Use of High-Resolution Imaging Techniques for Condition Assessment and Damage Detection of Bridges

This proposal consists of an innovative integrated solution for damage diagnosis of bridge structures using a non-contact image-based measurement methodology. High-resolution and regular camera systems will be used to capture the bridge movements and the traffic passing the bridge, respectively. Computer vision techniques will be used to extract the deflection time-histories of the bridge as well as the vehicle locations from the raw images. The information will be used for joint model and vehicular load identification using a Bayesian estimation technique. The updated model will be maintained as a “digital twin” of the infrastructure, which will be interrogated for damage diagnosis (e.g., deterioration, loss of prestress forces, etc.) at the bridge components. The resulting actionable information can be used to guide the decision-making related to maintenance and asset management. Phase II of this project will focus on refining the technical approach and developing a working prototype (hardware/software), which will be validated with experimental and real-world data. The envisioned product development stage after Phase II will result in a new technology product for cost-effective and non-interruptive monitoring of bridges. The project is aligned with the four strategic goals of the USDOT and the FHWA, which are safety, infrastructure, innovation, and accountability.