摄影测量学
计算机视觉
由运动产生的结构
人工智能
束流调整
计算机科学
点云
匹配(统计)
点(几何)
职位(财务)
工程类
运动(物理)
数学
统计
经济
财务
几何学
作者
Sizeng Zhao,Fei Kang,Junjie Li,Chuanbo Ma
标识
DOI:10.1016/j.autcon.2021.103832
摘要
This study presents a three-dimensional (3D) reconstruction model based on unmanned aerial vehicle (UAV) images for dam emergency monitoring and inspection. The structure from motion method is adopted to generate a high-precision 3D dam model with scene geometry by matching the features in multiple overlapping images. Then, the generated model is used to calculate the 3D point coordinates and camera pose through the bundle adjustment system. Effect of ground control points on the model accuracy is analyzed by different position sets for adaptation to various situations. The proposed emergency monitoring model is verified on two rock-fill dams, inspection model is utilized on a concrete dam, and damage detection method is achieved on a small-scale dam model with loadable panels. Results show that the proposed 3D dam reconstruction model based on UAV images can obtain satisfactory accuracy and result in a significant improvement in the dam monitoring and inspection efficiency.
科研通智能强力驱动
Strongly Powered by AbleSci AI