Adaptively Compensated-Disparity Prediction Scheme for Stereo Image Compression and Reconstruction

스테레오 영상 압축 및 복원을 위한 적응적 변이보상 예측기법

  • 배경훈 (광운대학교 전자공학과 국가지정 3차원 영상미디어 연구실) ;
  • 김은수 (광운대학교 전자공학과 국가지정 3차원 영상미디어 연구실)
  • Published : 2002.07.01

Abstract

In this paper, an effective stereo image compression and reconstruction technique using a new adaptively compensated-disparity prediction scheme is proposed. That is, by adaptively predicting the mutual correlation between the stereo image using the proposed method, the bandwidth of the stereo input image can be compressed to the level of the conventional 2D image and the predicted image also can be effectively reconstructed using this transmitted reference image and disparity data in the receiver. Especially, in the proposed method, once the feature values are extracted from the input stereo image, then the matching window size for the predicted image reconstruction is adaptively selected in accordance with the magnitude of this feature values. From this adaptive disparity estimation method, reduction of the mismatching probability of the disparity vectors is expected and as a result, the image quality in the reconstructed image can be improved. In addition, from some experiments using the CCETT's stereo images of 'Fichier', 'Manege' and 'Tunnel', it is shown that the proposed method improves the PSNR of the reconstructed image to about 9.08 dB on average by comparing with that of the conventional methods. And also, it is found that there is almost no difference between the original image and the predicted image reconstructed through the proposed method by comparison to that of the conventional methods.

본 논문에서는 적응적 변이보상 예측기법을 이용한 효과적인 스테레오 영상 압축 및 복원 방법을 제안하였다. 즉, 스테레오 영상간의 상호 상관도를 적응적으로 추정함으로써 단안 영상을 전송하는데 필요한 수준으로 전송 대역폭을 효율적으로 압축하고 복원할 수 있는 적응적 변이보상 예측기법을 제안하였다. 특히, 예측된 영상을 복원할 때, 스테레오 영상에서 추출된 특징값의 크기에 따른 적응적 정합기법을 적용함으로써 잘못된 변이벡터의 추정을 감소시키고 전체적인 변이의 신뢰도를 향상시켜 복원된 영상의 화질을 개선하였다. CCETT의 'Fichier', 'Manege' 및 'Tunnel' 영상을 사용한 실험한 결과, 제안된 적응적 변이보상 예측기법에 의해 복원된 영상은 기존의 화소기반 및 블록기반 방식에 비해 PSNR이 약 9.08dB 향상됨을 확인하였고, 오차영상의 비교에서도 기존의 방식보다 제안된 기법을 적용한 복원영상이 원영상과 차이가 거의 없음이 분석되었다.

Keywords

References

  1. Grinberg, V. 'Geometry of Binocular Imaging,' Proc. SPIE vol. 2177, pp. 56 - 65, February 1994
  2. 김은수/이승현 공역, '3차원 영상의 기초', 기다리, 1998
  3. Mark S. Moellenhoff, Mark W. Maier, 'Characteristics of disparity-compensated stereo image pair residuals', Signal Processing : Image Communication, vol. 14, pp 55 -69, 1998 https://doi.org/10.1016/S0923-5965(98)00028-9
  4. Kyung-hoon Bae, Song-taek Lim, Eun-soo Kim, 'Adaptive Disparity Estimation and Intermediate View Reconstruction for Multiview 3D Imaging System', Proc. of SPIE, vol. 4660A, San Jose, California, January 2001
  5. W. E. L. Grimson, 'Computational experiments with a feature based stereo algorithm', IEEE Trans. on Pattern Anal. Machine Intell., vol.7, pp. 17-34, 1985 https://doi.org/10.1109/TPAMI.1985.4767615
  6. Anthony Mancini, 'Disparity Estimation and Intermediate View Reconstruction for Novel Applications in Stereoscopic Video', McGill University, February 1998
  7. Ebroul Izquierdo M, 'Stereo matching for enhanced telepresence in three-dimensional video communications', IEEE transactions on circuits and systems for video technology, vol. 7, no. 4, pp. 629-643, August 1997 https://doi.org/10.1109/76.611174
  8. Cheng Hong Yang, 'Geometric Models in Stereoscopic Video', Rapport technique de l'INRS-T'el'ecommunications no. 95-12, 1995
  9. Z. Zhang, 'Determining the epipolar geometry and its uncertainty: A review', Tech. Rep. technical Report 2927, INRIA, Sophia-Antipolis, France, July 1996
  10. http://www.tnt.uni-hannover.de/js/project/eu/distima/images/