Automated Close-Quarter, High-Resolution Inspection and 3D Reconstruction of Unknown Infrastructure

• Published in: OCEANS 2023 - Limerick pp. 1 - 6
• Main Authors: Bartlett, Ben, Trslic, Petar, Santos, Matheus, Manduhu, Manduhu, Riordan, James, Dooly, Gerard
• Format: Conference Proceeding
• Language: English
• Published: IEEE 05-06-2023
• Subjects: 3D Reconstruction; autonomous workflow; Inspection; Manuals; Oceans; Solid modeling; Surveys; Three-dimensional displays; UAS; UAV; uniform GSD; unknown environments; Visualization
• DOI: 10.1109/OCEANSLimerick52467.2023.10244740

This paper presents a new automated workflow for 3D reconstruction of unknown infrastructure utilising UAS technology, developed within the EU funded RAPID project. A multi stage approach is used to produce highly accurate reconstructions of infrastructure, specifically unknown infrastructure. Using this approach, the drone operator is not required to perform extensive pre-flight surveying and mission planning, adding only a few high level inputs to the overall workflow. This benefits inspection workflows where the pilot is not onsite and cannot make visual observations on safety. Furthermore, this results in uniform high resolution reconstructions and a higher level of consistent and simple task loading for operator. Real-world environment tests consisting of using one of the most popular commercial UAS platforms to perform autonomous surveys was completed, with results to demonstrate the feasibility of the developed system.