Ying Li^1,2, Guanghong Gong¹, Dan Wang¹, Ni Li^1,3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.136, No.3, pp. 2237-2265, 2023, DOI:10.32604/cmes.2023.025193

Abstract There are two types of methods for image segmentation. One is traditional image processing methods, which are sensitive to details and boundaries, yet fail to recognize semantic information. The other is deep learning methods, which can locate and identify different objects, but boundary identifications are not accurate enough. Both of them cannot generate entire segmentation information. In order to obtain accurate edge detection and semantic information, an Adaptive Boundary and Semantic Composite Segmentation method (ABSCS) is proposed. This method can precisely semantic segment individual objects in large-size aerial images with limited GPU performances. It includes adaptively dividing and modifying the… More > Graphic Abstract

Xiaozhong Li^*, Caiyun Sun

Structural Durability & Health Monitoring, Vol.16, No.3, pp. 235-254, 2022, DOI:10.32604/sdhm.2022.013141

Abstract During the construction of subway tunnels, safety issues should not be ignored, so it is necessary to prevent and resolve the risk in time and accurately. However, there are some shortcomings in the research of risk assessment, such as the subjectivity of initial data or the lack of scientific evaluation model, in order to solve the problem, this paper relies on the Changping section of the Guanhui Intercity Metro, in order to establish a dynamic risk-warning model for the construction process of subway tunnel with the CD-Bench composite method. First, a monitoring plan was equationted according to the specification requirements… More >