Image analysis for building facade inspection

• Main Author: Fan, Yaxi
• Other Authors: Li King Ho Holden
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Mechanical engineering
• Online Access: https://hdl.handle.net/10356/140502
• Institution: Nanyang Technological University

Drone technology has been widely implemented among the commercial sector, defence and tech-savvy organizations in recent years. With the increasing availability of UAV applications, drone-based inspections have brought out significant improvements in identifying defective components efficiently and accurately. Commercial drones are penetrating into the building and construction industry in recent years but are still under R&D for their better productivity. By developing the automated system in the façade inspection process is expected to reduce risks to trained personnel who is climbing up to scaffolding structures and other supporting equipment for diagnostics work. The introduction of an artificial vision based inspection system is likely to be an effective solution ranging from data acquisition, data processing to report delivery to these problems. In this paper, we are mainly focused on 2 phases. Phase one includes developing the base platform and capabilities to fly the drone, capturing images, generating a 3D model, writing algorithms and codes to identify cracks and spalling in concrete, plaster and tiles, and finally mapping the images along with defects on the 3D model generated. Whereas phase 2 is to test out the capabilities and developed platform.