Camera Calibration of Thermal-Infrared Stereo Vision System

Accurate and efficient thermal-infrared camera calibration is important for advancing computer vision research within the thermal modality. This paper proposes a specially designed calibration pattern for stereo vision systems. Small circular thermostatic heaters are used as sources of thermal radiations so that the pattern can present obvious thermal contrast. The circular features can be easily and accurately extracted. Additionally, the paper proposes a calibration algorithm to exploit the centers of circles as feature points with high precision. Experiments were carried out in outdoor environment of large field of view. From the experiments we have obtained the mean re-projection error of calibration in 0.786 pixels at a distance of 10 meters. The proposed method is simple and efficient.