1.装备学院研究生院 北京 101416;2.装备学院信息装备系 北京 101416
TN95
1.Postgraduate School，Academy of Equipment，Beijing 101416，China;2.Department of Information Equipment，Academy of Equipment，Beijing 101416，China
随着合成孔径雷达成像技术的发展，SAR图像的数据处理和图像分类识别工作成为近年来研究的热点。由于SAR图像固有的特征，使得SAR图像的匹配分类不能直接使用光学遥感图像自动匹配。针对SAR图像自身的特性，提出了基于图像特征中保持不变的特性，作为两幅图像的参考信息进行配准。该方法在图像中选取了表示某些特征的参考点，提取图像的特征，利用特征计算空间变换参数。采用基于SIFT特征匹配的分类方法对飞机目标进行分类，仿真结果表明，在对3种类型的飞机进行分类的情况下，本文方法取得了较好的匹配结果，证明了算法的有效性。
With the development of synthetic aperture radar(SAR) technology，SAR image data processing and image classification and recognition has become a hot research topic in recent years. Due to the inherent characteristics of SAR image, the SAR image matching classification can not directly use optical remote sensing image matching. According to the characteristics of SAR image itself, and puts forward on the basis of the characteristics of image characteristics remain the same in, as the two images of reference information for registration. The method selects a reference point that represents some features in the image, feature extraction, using the feature to calculate the spatial transformation parameters. In this paper, a classification method based on SIFT feature matching is used to classify the aircraft targets, the simulation results show that the classification of three types of aircraft, this paper adopts the methods have achieved good matching results, proved the effectiveness of the algorithm.
张维坤,叶伟,劳国超.基于SIFT特征的SAR图像飞机目标匹配分类方法研究[J].国外电子测量技术,2016,35(8):19-21
复制
