提出一种基于遗传规划的合成孔径雷达图像识别方法.首先提取SAR图像的5种特征作为原始特征,然后利用遗传规划算法在5种原始特征上合成新的特征,最后采用支持向量机进行分类.实验结果表明了算法的有效性.
A genetic programming-based method for SAR image recognition is proposed. Five basic SAR image features are first extracted from SAR images, and then several new features are synthesized using the five basic features. Finally a support vector machine is used to complete classification. Experimental results show the effectiveness of this method.
[1] Huan R H, Yang R L, Yue J. A new method for synthetic aperture radar images feature extraction and target recognition[J]. Journal of Electronics & Information Technology, 2008, 30(3):554-558(in Chinese). 宦若虹,杨汝良,岳晋. 一种合成孔径雷达图像特征提取与目标识别的新方法[J].电子与信息学报, 2008, 30(3):554-558.
[2] Hu L P, Liu H W, Wu S J. SAR target feature extraction and recognition based on improved clustering-based discriminant analysis[J]. Journal of Electronics & Information Technology, 2009, 31(9):2264-2268(in Chinese). 胡利平,刘宏伟,吴顺君. 基于改进的子类判决分析的SAR目标特征提取与识别[J].电子与信息学报, 2009, 31(9):2264-2268.
[3] Lin Y L, Bhanu B. Evolutionary feature synthesis for object recognition[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part C: Applications and Reviews, 2005, 35(2):156-171.
[4] 云庆夏.进化算法[M].北京:冶金工业出版社, 2000:84-115.
[5] Lin Y L, Bhanu B. Object detection via feature synthesis using MDL-based genetic programming[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, 2005, 35(3): 538-547.
[6] Verbout S M, Alison L, Weaver, et al. New image features for discriminating targets from clutter //Part of the SPIE Conference on Radar Sensor Technology III Orlando. USA: Florida, 1998: 120-137.
[7] Gao G, Zhou D F, Zhang J, et al. Feature selection for target discrimination in SAR images based on genetic algorithm[J]. Acta Electronica Sinica, 2008, 36(6):1041-1046(in Chinese). 高贵,周蝶飞,张军,等. 基于遗传算法的SAR图像目标鉴别特征选择[J].电子学报, 2008, 36(6):1041-1046.
