Displacement Field Calculation of Large-Scale Structures Using Computer Vision with Physical Constraints: An Experimental Study

Abstract

In recent years, computer vision-based structural displacement acquisition technique has received wide attention and research due to the advantages of easy deployment, low-cost, and non-contact. However, the displacement field acquisition of large-scale structures is a challenging topic as a result of the contradiction of camera field-of-view and resolution. This paper presents a large-scale structural displacement field calculation framework with integrated computer vision and physical constraints using only one camera. First, the full-field image of the large-scale structure is obtained by processing the multi-view image using image stitching technique; second, the full-field image is meshed and the node displacements are calculated using an improved template matching method; and finally, the non-node displacements are described using shape functions considering physical constraints. The developed framework was validated using a scaled bridge model and evaluated by the proposed evaluation index for displacement field calculation accuracy. This paper can provide an effective way to obtain displacement fields of large-scale structures efficiently and cost-effectively.