Abstract
We propose a novel layered complex-valued neural network to reduce singular points (SP’s) in phase images to obtain digital elevation maps (DEM’s) through phase unwrapping. First we prepare a SPfree distorted image for a wrapped image data by constructive Fourier synthesis. We patch fractions of the SP-free image at the SP locations of the raw image and, then, feed it to estimation layer of the network as the initial image. The estimation layer interacts with raw-image layer with a complex-valued neurodynamics to yield a better estimation in which the SP number is reduced. The proposal reduces the calculation cost of unwrapping process and also increases the accuracy of the output DEM.
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
R.M. Goldstein, H.A. Zebker, C.L. Werner, “Satellite radar interferometry: twodimensional phase unwrapping,” Radio Science, 23(1988) 713–720
Jong-Sen Lee, A.R. Miller, K.W. Hoppel, “Statistics of phase difference and product magnitude of multi-look processed Gaussian signals,” Waves in Random Media, 4 (1994) 307–319
M. Shimada, H. Hirosawa, “Slope corrections to normalized RCS using SAR interferometry,” IEEE Trans. on Geoscience and Remote Sensing, 38 (2000) 1479–1484
R.M. Goldstein, C.L. Werner, “Radar interferogram filtering for geophysical applications,” Geophysical Research Letters, 25(1998) 4035–4038
Jong-Sen Lee, K.P. Papathanassiou, T.L. Ainsworth, M.R. Grunes, A. Reigber, “A new technique for phase noise filtering of SAR interferometric phase images,” IEEE Trans. on Geoscience and Remote Sensing, 36(1998) 1456–1465
A.B. Suksmono, A. Hirose, “Adaptive noise resuction of InSAR image based on complex-MRF model and its application to phase unwrapping problem,” IEEE Trans. on Geoscience and Remote Sensing, 40(2002) 699–709699–709
A. Hirose, M. Minami, “Complex-valued region-based-coupling image clustering neural networks for interferometric radar image processing,” IEICE Trans. on Electron., E84-C (2001) 1932–1938
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Minami, M., Hirose, A. (2003). Phase Singular Points Reduction by a Layered Complex-Valued Neural Network in Combination with Constructive Fourier Synthesis. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_112
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_112
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive