Presentation 2005/3/21
Adaptive Radar-Image Clustering System That Focuses Attention on Variance of Pixel Value Correlations in Spatial and Frequency Domains
Takahiro HARA, Akira HIROSE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, we describe a plastic landmaine detecting system which deals with radar images obtained by an interferometric ground penetrating radar at multiple frequencies. The system realizes high-resolutional imaging by using wide-range frequecy scan. Moreover, the system interprets the obtained data, which consist of in- and quadrature-phase components, as complex amplitude. The system adaptively classifies the complex-valued texture in spatial and frequency domains with the use of a Complex-valued Self-Organizing Map(C-SOM) and visualizes plastic landmines buried in the ground. Furthermore, we mention the fact that the system realizes faster and better clustering by focusing attention on the variance of pixel value correlations, out of a variety of texture features, in spatial and frequency domains.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Plastic landmine / Interferometric radar / Complex-valued Self-Organizing Map / Texture
Paper # NC2004-157
Date of Issue

Conference Information
Committee NC
Conference Date 2005/3/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Adaptive Radar-Image Clustering System That Focuses Attention on Variance of Pixel Value Correlations in Spatial and Frequency Domains
Sub Title (in English)
Keyword(1) Plastic landmine
Keyword(2) Interferometric radar
Keyword(3) Complex-valued Self-Organizing Map
Keyword(4) Texture
1st Author's Name Takahiro HARA
1st Author's Affiliation Graduate School of Frontier Sciences, The University of Tokyo()
2nd Author's Name Akira HIROSE
2nd Author's Affiliation Graduate School of Engineering, The University of Tokyo
Date 2005/3/21
Paper # NC2004-157
Volume (vol) vol.104
Number (no) 758
Page pp.pp.-
#Pages 6
Date of Issue