Characterizing Footbridge Response from Cyclist Crossings with Computer Vision-Based Monitoring

Abstract

Computer vision applications are frequently selected for short-term monitoring of bridges. The availability of high resolution and frame rate consumer-grade cameras such as action cameras makes the computer vision-based monitoring an attractive and affordable option. This paper presents findings from monitoring deformations of a steel girder footbridge subjected to cyclist loads captured with an action camera. A modified GoPro action camera with a zoom lens was located 35 m from the centre of the bridge. High resolution (720 × 1080 pixel) and high frame rate (240 fps) videos were recorded during cyclist crossings. Image processing, measurement denoising, vertical deflection interpretation and influence line (bridge signature) derivations are presented and discussed. Both static and dynamic responses are identifiable (discernible in vision measurements) and even tiny (a fraction of a millimetre) vertical deflections can be accurately computed from videos collected with the action camera.