作者: Linmiao Zhang , Yong Lei , Nan Chen
DOI: 10.1109/IEEM.2015.7385868
关键词: Deformation monitoring 、 Point cloud 、 Statistical model 、 Surface (mathematics) 、 Structural engineering 、 Cartesian coordinate system 、 Gaussian process 、 Measure (physics) 、 Measurement uncertainty 、 Aerospace engineering 、 Engineering
摘要: Tunnel profile is an important quality measure for deformation monitoring throughout lifetime of a tunnel. Recently, statistical models such as cylindrical regression have been introduced to model the tunnel with help Terrestrial Laser Scanning (TLS) surveyed point cloud data. However, these cannot capture local variability surface, which monitoring. This paper presents Gaussian process (GP) based approach profile. We introduce reading-surface uniquely determines three-dimensional in Cartesian coordinate system. Based on reading-surface, we can fit GP and obtain continuous prediction surface. present case study demonstrate that our flexible therefore has great potential