Automatic hyperbola detection and fitting in GPR B-scan image
发布时间：2021-06-28
点击次数：
影响因子：6.121
DOI码：10.1016/j.autcon.2019.102839
发表刊物：AUTOMATION IN CONSTRUCTION
关键字：Automatic hyperbola detection; Double cluster seeking estimate (MSS) algorithm; Ground penetrating radar (GPR); Faster R-CNN
摘要：Detecting buried objects from ground penetrating radar (GPR) profiles often requires manual interaction and plenty of time. This paper presents an automatic scheme for buried objects detection and localization. First, a trained deep learning framework - Faster R-CNN with data augmentation strategy is applied to identify hyperbolic signatures from a gray GPR B-scan image, which is capable of not only recognizing whether a B-scan profile contains traces of buried object, but also detecting candidate hyperbola region. Then, the detected rectangle region is extracted and transformed to a binary image, a novel double cluster seeking estimate (DCSE) algorithm is proposed to separate object point duster from each other and enable the identification of hyperbolic signatures. Subsequently, a column-based transverse filter points (CTFP) method is utilized to extract hyperbola fitting points automatically from the validated point duster. Downward opening hyperbola fitting is carried out and their respective peaks are obtained finally. The proposed scheme is able to extract information from GPR B-scan images automatically and efficiently; it is validated significant performance in the analysis of synthetic and on-site GPR data sets.
第一作者：雷文太
论文类型：期刊论文
通讯作者：侯斐斐(博士生)
学科门类：工学
一级学科：信息与通信工程
文献类型：J
是否译文：否
发表时间：2019-10-01
收录刊物：SCI、EI