光电工程, 2012, 39 (9): 86, 网络出版: 2013-01-08
基于NSCT域特征和PCNN的SAR图像目标分割
Target Segmentation for SAR Images Based on Nonsubsampled Contourlet Characteristic and PCNN
SAR图像目标分割 非下采样轮廓波变换 脉冲耦合神经网络 MSTAR图像 target segmentation for SAR images nonsubsampled contourlet transform pulse coupled neural networks MSTAR images
摘要
针对 SAR图像的目标自动分割问题, 在分析非下采样轮廓波变换和脉冲耦合神经网络的基础上, 提出了一种基于非下采样轮廓波域特征图和 PCNN的 SAR图像目标分割算法。对 SAR图像经过 NSCT分解后的高、低频图像分别运用不同方式进行处理。对低频图用 PCNN进行分割以获取目标所在的区域, 对高频子带构造了特征图, 对特征图利用 PCNN进行分割以获取目标的精细结构。利用 MSTAR数据进行了仿真实验, 并与基于模糊 C均值的分割算法、基于马尔可夫随机场的分割算法进行了对比。实验结果表明, 所提出算法对 SAR图像目标的分割结果更为准确, 同时较其它算法具有更强的抗噪性能, 是一种有效可行的 SAR目标分割算法。
Abstract
To solve the problem of automatic target segmentation for SAR images, a target segmentation algorithm for SAR images was proposed after the analysis of nonsubsampled contourlet transform and pulse coupled neural networks. Via researching the characteristics of low and high frequency, the conclusion was acquired that the first one contained probable region of target mainly. Correspondingly, the latter contained fine contour and background disturbance mainly. Fire image of low frequency was produced by Pulse Coupled Neural Networks (PCNN) acting on low frequency image, and the region which the target located was confirmed on the basis of segmentation for the fire image using OTSU method. A characteristic figure was constructed for the high frequency, and the fine configuration of the target was acquired on the basis of segmentation for characteristic figure’s fire image. Experiments with MSTAR images were processed and the proposed algorithm was compared with algorithms based on fuzzy C mean and Markov random fields. The results indicate that the proposed algorithm which has more accurate segmentation for SAR target and more strongly immune ability for speckle was effective.
吴俊政, 严卫东, 边辉, 倪维平, 芦颖. 基于NSCT域特征和PCNN的SAR图像目标分割[J]. 光电工程, 2012, 39(9): 86. WU Jun-zheng, YAN Wei-dong, BIAN Hui, NI Wei-ping, LU Ying. Target Segmentation for SAR Images Based on Nonsubsampled Contourlet Characteristic and PCNN[J]. Opto-Electronic Engineering, 2012, 39(9): 86.