摘要
提出了一种有效的SAR图像中自动目标识别的方法。首先采取双阈值CFAR目标分割算法对SAR图像进行目标分割。通过对SAR图像的空间局部特征和PCA全局特征的提取,在参数学习的基础上,结合了遗传算法进行迭代优化获取分类器,实现SAR图像的自动目标识别。该方法可以直接对原始图像进行计算,避免了基于数据特征计算所带来的问题。实验结果显示,这种基于遗传算法的自动目标识别方法对T-72和BMP2坦克进行识别,获得了较好的识别率。
An effective approach for automatic target recognition targets are segmented by a double CFAR (Constant False Alarm in SAR(Synthetic Aperture Radar) images is proposed.The SAR Rate) segmentation method for SAR targets.With the space local features and overall PCA (Prinicpal Component Analysis) features extract from the SAR images,the targets are recognized by the method based on parameter learning and a combination of genetic algorithm optimization on the classifier.This method does calculation on the original image directly,avoids mass problems of compute depending on the data model.The result shows that the automatic target recognition method based on genetic algorithm performs well to targets T-72 and BMP2.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第31期186-189,共4页
Computer Engineering and Applications
关键词
自动目标识别
遗传算法
主成分分析
双阈值CFAR分割
合成孔状雷达
automatic target recognition
genetic algorithm
Prinicpal Component Analysis (PCA)
double CFAR segmentation
Synthetic Aperture Radar(SAR)