Date of this Version
The use of unmanned aerial vehicles (UAVs) in construction sites has been widely growing for surveying and inspection purposes. Their mobility and agility have enabled engineers to use UAVs in Structural Health Monitoring (SHM) applications to overcome the limitations of traditional approaches that require labor-intensive installation, extended time, and long-term maintenance. One of the critical applications of SHM is measuring bridge deflections during the bridge operation period. Due to the complex remote sites of bridges, remote sensing techniques, such as camera-equipped drones, can facilitate measuring bridge deflections. This work takes a step to build a pipeline using the state-of-the-art computer vision ArUco framework to detect and track ArUco tags placed on the area of interest. The proposed pipeline analyzes videos of tags captured by stationary cameras and camera-equipped UAVs to return the displacements of tags. This work provides experiments of the ArUco pipeline with stationary and dynamic camera platforms in controlled environments. Estimated displacements are then compared with ground truth data. Experiments show the significance of pixel resolution, platform stability, and camera resolution in achieving high accuracy estimation. Results demonstrate that the ArUco pipeline outperforms existing methods with stationary cameras, reaching an accuracy of 95.7%. Moreover, the pipeline introduces an approach to eliminating the noised cause drone’s motion using a static reference tag. This technique has yielded an accuracy of 90.1%. This work shows promise toward a completely targetless approach using computer vision and camera-equipped drones.
Advisor: Carrick Detweiler