An Algorithm to Calibrate Field Cameras for Stereo Clouds

This paper presents a robust extrinsic parameter estimation algorithm to calibrate field cameras which were used to observe the formation of clouds on a mountainous region. Generally, camera calibration needs accurate landmark survey and image feature identification. However, our observation area is a large scale scene in a physically inaccessible area, therefore the landmark surveys are not precise. Since clouds are distant to cameras, cloud features in the images are also difficult to accurately identify for stereo correspondences. The noise in landmark survey and cloud feature correspondence makes it challenging to obtain desired cloud observation accuracy by using traditional least squares based camera calibration approaches. Our camera calibration approach is based on a generalized total least square (GTLS) algorithm instead of a normal least square method. Experiments show that the GTLS-based camera calibration is more accurate and robust than LS-based methods for our application.