대한전자공학회논문지SP (Journal of the Institute of Electronics Engineers of Korea SP)

대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지

파노라믹 영상 모델에 근거한 파라메트릭 비디오 압축

Parametric Video Compression Based on Panoramic Image Modeling

  • 발행 : 2006.07.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 파노라믹 영상 모델링에 근거한 비디오 압축 전송 방법을 제안한다. 제안한 방법은 회전 카메라에 입력되는 영상에서 배경 영상과 움직이는 물체로 분리하고 차영상을 추출하여 압축/전송하는 방법을 사용한다. 제안한 비디오 압축 시스템은 초기화 과정에서 전송된 파노라믹 영상으로부터 배경영상을 합성할 수 있도록 파라메터 만을 전송하게 된다. 본 논문 에서는 정확한 배경 합성을 위한 정확한 카메라 모델링 기반 파노라믹 영상 합성법을 제시하며, 이를 바탕으로 비디오 압축에 응용하는 방법을 제안하였다. 제안한 비디오 압축방법에 의하여 기존의 JPEG-2000이나 MPEG-4 비디오 압축 방법에 비하여 PSNR 관점에서 $2{\sim}4dB$ 효율적임을 보였다.

In this paper, a low bitrate video coding method based on new panoramic modeling is proposed for panning cameras. An input video frame from a panning camera is decomposed into a background image, rectangular moving object regions, and a residual image. In coding the background, we employ a panoramic model that can account for several image formation processes, such as perspective projection, lens distortion, vignetting and illumination effects. Moving objects aredetected, and their minimum bounding rectangular regions are coded with a JPEG-2000 coder. We have evaluated the effectiveness of the proposed algorithm with several indoor and outdoor sequences and found that the PSNR is improved by $1.3{\sim}4.4dB$ compared to that of JPEG-2000.

키워드

참고문헌

  1. I. Pavlidis, V. Morellas, P. Tsiamyrtzis, and S. Harp, 'Urban surveillance systems: From the laboratory to the commercial world,' Proceedings of IEEE, vol. 89, pp. 1478-1497, 2001 https://doi.org/10.1109/5.959342
  2. C. S. Regazzoni and G. L. Foresti, 'Guest editorial: Video processing and communications in real-time surveillance,' Real-Time Imaging, vol. 7, pp. 381-388, 2001 https://doi.org/10.1006/rtim.2001.0207
  3. C. Regazzoni, V. Ramesh, and G. L. Foresti, 'Special Issue on video communications, processing, and understanding for third generation surveillance systems,' Proceedings of IEEE, vol. 89, pp. 1355-1367, 2001 https://doi.org/10.1109/5.959335
  4. B. Rieger and H. Rode, 'Digital image recording for court-related purposes,' Proc. Security Technology, pp. 262-279, 1999 https://doi.org/10.1109/CCST.1999.797924
  5. T. Boult, R. J. Micheals, X. Gao, and M. Eckmarm, 'Into the woods: Visual surveillance of noncooperative and camouflaged targets in complex outdoor setting,' Proceedings of IEEE, vol. 89, pp. 1382-1402, 2001 https://doi.org/10.1109/5.959337
  6. T. Sikora, 'The MPEG-4 video standard verification model,' IEEE Trans. Circuits and Systems for Video Technology, vol. 7, pp. 19-31, 1997 https://doi.org/10.1109/76.554415
  7. ISO/IEC 14496-2: Information technology-Coding of audio-visual objects, Part-2
  8. C. Christopoulos, J. Askelof, and M. Larsson, 'Efficient methods for encoding regions of interest in the upcoming JPEG2000 still image coding standard,' Int. Conf. Image Processing, vol. 2, pp. 247-249, 2000 https://doi.org/10.1109/97.863146
  9. ISO/IEC 15444-1: Information technology- JpEG 2000 image coding system-Part 1: Core coding system, 2000
  10. H.-Y. Shum and R. Szeliski, 'Construction and refinement of panoramic mosaics with global and local alignment,' Proc. Conf. Computer Vision, pp. 953-956, 1998 https://doi.org/10.1109/ICCV.1998.710831
  11. R. Szeliski, 'Video mosaics for virtual environments,' Computer Graphics and Applications, vol. 15, no. 2, pp. 22-30, 1996 https://doi.org/10.1109/38.486677
  12. S. Peleg and J. Herman, 'Panoramic mosaics by manifold projection,' Proc. Computer Vision Pattern Recognition, pp. 338-343, 1997
  13. P. J. Burt, M. Irani, S. C. Hsu, P. Anandan, and M. W. Hansen, 'Method and apparatus for performing mosaic based image compression,' United States Patent 5,991,444, Nov. 1999
  14. Y. Altunbasak, R. M. Mersereau, and A. J. Patti, 'A fast parametric motion estimation algorithm with illumination and lens distortion correction,' IEEE Trans. Image Processing, vol. 12, pp. 395-408, 2003 https://doi.org/10.1109/TIP.2003.809012
  15. Z. Zhang, 'On the epipolar geometry between two images with lens distortions,' Proc. Int. Conf. Pattern Recognition, vol. 1, pp. 407-411, 1996 https://doi.org/10.1109/ICPR.1996.546059
  16. G. Stein, 'Lens distortion calibration using point correspondences,'; Proc. IEEE Colli. Computer Vision and Pattern Recognition, pp. 602-608, 1997 https://doi.org/10.1109/CVPR.1997.609387
  17. M. J. Black and P. Anandan, 'The robust estimation of multiple motions: Affine and piecewise smooth flow fields,' Computer Vision and Image Understanding, vol. 63, pp. 75-104, 1996 https://doi.org/10.1006/cviu.1996.0006
  18. D. -G. Simand R. - H. Park, 'Robust reweighted MAP motion estimation,' IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, pp. 353-365, 1998 https://doi.org/10.1109/34.677261
  19. M. D. Adams and F. Kossentini, 'Jasper: a software-based JPEG-2000 codec implementation,' Int. Conf. Image Processing, vol. 2, pp. 53-56, 2000 https://doi.org/10.1109/ICIP.2000.899223