Camera-based Bridge Safety Monitoring

摘要

This paper describes a research project focused on the safety assessment of bridges using camera-based technologies. It is a collaboration with partners in three countries: Ireland, the United Kingdom and the United States. A major challenge of the project is the development of algorithms and methods that transform the measured sensor signals and video images into a form that is highly damage-sensitive/ change-sensitive for bridge safety assessment. The study will exploit the unique attributes of computer vision systems, where the signal is "continuous in space". This research will significantly advance current sensor-based structural health monitoring with computer-vision techniques, leading to practical applications for damage detection of complex structures with a novel approach. In the long term, monitoring with cameras is expected to be more broadly utilized for structural engineering purposes because of its potential for inexpensive deployment in real life bridges. While advancing the knowledge by integrating multidisciplinary concepts from theory to application, this research will have direct benefits as civil infrastructure (and particularly aged bridges) has become a critical societal concern from safety and cost perspectives. The paper will describe the bridge monitoring system that will be developed. It will include a weigh-in-motion (WIM) system to weigh vehicles, with cameras to monitor both the traffic and the bridge. The WIM system and the 1st camera will track the traffic and will extract its properties. The 2nd camera with some supplementary sensors will monitor the response of the bridge to the traffic. Structural identification algorithms will transform all of this data into damage indicators that indicate when the bridge has deteriorated or changed. The system will be tested using numerical simulation, scale models in the laboratory and trials using full scale bridges in the field.