Automatic Generation of High-Resolution Thermal 3D Building Envelope Models exploiting UAV Imagery

Abstract

Buildings are major contributors to global energy consumption, with the thermal performance of their envelopes playing a crucial role. Detecting thermal bridges, which compromise insulation, is essential for energy efficiency. To efficiently detect thermal bridges, thermal infrared (TIR) imagery is widely used through visual inspections, more recently by exploiting sensors mounted on unmanned aerial vehicles (UAVs). While RGB images have been extensively used in Structure-from-Motion and Multi-View Stereo processes, applying these techniques to TIR images presents challenges due to lower resolution and inconsistent colour spaces. To overcome the challenges posed by TIR imagery, approaches from different fields investigated the integration of TIR images with other data to support the alignment. Our approach improves upon these methods by using a DJI Mavic 3 Enterprise Thermal UAV to collect RGB and TIR datasets simultaneously. Our guided image alignment and camera rig estimation approach accounts for unknown camera calibration, misalignment, and lever arm parameters, ensuring robust alignment of TIR images with a total error of 5 pixels. With this approach, the geometric accuracy of the resulting point cloud reached an RMSE of 0.13 m. Finally, thermal calibration values collected on site were applied to correct the thermal images, improving temperature value accuracy for 3D model texturing with a temperature deviation of 2.8 °C. The developed method requires no prior camera calibration, TIR image pre-processing, or ground control points, permitting a complete automation of the process.