Vision-based displacement measurement using an unmanned aerial vehicle

Vision-based displacement measurement for structural health monitoring has gained popularity in recent years but still has several limitations in practical applications. Unmanned aerial vehicles (UAVs) provide opportunities to address the bottleneck problems of camera resolution insufficiency and mounting inconvenience due to their high maneuverability. However, existing methods using UAVs for structural displacement measurement are often complicated to operate due to the use of multiple stationary markers or multiple UAVs. This paper describes a novel vision-based displacement measurement approach, using only one UAV, along with a motionless laser spot projected from a distance away as a reference. The positions of the marker and the laser spot are precisely calculated using a two-step strategy, in which a designed black and white marker of known size is applied to the structure for scale definition and precise positioning. The adaptive region of interest (ROI) and adaptive binarization methods are utilized to improve the automatic applicability of the proposed approach with various background and brightness values. In this way, the motion of the UAV parallel and perpendicular to the plane of the structure can be eliminated by the stationary reference laser spot and the constantly updated scaling factors, respectively. The performance of the proposed method is validated on a two-story frame and a suspension bridge. The results show that the displacement measured using the UAV agrees with the reference data obtained using the laser displacement sensor and the stationary camera, thereby demonstrating the accuracy and feasibility of the proposed method for displacement measurement for small- and large-scale infrastructure.

Automated summary

This paper presents a vision-based displacement measurement method using a single UAV and a stationary laser spot as a reference. By precisely calculating the positions of a marker and the laser spot, and utilizing adaptive region of interest and adaptive binarization methods, this method eliminates the motion of the UAV on the structure plane, enabling accurate displacement measurement.