The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

A New Intermediate View Reconstruction Scheme based-on Stereo Image Rectification Algorithm

스테레오 영상 보정 알고리즘에 기반한 새로운 중간시점 영상합성 기법

  • Published : 2004.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a new intermediate view reconstruction method employing a stereo image rectification algorithm by which an uncalibrated input stereo image can be transformed into the calibrated one is suggested and its performance is analyzed. In the proposed method, feature point are extracted from the stereo image pair though detection of the corners and similarities between each pixel of the stereo image. And then, using these detected feature points, the moving vectors between stereo image and the epipolar line is extracted. Finally, the input stereo image is rectified by matching the extracted epipolar line between the stereo image in the horizontal direction and intermediate views are reconstructed by using these rectified stereo images. From some experiments on synthesis of the intermediate views by using three kinds of stereo image; a CCETT's stereo image of 'Man' and two stereo images of 'Face' ＆ 'Car' captured by real camera, it is analyzed that PSNRs of the intermediate views reconstructed from the calibrated image by using the proposed rectification algorithm are improved by 2.5㏈ for 'Man', 4.26㏈ for 'Pace' and 3.85㏈ for 'Car' than !hose of the uncalibrated ones. This good experimental result suggests a possibility of practical application of the unposed stereo image rectification algorithm-based intermediate view reconstruction view to the uncalibrated stereo images.

본 논문에서는 비교정 상태의 스테레오 입력영상에 영상보정 알고리즘을 적용한 새로운 중간시점 영상합성 기법을 제시하고 그 성능을 분석하였다. 제시된 방법에서는 먼저, 좌, 우 스테레오 영상의 각 화소 간들에 대한 유사도 및 모서리 검출을 통해 특징점을 추출한 다음, 이들 특징점을 이용하여 스테레오 영상간의 움직임 벡터와 에피폴라 선을 검출하였다. 그리고 스테레오 영상간의 수평선을 일치시킴으로써 좌, 우 스테레오 영상을 보정하고 최적으로 적응적 변위추정 기법을 이용하여 최적화된 중간시점 영상을 합성하였다. CCETT의 'Man' 영상과 스테레오 카메라를 사용하여 촬영한 '사람' 및 '자동차' 영상을 사용한 중간영상 합성 실험결과 본 논문에서 제안된 보정기법으로 교정된 스테레오 영상의 경우가 비교정 상태에 비해 'Man' 영상은 3.6㏈, '사람' 및 '자동차' 영상은 2.59㏈, 1.47㏈의 PSNR이 각각 개선됨이 분석됨으로써 본 논문에서 새로이 제시한 스테레오 영상 보정 알고리즘 기반의 중간시점 영상합성 기법의 실질적 응용 가능성을 제시하였다.

Keywords

References

  1. IEEE Signal Processing Magazine v.16 no.3 Correspondence estimation in image pairs A.Redert;E.Hendriks;J.Biemond https://doi.org/10.1109/79.768571
  2. Introductory Techniques For 3-D Computer Vision T.Emanuele;V.Alessandro
  3. Three-Dimensional Computer Vision: A Geometric Viewpoint O.Faugeras
  4. Optical Engineering v.42 no.6 New disparity estimation scheme based on adaptive matching window for intermediate view reconstruction K.H.Bae;J.J.Kim;E.S.Kim https://doi.org/10.1117/1.1571828
  5. IEEE Trans. on Image Processing v.5 no.4 Epipolar line estimation and rectification for stereoimage pairs D.V.Papadimitriou;T.J.Dennis
  6. International Journal of Computer Vision v.35 no.22 Theory and practice of projective rectification Richard I.Hartley https://doi.org/10.1023/A:1008115206617
  7. IEEE Proc. of International Conference on Image Analysis and Processing On robust rectification for uncalibrated images F.Isgro;E.Trucco
  8. IEEE Trans. on Image Processing v.5 no.4 Epipolar line estimation and rectification for stereo image pairs D.Papadimitriou;T.Dennis https://doi.org/10.1109/83.491345
  9. Proc. of International Conference on Pattern Recognition v.1 Rectification of images for binocular and trinocular stereovision N.Ayache;C.Hansen
  11. Disparity estimation and intermediate view reconstruction for noble applications in steroscopic video A.Mancini
  12. Optics Communication v.191 real-time stereo object tracking system by using block matching algorithm and optical binary phase extraction joint transform correlator J.S.Lee;J.H.Ko;E.S.Kim https://doi.org/10.1016/S0030-4018(01)01137-3
  13. Signal Processing Magazine v.16 no.3 Correspondence estimation in image pairs A.Redert;E.Hendriks;J.Biemond https://doi.org/10.1109/79.768571
  14. Geomatics Research Australasia v.71 Rectification and matching of trinocular imagery J.Shao;C.Fraser
  15. Machine Vision Applications v.12 no.1 A compact algorithm for rectification of stereo pairs A.Fusiello;E.Trucco;A.Verri https://doi.org/10.1007/s001380050120
  17. IEEE trans. on Pattern Analysis and Machine Intelligence v.22 no.4 Trajectory triangulation: 3D reconstruction of moving points from a monocular image sequence S.Avidan
  18. Pattern Recognition Letters v.24 no.1-3 A new image rectification algorithm Z.Chen;C.Wu;H.T.Tsui https://doi.org/10.1016/S0167-8655(02)00239-8
  20. IEEE Control System Cooperative gaze holding in binocular vision D.J.Coombs;C.M.Brown
  21. Proc. of SPIE v.2177 Geometry of binocular imaging V.S.Grinberg;G.W.Pondar;M.W.Sigel https://doi.org/10.1117/12.173906
  22. IEEE Trans. on Circuits and Systems for Video Technology v.7 no.4 Stereo matching for enhanced telepresence in three-dimensional video communications E.Izquierdo https://doi.org/10.1109/76.611174
  23. Rapport technique de l'INRS-T'el'ecommunications v.9 Geometric models in stereoscopic video C.H.Yang