Vision-based trajectory monitoring for assembly alignment of precast concrete bridge components

The prefabricated structures are popularly used because of their high efficiency and it is important to ensure their installation quality. The current installation is guided by visual observation and total station, which is inaccurate and time-consuming. This study presents a stereo-vision-based pose measurement technique for guiding the installation to address the problems. The contributions are as follows: 1) A framework of a vision-based 6-DOF pose monitoring system is designed to track the precast member continuously; 2) A two-level adjustment strategy is suggested by transferring the relative pose measurement between the precast member and existing structure to the process to determine the relative relations of two coordinate systems; 3) A robust deep-learning-based ellipse detection method is proposed to identify and classify the artificial targets accurately. The proposed technique is evaluated in both indoor experiments and the construction of an expressway viaduct to demonstrate its accuracy and effectiveness.