This paper describes a novel video mosaicing method based on extrinsic camera parameter estimation. The proposed method generates a mosaic image without perspective distortion, even if none of the input image plane is parallel to the target document. First, extrinsic camera parameters are estimated by tracking image features. Next, estimated extrinsic camera parameters are globally optimized to minimize the estimation error in the whole input sequence, utilizing re-appearing features. Finally, all the images are projected onto the mosaic image plane, and a super-resolved mosaic image is generated by applying an iterative back projection algorithm. Experiments have successfully demonstrated the feasibility of the proposed method.