Inspection planning is a primary element of computer vision-and unoccupied aerial vehicle (UAV)-enabled construction monitoring. Prior to the on-site deployment of camera-mounted UAVs, the inspection objectives need to be identified, and optimal inspection plans must be developed; Such plans should ensure complete data acquisition and minimize the use of UAV's limited flight time. The image capture configuration must be taken into account since it directly affects the downstream applications of the captured data such as progress detection and as-built modeling. This paper proposes a framework and a novel technique which utilizes four-dimensional (4D) building information models (BIM) and swarm intelligence to automatically generate the UAV inspection mission plans. It computationally supports both static and dynamic site layouts. The inspection objectives, their geometry, and their semantics are automatically extracted from BIM, and the corresponding elements are identified. An optimal inspection plan is developed using artificial intelligence, ensuring complete coverage of inspection targets while minimizing flight duration. The method has been tested in UAV-enabled data acquisition scenarios. It is based on the industry foundation classes (IFC), facilitating OpenBIM and reducing the costs associated with the lack of interoperability, a core challenge in information modeling. Due to the target extraction at element and sub-element levels, it supports computer vision-based construction progress monitoring and automated as-built and as-is BIM development.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.