Improvement of Plastic Landmine Visualization Performance by Use of Ring-CSOM and Frequency-Domain Local Correlation

Yukimasa NAKANO  Akira HIROSE 

Publication
IEICE TRANSACTIONS on Electronics  Vol.E92-C  No.1  pp.102-108
Publication Date: 2009/01/01
Online ISSN: 1745-1353
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Section on Recent Progress in Electromagnetic Theory and its Application)
Category: 
Keyword: 
ground penetrating radar (GPR),  self-organizing map (SOM), 

Full Text: PDF(524.4KB)

Summary: 
The complex-valued self-organizing map (CSOM) realizes an adaptive distinction between plastic landmines and other objects in landmine visualization systems. However, when the spatial resolution in electromagnetic-wave measurement is not sufficiently high, the distinction sometimes fails. To solve this problem, in this paper, we propose two techniques to enhance the visualization ability. One is the utilization of SOM-space topology in the CSOM adaptive classification. The other is a novel feature extraction method paying attention to local correlation in the frequency domain. In experimental results, we find that these two techniques significantly improve the visualization performance. The local-correlation method contributes also to the reduction of the number of tuning parameters in the CSOM classification.