Online Photometric Calibration of Automatic Gain Thermal Infrared Cameras

Thermal infrared cameras are increasingly being used in various applications such as robot vision, industrial inspection and medical imaging, thanks to their improved resolution portability. However, the performance of traditional computer vision techniques developed for electro-optical imagery does not directly translate thermal domain due two major reasons: these algorithms require photometric assumptions hold, methods calibration RGB cannot be applied thermal-infrared difference data acquisition sensor phenomenology. In this letter, we take a step direction, introduce novel algorithm online cameras. Our proposed method any specific driver/hardware support hence can commercial off-the-shelf IR camera. We present context visual odometry SLAM algorithms, demonstrate efficacy our system through extensive experiments both standard benchmark datasets, real-world field tests with camera natural outdoor environments.