基于行方差的GPR图像感兴趣区域提取定位方法  

Extracting and Locating ROI in GPR Images Based on Row Variance

作　　者：刘普 焦良葆[2] 曹雪虹[1,2] LIU Pu;JIAO Liang-bao;CAO Xue-hong(School of Communications and Information Technology,Nanjing University of Posts and Telecommunications,Nanjing 210003,China;Institute of Artificial Intelligence Industrial Technology,Nanjing Institute of Technology,Nanjing 211167,China)

机构地区：[1]南京邮电大学通信与信息工程学院,江苏南京210003 [2]南京工程学院人工智能产业技术研究院,江苏南京211167

出　　处：《软件导刊》2020年第6期218-222,共5页Software Guide

基　　金：国家自然科学基金青年项目(61703201);江苏省自然科学基金青年项目(BK20170765)。

摘　　要：传统探地雷达数据的解译通常由人工实现,随着电磁波技术的发展,人们对自动化作业的需求日益迫切,由此提出一种基于行方差的探地雷达图像感兴趣区域提取定位方法。该方法首先建立地质病害建模,并分析其特征,病害类型包括空洞与脱空;然后利用探地雷达数据的行方差特性,对感兴趣区域作初步提取;最后,增强感兴趣区域相位特征,并根据雷达反射波的相位特征进行模板匹配。仿真结果表明,该算法在降低定位成本的情况下有效缩小了感兴趣区域,定位精度比传统方法提高了10%~15%。Traditionally most GPR data interpretations are performed manually.With the advancement of electromagnetic wave technol⁃ogies and the desire for automation,a method based on row variance to extract and locate ROI of GPR image is proposed in this paper.The method firstly models and analyzes geological diseases,including air void and delamination.Then,a preliminary extraction of the ROI is performed using the row variance characteristics of the GPR data.Finally,after enhancing the phase characteristics of the ROI,graphical features of reflected waves are used for template matching.The simulation results indicate that the proposed algorithm can narrow the ROI down effectively while reducing the cost.Compared with traditional methods,the proposed algorithm improves the posi⁃tioning accuracy by 10%~15%.

关 键 词：探地雷达 雷达图像 感兴趣区 提取定位 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]