Project PI : Immanuel Koh
Project Period : 16 May 2025 to 15 May 2027
Description:
The research leverages state-of-the-art AI techniques of deep neural networks in 3D building semantic segmentation and 2D floorplan prediction and outputting them as vector file format useful for large-scale building digitisation. It targets spatially and visually more complex private housing typologies of non-HDB buildings, namely high-rise condominiums and high-rise service apartments.
Current and targeted Technology Readiness Level (TRL)
Current TRL: 3
Target TRL: 4
Potential applications (both commercial and military)
Intelligent building façade recognition for navigating drones and autonomous vehicles, automated building defects detection for building maintenance, rapid generative design for real estate development and large-scale building digitisation for cities.
Roadmap of the technology
The project will progressively include more diverse building typologies (i.e., beyond residential). This tool will be developed and made transferrable to other related spatial domains.
Project team’s current expertise and relevant research achievements
This research is supported and informed by expertise drawn from the domains of artificial intelligence, computer vision, remote sensing, generative design, architectural and urban planning.