自适应直方图均衡化的合成孔径雷达图像增强  

Synthetic Aperture Radar Image Enhancement Based on Adaptive Histogram Equalization

作　　者：施丽红[1] SHI Lihong(School of E-commerce and Logistics,Jiangsu Vocational College of Business,Nantong 226000,China)

机构地区：[1]江苏商贸职业学院电子商务与物流学院,江苏南通226000

出　　处：《无线电工程》2021年第9期921-926,共6页Radio Engineering

基　　金：江苏省第五期“333工程”科研资助项目(BRA2018220)。

摘　　要：合成孔径雷达(Synthetic Aperture Radar,SAR)成像技术在海岸线检测、舰船检测等领域具有广泛应用。为了解决SAR图像质量不稳定的问题,提出一种自适应直方图均衡化的SAR图像增强方法。该方法通过均值漂移聚类方法删除图像中低信息量的数据,以缓解局部暗淡现象与噪声放大的现象。设计了增强的布谷鸟搜索算法学习图像直方图均衡化的最优参数,实现自适应的SAR图像增强处理。在SAR图像上完成了验证实验,结果表明,该增强方法使SAR图像在主观视觉评价与客观定量评价上均取得了明显提高。Synthetic aperture radar imaging technique has a wide application in the fields such as coastline detection,ship detection and so on.In order to overcome the problem of instable quality of SAR images,an SAR image enhancement method based on adaptive histogram equalization is proposed.The method takes advantage of mean shift clustering method to delete the less informative data,in order to reduce the artifact and noise amplification.Besides,an enhanced cuckoo search algorithm is proposed to learn the optimal parameters of image histogram equalization,so that the adaptive SAR image enhancement process is realized.A set of validation experiments on SAR images are made.The results indicate that the proposed enhancement method can improve the SAR images in terms of both subjective visual evaluation and objective quantitative evaluation.

关 键 词：布谷鸟搜索 直方图均衡化 图像增强 合成孔径雷达 均值漂移聚类 对比度增强 

分 类 号：TN957.52[电子电信—信号与信息处理] TP183[电子电信—信息与通信工程]