Enriching thermal point clouds of buildings using semantic 3D building models

TL;DR

This paper presents a workflow that enhances thermal point clouds of buildings by integrating detailed 3D building models, enabling better semantic interpretation and supporting advanced thermal analysis and deep learning applications.

Contribution

It introduces an automatic method to co-register and enrich thermal point clouds with semantic information from detailed 3D building models at LoD3.

Findings

Enables precise semantic annotation of thermal point clouds.

Supports improved thermal analysis and deep learning model development.

Facilitates integration of multi-source 3D data for building analysis.

Abstract

Thermal point clouds integrate thermal radiation and laser point clouds effectively. However, the semantic information for the interpretation of building thermal point clouds can hardly be precisely inferred. Transferring the semantics encapsulated in 3D building models at LoD3 has a potential to fill this gap. In this work, we propose a workflow enriching thermal point clouds with the geo-position and semantics of LoD3 building models, which utilizes features of both modalities: The proposed method can automatically co-register the point clouds from different sources and enrich the thermal point cloud in facade-detailed semantics. The enriched thermal point cloud supports thermal analysis and can facilitate the development of currently scarce deep learning models operating directly on thermal point clouds.