A new rectification scheme for uncalibrated stereo image pairs and its application to intermediate view reconstruction

摘要

In this paper, a new rectification scheme to transform the uncalibrated stereo image pair into the calibrated one is suggested and its performance is analyzed by applying this scheme to reconstruction of the intermediate views for multi-view stereoscopic display. In the proposed method, feature points are extracted from the stereo image pair through detection of the corners and similarities between each pixel of the stereo image pair. And then, using these detected feature points, moving vectors between the stereo image pair and the epipolar line is extracted. Finally, the input stereo image pair is rectified by matching the extracted epipolar line between the stereo image pair in the horizontal direction. From some experiments on synthesizing the intermediate views by using the calibrated stereo image pairs through the proposed rectification algorithm and the uncalibrated ones for three kinds of stereo image pairs; 'Man', 'Face' and 'Car', it is analyzed that PSNRs of the intermediate views reconstructed from the calibrated images are improved about 2.5 ～ 3.26 dB than those of the uncalibrated ones.