Authors: Karsten W. Johansen, Rui Pimentel de Figueiredo, Olga Golovina and Jochen Teizer
University: Civil and Architectural Engineering, Aarhus University, Denmark – Electrical and Computer Engineering, Aarhus University, Denmark
Construction sites are dynamic, and the environment is changing fast, which means the collective safety equipment, such as fall protection barriers, should also be changed to keep it compliant with the construction codes. However, the safety equipment can become non-compliant for several reasons, e.g., temporal removal in combination with incorrect or omitted re-installation or changes in the building. Thus, there is a demand for frequent inspection of the equipment, which is time- and labor-intensive as this is currently done through manual examination by safety experts. In this work, we utilize an unmanned aerial vehicle (UAV) to detect the presence, absence, and defects of safety equipment in construction work-site environments. Furthermore, the UAV continuously inspects and provides safety object location information that human collaborators can use to improve safety within the environment. We utilize an 3D occupancy grid representation to map the environment and compact point pair feature representations for efficient and robust object recognition and pose estimation. To assess the applicability and accuracy of our methods for model-based pose estimation of BIM structures, we created a realistic simulation construction environment. A set of experiments demonstrate the applicability and precision of drone-aided localization and inspection of safety equipment in the construction industries.