Abstract
This paper proposes a segmentation method of SAR (Synthetic Aperture Radar) images based on a SOM (Self-Organizing Map) neural network. SAR images are obtained by observation using microwave sensor. For teacher data generation, they are segmented into the drift ice (thick and thin), and sea regions manually, and then their features are extracted from partitioned data. However they are not necessarily effective for neural network learning because they might include incorrectly segmented data. Therefore, in particular, a multi-step SOM is used as a learning method to improve reliability of teacher data, and carry out classification. This process enable us to fix all mistook data and segment the SAR image data using just data. The validity of this method was demonstrated by means of computer simulations using the actual SAR images.
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
Bhanu, B., Jones III, G.: Object Recognition Results Using MSTAR Synthetic Aperture Radar Data. In: Proc. of the IEEE Workshop CVBVS 2000, Session C: Synthetic Aperture Radar Image Analysis (2000)
Bors, A., Hancock, E., Wilson, R.: 3-D Terrain from Synthetic Aperture Radar Images. In: Proc. of the IEEE Workshop on CVBVS 2000, Session C: Synthetic Aperture Radar Image Analysis (2000)
Betti, M.B., Mecocci, A.: Using a wavelet-based fractal feature to improve texture discrimination on SAR images. In: Proc. of the 1997 International Conference on Image Processing (1997)
Kurita, T., Hotta, K., Mishima, T.: Scale Invariant Recognition of Face Image Using Higher Order Local Autocorrelation Features of Log-Polar Image. IEICE D-II J80-DII(8), 2209–2217 (1999) (in Japanese)
Kreutz, M., Volpel, B., Janben, H.: Scale-invariant image recognition based on higherorder autocorrelation features. Pattern Recognition 29(1) (1996)
Galloway, M.M.: Texture Analysis Using Gray Level Run Lengths. Computer Graphics and Image Processing 4, 172–179 (1975)
Nagao, T., Mitsukura, Y., Fukumi, M., Akamatsu, N.: Drift ICE Recognition using Remote Sensing Data by Neural Networks. In: CD-ROM Proc. of ICONIP 2002, Singapore, #1325, pp. 1–5 (2002)
Kohonen, T.: The Self Organizing Map. Proc. of The IEEE 78(9), 1464–1480 (1999)
Tadokoro, S., Nagao, T., Fukumi, M., Akamatsu, N.: Research on Drift Ice Detection from SAR Images Using Bio-Information Processing. In: Proc. of SIP 2003, Hawaii, pp. 167–172 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fukumi, M., Nagao, T., Mitsukura, Y., Khosla, R. (2005). Drift Ice Detection Using a Self-organizing Neural Network. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3681. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11552413_181
Download citation
DOI: https://doi.org/10.1007/11552413_181
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28894-7
Online ISBN: 978-3-540-31983-2
eBook Packages: Computer ScienceComputer Science (R0)