The growing need for digital representations of existing buildings in the Architecture, Engineering, Construction & Operations (AECO) domain necessitates efficient methods to retrospectively create Building Information Modeling (BIM) models. One prominent approach to obtain the necessary information is Plan-to-BIM, i.e., analyzing building documentation such as floor plans. However, the storage of this information is not standardized which leads to compatibility issues in collaborative scenarios. To address this, the paper presents the Drawing Analysis Ontology (DAnO), which is designed to standardize the representation of technical drawing data extracted through computer vision techniques. Focusing on floor plans, DAnO enables the aggregation, integration, and validation of extracted elements by defining key concepts, such as DrawingElement, DisplayElement, and DescriptionElement, and their relationships. By means of real floor plans, a case study demonstrates the ontology’s effectiveness in facilitating the generation of building models from legacy drawings, highlighting its potential to streamline BIM reconstruction workflows and to enhance interoperability in the AECO industry.

Efficient maintenance planning and streamlined inspection for bridges are essential to prevent catastrophic structural failures. Digital Bridge Management Systems (BMS) have the potential to streamline these tasks. However, their effectiveness relies heavily on the availability of accurate digital bridge models, which are currently challenging and costly to create, limiting the widespread adoption of BMS. This study addresses this issue by proposing a computer vision-based process for generating bridge superstructure models from pixel-based construction drawings. We introduce an automatic pipeline that utilizes a deep learning-based symbol pose estimation approach based on Keypoint R-CNN to organize drawing views spatially, implementing parts of the proposed process. By extending the keypoint-based detection approach to simultaneously process multiple object classes with a variable number of keypoints, a single instance of Keypoint R-CNN can be trained for all identified symbols. We conducted an empirical analysis to determine evaluation parameters for the symbol pose estimation approach to evaluate the method’s performance and improve the trained model’s comparability . Our findings demonstrate promising steps towards efficient bridge modeling, ultimately facilitating maintenance planning and management.