A novel vision measurement system for health monitoring of tunnel structures

Automation and intelligent health monitoring technologies will be one of the most important development directions for rail transit operation and maintenance considering the continuous expansion of the scale of urban rail transit and the increase of labor costs. The highly accurate, full-field data acquisition based on vision measurement technology, which is combined with photogrammetry and three-dimensional scanning technology, is an effective way to improve the intelligence of monitoring. In this paper, accuracy tests of vision measurement and total station technology in multipoint measurement is carried out under the same conditions where the accuracy and reliability are compared according to the various datasets which are collected from experiment and testing. A novel visual measurement technology is proposed for the deformation monitoring of tunnel structures, such as settlement and convergence. The results show that the measurement system has a resolution of 0.01 mm which is better than the total station resolution, and the deviation ratios of the vertical and horizontal displacement are 1.6% and 2.5%, which demonstrate the proposed system has a good potential for practical applications in terms of resolution and accuracy.