Project Details
Projekt
Optical 3D-bridge-inspect: Innovative inspection of complex infrastructure combining very high-resolution UAV-borne imagery and structured-light scanning
Subject Area
Geodesy, Photogrammetry, Remote Sensing, Geoinformatics, Cartography
Structural Engineering, Building Informatics and Construction Operation
Structural Engineering, Building Informatics and Construction Operation
Term
since 2022
Project identifier
Deutsche Forschungsgemeinschaft (DFG) - Project number 501682769
Bridges as one of the main components of the transportation infrastructure suffer a lot of external strains and must bear fatigue loads, for example traffic, as well as climatological effects such as wind or thermal changes, apart from the natural degradation of the materials caused by aging. Moreover, if the structure has already some construction defect, the deterioration process speeds up with daily use. However, currently the necessary bridge inspections are mostly done manually by highly qualified operators who have yearlong experience on detecting possible dangerous damages on the bridges like cracks. But these manual inspections, even if are considered reliable, are still a subjective method and usually time consuming, as well as dangerous for the operators. In this project we propose to employ several state-of-the-art sensing technologies, and employ newly emerging data processing and machine learning approaches: Unmanned aerial vehicles (UAV) - or drones - will be equipped with high quality cameras and are used for accessing locations of the bridge that are hard to reach by humans as well as for taking high resolution images that are processed by a computer vision module for automatic evaluation; this makes them a powerful and flexible tool for structural health monitoring. We will use full-frame high-end metric cameras in combination with proper multi-rotor carriers to monitor both, comprehensive geometric deformation of the entire construction, and visual damage at the structure. In addition, we will make use of structured-light scanners, which are able to resolve a surface in three dimensions in the sub-mm range. All sensors will be co-registered in a coordinate frame which is defined by the infrastructure and stable over time. Through an innovative approach to control the UAV and combine all the sensor data within an advanced deep-learning image interpretation framework, we propose a holistic vision-based monitoring method. The work programme consists out of four working packages (WPs). For all four WPs there is one specific sub-WP which focusses on evaluation and testing. Here, the aim is to generate own, WP-wide, experiments in the premises of TU Braunschweig, specific to the WP, but it is also planned to conduct well-coordinated experiments at the demonstrator bridge at the highway A2, which is indicated in the call text. This project fits very well into the realm of this SPP since it connects methods on digital twins, being developed in are one (digital models) with the last area (condition indicators). The methods to be developed will be applicable not only to bridge structures but also to the monitoring of other complex infrastructures, as they are in principle generic in nature.
DFG Programme
Priority Programmes
