Abstract

The conventional data collection in bridge inspection is paper-based and provides limited support for spatial visualization, which makes the data collection process inaccurate and inefficient. In addition, condition rating evaluation of bridge components from the collected data still depends on the subjective opinion of the inspector. Therefore, new technologies are motivating the development of new types of bridge inspection systems to improve the quality and efficiency of bridge inspection and to allow the inspectors to better focus on their tasks. In this research, we describe a new approach to support bridge inspection data collection using location-based computing and to evaluate condition rating using a Bayesian network that can learn from the previous bridge inspection data. Using 3D bridge model, inspectors can visualize and analyze information related to the inspection of bridges based on various interaction methods and a database