首页> 外国专利> APPARATUS FOR CLASSIFYING TARGET OF INVERSE SYNTHETIC APERTURE RADAR IMAGE USING TRACE TRANSFORM AND METHOD THEREOF

APPARATUS FOR CLASSIFYING TARGET OF INVERSE SYNTHETIC APERTURE RADAR IMAGE USING TRACE TRANSFORM AND METHOD THEREOF

机译:利用轨迹变换对逆合成孔径雷达图像目标进行分类的装置及其方法

摘要

The present invention relates to an apparatus and method for a target classification apparatus for an inverse synthetic aperture surface radar image using a trace transformation, and a method for classifying an inverse synthetic aperture surface radar image by receiving an inverse synthetic aperture surface radar image for a target, Preprocessing the inverse synthesized aperture radar image by removing a noise response, a clutter response, and a signal level change due to a different distance between the radar and the target from the inverse synthesized aperture radar image, Extracting a classification feature function along a main axis of the target from the preprocessed inverted synthetic aperture radar image using a trace transform, extracting a candidate feature database from a pre-stored training database using the classification feature function, Selecting a classification feature value included in the candidate database, And classifying the type of the target using the extracted classification feature. According to the present invention, according to the embodiment of the present invention, it is possible to reduce the amount of the database using the trace transformation and reduce the amount of computation in the feature extraction process for classification in the inverse synthetic aperture radar image, The time consumed and the amount of computation can be reduced. In addition, it is possible to acquire abundant identification information without being influenced by the translation, rotation, reflection, etc. of the inverse synthesized opening surface radar image, so that the classification accuracy of the target can be greatly improved.
机译:技术领域本发明涉及用于使用迹线变换的逆合成孔径表面雷达图像的目标分类设备的装置和方法,以及通过接收用于卫星的逆合成孔径表面雷达图像来对逆合成孔径表面雷达图像进行分类的方法。目标,通过从逆合成孔径雷达图像中去除噪声响应,杂波响应和由于雷达与目标之间的距离不同而引起的信号电平变化,对逆合成孔径雷达图像进行预处理,沿使用轨迹变换从预处理的倒置合成孔径雷达图像中获取目标主轴,使用分类特征函数从预先存储的训练数据库中提取候选特征数据库,选择候选数据库中包含的分类特征值,并对目标分类使用提取的目标的类型分类功能。根据本发明,根据本发明的实施例,可以利用跟踪变换来减少数据库的数量,并且可以减少用于反合成孔径雷达图像的分类的特征提取处理中的计算量,可以减少消耗的时间和计算量。另外,可以不受逆合成开口面雷达图像的平移,旋转,反射等的影响而获取大量的识别信息,从而可以大大提高目标的分类精度。

著录项

  • 公开/公告号KR101891410B1

    专利类型

  • 公开/公告日2018-08-23

    原文格式PDF

  • 申请/专利权人 포항공과대학교 산학협력단;

    申请/专利号KR20160167771

  • 发明设计人 김경태;이승재;

    申请日2016-12-09

  • 分类号G01S13/90;G01S7/28;

  • 国家 KR

  • 入库时间 2022-08-21 12:37:15

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号