Extrinsic camera calibration method and its performance evaluation
This is an incremental improvement for computer vision systems, potentially reducing keypoint requirements in stereo reconstruction.
The paper tackles the problem of extrinsic camera calibration from image sequences, assuming known and fixed intrinsic parameters, and evaluates its performance on multi-view stereo datasets.
This paper presents a method for extrinsic camera calibration (estimation of camera rotation and translation matrices) from a sequence of images. It is assumed camera intrinsic matrix and distortion coefficients are known and fixed during the entire sequence. %This allows to decrease a number of pairs of corresponding keypoints between images needed to estimate epipolar geometry compared to uncalibrated case. Performance of the presented method is evaluated on a number of multi-view stereo test datasets. Presented algorithm can be used as a first stage in a dense stereo reconstruction system.