Computing Thermal Point Clouds by Fusing RGB-D and Infrared Images: From Dense Object Reconstruction to Environment Mapping

Compared with 2D thermal images, visualizing the temperature of objects with their corresponding 3D surfaces provides a more intuitive way to perceive the environment. In this paper, we present an integrated system for large-scale and real-time 3D thermographic reconstruction through fusion of visible, infrared and depth images. The system is composed of an RGB-D and a thermal camera, whose image measurements are aligned with respect to the same coordinate frame. A thermal direct method based on infrared features is proposed and integrated into state-of-art localization algorithms for generating reliable 3D thermal point clouds. The reported experimental results demonstrate that our approach can be used for 3D reconstruction of small and large scale environments based on dual spectrum 3D information.