The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Um novo algoritmo associado a pré-processadores fractais, extratores de características wavelet e classificadores neurais não supervisionados é proposto para detectar alvos de radar embutidos no gelo marinho e na desordem marítima. Utilizando as vantagens de fractais, wavelets e redes neurais, o algoritmo é adequado para aplicações automáticas e em tempo real. O pré-processador fractal pode aumentar a relação sinal-desordem (S/C) de 10 dB para imagens de radar usando erro fractal. O erro fractal facilitará a detecção de alvos de radar incorporados em ambientes de alta confusão. Extratores de recursos Wavelet com uma arquitetura de computação de alta velocidade podem extrair informações suficientes para classificar alvos de radar e interferências e melhorar a relação sinal-obstáculo. Os extratores de recursos Wavelet também podem fornecer combinações flexíveis para vetores de recursos em diferentes ambientes desordenados. O classificador neural não supervisionado possui uma arquitetura de operação paralela facilmente aplicada ao hardware, e um algoritmo de baixa carga computacional sem intervenções manuais durante a fase de aprendizagem. Modificamos o algoritmo de aprendizagem competitiva não supervisionada para ser aplicável na detecção de pequenos alvos de radar, introduzindo um fator de vizinhança de assimetria. O fator de vizinhança de assimetria pode fornecer um aprendizado protetor para evitar interferências desordenadas e melhorar os efeitos de aprendizado dos alvos do radar. Os pequenos alvos de radar em ondas milimétricas (MMW) e imagens de radar de banda X foram discriminados com sucesso pelo nosso algoritmo proposto. As características eficazes, eficientes e de alta imunidade a ruído do nosso algoritmo proposto demonstraram ser adequadas para aplicações automáticas e em tempo real.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Chih-ping LIN, Motoaki SANO, Shuji SAYAMA, Matsuo SEKINE, "Detection of Radar Targets Embedded in Sea Ice and Sea Clutter Using Fractals, Wavelets, and Neural Networks" in IEICE TRANSACTIONS on Communications,
vol. E83-B, no. 9, pp. 1916-1929, September 2000, doi: .
Abstract: A novel algorithm associated with fractal preprocessors, wavelet feature extractors and unsupervised neural classifiers is proposed for detecting radar targets embedded in sea ice and sea clutter. Utilizing the advantages of fractals, wavelets and neural networks, the algorithm is suitable for real-time and automatic applications. Fractal preprocessor can increase 10 dB signal-to-clutter ratios (S/C) for radar images by using fractal error. Fractal error will make easy to detect radar targets embedded in high clutter environments. Wavelet feature extractors with a high speed computing architecture, can extract enough information for classifying radar targets and clutter, and improve signal-to-clutter ratios. Wavelet feature extractors can also provide flexible combinations for feature vectors at different clutter environments. The unsupervised neural classifier has a parallel operation architecture easily applied to hardware, and a low computational load algorithm without manual interventions during learning stage. We modified the unsupervised competitive learning algorithm to be applicable for detecting small radar targets by introducing an asymmetry neighborhood factor. The asymmetry neighborhood factor can provide a protective learning to prevent interference from clutter and improve the learning effects of radar targets. The small radar targets in Millimeter wave (MMW) and X-band radar images have been successfully discriminated by our proposed algorithm. The effective, efficient, high noise immunity characteristics for our proposed algorithm have been demonstrated to be suitable for automatic and real time applications.
URL: https://global.ieice.org/en_transactions/communications/10.1587/e83-b_9_1916/_p
Copiar
@ARTICLE{e83-b_9_1916,
author={Chih-ping LIN, Motoaki SANO, Shuji SAYAMA, Matsuo SEKINE, },
journal={IEICE TRANSACTIONS on Communications},
title={Detection of Radar Targets Embedded in Sea Ice and Sea Clutter Using Fractals, Wavelets, and Neural Networks},
year={2000},
volume={E83-B},
number={9},
pages={1916-1929},
abstract={A novel algorithm associated with fractal preprocessors, wavelet feature extractors and unsupervised neural classifiers is proposed for detecting radar targets embedded in sea ice and sea clutter. Utilizing the advantages of fractals, wavelets and neural networks, the algorithm is suitable for real-time and automatic applications. Fractal preprocessor can increase 10 dB signal-to-clutter ratios (S/C) for radar images by using fractal error. Fractal error will make easy to detect radar targets embedded in high clutter environments. Wavelet feature extractors with a high speed computing architecture, can extract enough information for classifying radar targets and clutter, and improve signal-to-clutter ratios. Wavelet feature extractors can also provide flexible combinations for feature vectors at different clutter environments. The unsupervised neural classifier has a parallel operation architecture easily applied to hardware, and a low computational load algorithm without manual interventions during learning stage. We modified the unsupervised competitive learning algorithm to be applicable for detecting small radar targets by introducing an asymmetry neighborhood factor. The asymmetry neighborhood factor can provide a protective learning to prevent interference from clutter and improve the learning effects of radar targets. The small radar targets in Millimeter wave (MMW) and X-band radar images have been successfully discriminated by our proposed algorithm. The effective, efficient, high noise immunity characteristics for our proposed algorithm have been demonstrated to be suitable for automatic and real time applications.},
keywords={},
doi={},
ISSN={},
month={September},}
Copiar
TY - JOUR
TI - Detection of Radar Targets Embedded in Sea Ice and Sea Clutter Using Fractals, Wavelets, and Neural Networks
T2 - IEICE TRANSACTIONS on Communications
SP - 1916
EP - 1929
AU - Chih-ping LIN
AU - Motoaki SANO
AU - Shuji SAYAMA
AU - Matsuo SEKINE
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Communications
SN -
VL - E83-B
IS - 9
JA - IEICE TRANSACTIONS on Communications
Y1 - September 2000
AB - A novel algorithm associated with fractal preprocessors, wavelet feature extractors and unsupervised neural classifiers is proposed for detecting radar targets embedded in sea ice and sea clutter. Utilizing the advantages of fractals, wavelets and neural networks, the algorithm is suitable for real-time and automatic applications. Fractal preprocessor can increase 10 dB signal-to-clutter ratios (S/C) for radar images by using fractal error. Fractal error will make easy to detect radar targets embedded in high clutter environments. Wavelet feature extractors with a high speed computing architecture, can extract enough information for classifying radar targets and clutter, and improve signal-to-clutter ratios. Wavelet feature extractors can also provide flexible combinations for feature vectors at different clutter environments. The unsupervised neural classifier has a parallel operation architecture easily applied to hardware, and a low computational load algorithm without manual interventions during learning stage. We modified the unsupervised competitive learning algorithm to be applicable for detecting small radar targets by introducing an asymmetry neighborhood factor. The asymmetry neighborhood factor can provide a protective learning to prevent interference from clutter and improve the learning effects of radar targets. The small radar targets in Millimeter wave (MMW) and X-band radar images have been successfully discriminated by our proposed algorithm. The effective, efficient, high noise immunity characteristics for our proposed algorithm have been demonstrated to be suitable for automatic and real time applications.
ER -