommer, G. (ed.) Mustererkennung 2000, pp. 221–228. Springer, Berlin (2000)
Barth, E., Caelli, T., Zetzsche, C.: Image encoding, labeling, and reconstruction from differential geometry. CVGIP: Graphical Model and Image Processing 55(6), 428–446 (1993)
Barth, E., Stuke, I., Aach, T., Mota, C.: Spatio-temporal motion estimation for transparency and occlusion. In: Proc. IEEE Int. Conf. Image Processing, Barcelona, Spain, September 14-17, vol. III, pp. 69–72. IEEE Signal Processing Soc (2003)
Barth, E., Stuke, I., Mota, C.: Analysis of motion and curvature in image sequences. In: Proc. IEEE Southwest Symp. Image Analysis and Interpretation, Santa Fe, NM, April 7-9, pp. 206–210. IEEE Computer Press, Los Alamitos (2002)
Bigün, J., Granlund, G.H., Wiklund, J.: Multidimensional orientation estimation with application to texture analysis and optical flow. IEEE Trans. Pattern Analysis and Machine Intelligence 13(8), 775–790 (1991)
Di Zenzo, S.: A note on the gradient of a multi-image. Computer Vision, Graphics, and Image Processing 33, 116–125 (1986)
Förstner, W., Gülch, E.: A fast operator for detection and precise locations of distinct points, corners, and centres of circular features. In: Intercommission Conference on Fast Processing of Photogrammetric Data, pp. 281–305 (1987)
Freeman, W.T., Adelson, E.H.: The design and use of steerable filters. IEEE Trans. Pattern Analysis and Machine Intelligence 13(9), 891–906 (1991)
Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. The Fourth Alvey Vision Conference, pp. 147–152 (1988)
Huffman, D.A.: Impossible objects as non-sense sentences. Machine Intelligence VI, 295–323 (1971)
Kitchen, L., Rosenfeld, A.: Gray level corner detection. Pattern Recognition Letters, 95–102 (1982)
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)
Mota, C., Barth, E.: On the uniqueness of curvature features. In: Baratoff, G., Neumann, H. (eds.) Dynamische Perzeption, Köln. Proceedings in Artificial Intelligence, vol. 9, pp. 175–178. Infix Verlag (2000)
Mota, C., Stuke, I., Barth, E.: Analytic solutions for multiple motions. In: Proc. IEEE Int. Conf. Image Processing, Thessaloniki, Greece, October 7-10, vol. II, pp. 917–920. IEEE Signal Processing Soc. (2001)
Nagel, H.H., Enkelmann, W.: Investigation of second order greyvalue variations to estimate corner point displacements. In: International Conference on Pattern Recognition, pp. 768–773 (1982)
Parida, L., Geiger, D., Hummel, R.: Kona:Amulti-junction detector using minimum description length principle. In: Pelillo, M., Hancock, E.R. (eds.) EMMCVPR 1997. LNCS, vol. 1223, pp. 51–65. Springer, Heidelberg (1997)
Rohr, K.: Recognizing corners by fitting parametric models. International Journal of Computer Vision 9, 213–230 (1992)
Stuke, I., Aach, T., Barth, E., Mota, C.: Analysing superimposed oriented patterns. In: Proc. IEEE Southwest Symp. Image Analysis and Interpretation, Lake Tahoe, NV, March 28-30, pp. 133–137 (2004)
Stuke, I., Aach, T., Mota, C., Barth, E.: Estimation of multiple motions: regularization and performance evaluation. In: Vasudev, B., Hsing, T.R., Tescher, A.G., Ebrahimi, T. (eds.) Image and Video Communications and Processing 2003, May 2003. Proceedings of SPIE, vol. 5022, pp. 75–86 (2003)
Tomasi, C., Kanade, T.: Detection and tracking of point features. Technical report, Carnegie Mellon University Technical, Report CMU-CS-91-132 (April 1991)
Zetzsche, C., Barth, E., Wegmann, B.: The importance of intrinsically twodimensional image features in biological vision and picture coding. In: Watson, A.B. (ed.) Digital Images and Human Vision, October 1993, pp. 109–138. MIT Press, Cambridge (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mota, C., Stuke, I., Aach, T., Barth, E. (2004). Estimation of Multiple Orientations at Corners and Junctions. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds) Pattern Recognition. DAGM 2004. Lecture Notes in Computer Science, vol 3175. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28649-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-28649-3_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22945-2
Online ISBN: 978-3-540-28649-3
eBook Packages: Springer Book Archive