摘要
探地雷达作为一种重要的无损探测技术,可以准确快速对浅层地表进行成像,以获取埋设目标的空间与几何信息.该文在分析探地雷达成像模型与目标识别基本思路的基础上,简述和归纳了七类探地雷达图像双曲线特征的检测方法,分别为基于双曲线性质、时域信号分析、数字图像分析、机器学习、数学模型、综合性方法以及深度学习方法,最后展望了深度学习在双曲线形态识别中的应用前景.
Ground penetrating radar (GPR),as an important non-destructive detection technology,can image the shallow subsurface accurately and quickly to obtain the spatial and geometric information of the buried targets.This paper describes and summarizes seven detection methods of hyperbolic signatures in GPR images,i.e.,based on hyperbolic properties,based on the time domain signal analysis,based on the digital image analysis,based on the machine learning,based on the mathematical model,based on the comprehensive and deep learning methods.Finally,we discuss the application potential of the deep learning method for the recognition of hyperbolic signatures.
作者
郝彤
赵杰
HAO Tong;ZHAO Jie(Application Center for Spatial Information Science and Sustainable Development,Shanghai 200092,China;College of Surveying and Geo-informatics,Tongji University,Shanghai 200092,China)
出处
《电子学报》
EI
CAS
CSCD
北大核心
2019年第6期1366-1372,共7页
Acta Electronica Sinica
关键词
物探技术
无损探测
探地雷达
目标识别
双曲线特征
深度学习
geophysical technology
non-destructive detection
GPR
object recognition
hyperbola signature
deep learning