Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Poisson Video Composition Using Shape Matching

형태 정합을 이용한 포아송 동영상 합성

  • Heo, Gyeongyong (Department of Electronic Engineering, Dong-Eui University) ;
  • Choi, Hun (Department of Electronic Engineering, Dong-Eui University) ;
  • Kim, Jihong (Department of Electronic Engineering, Dong-Eui University)
  • Received : 2017.12.01
  • Accepted : 2018.02.27
  • Published : 2018.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a novel seamless video composition method based on shape matching and Poisson equation. Video composition method consists of video segmentation process and video blending process. In the video segmentation process, the user first sets a trimap for the first frame, and then performs a grab-cut algorithm. Next, considering that the performance of video segmentation may be reduced if the color, brightness and texture of the object and the background are similar, the object region segmented in the current frame is corrected through shape matching between the objects of the current frame and the previous frame. In the video blending process, the object of source video and the background of target video are blended seamlessly using Poisson equation, and the object is located according to the movement path set by the user. Simulation results show that the proposed method has better performance not only in the naturalness of the composite video but also in computational time.

본 논문에서는 형태 정합 및 포아송 방정식을 기반으로 객체와 배경과의 이음매가 없는 효율적인 동영상 합성 기법을 제안한다. 동영상 합성 기법은 영상 분할 과정과 영상 조합 과정으로 구성된다. 영상 분할 과정에서는 먼저 첫번째 프레임에 대해 사용자가 3 영역 지도를 설정한 후, 그랩 컷(grab cut) 알고리즘을 수행한다. 그리고 객체와 배경의 색상, 밝기, 텍스쳐 등이 유사할 경우 영상 분할의 성능이 감소될 수 있음을 감안하여, 현재 프레임과 이전 프레임 객체들 간의 형태 정합을 통해 현재 프레임에서 영상 분할된 객체를 보정한다. 영상 조합 과정에서는 포아송 방정식을 이용하여 객체와 목표 동영상의 배경이 서로 이음매 없이 조합되도록 하며, 또한 사용자가 설정한 움직임 경로에 따라 객체를 배치한다. 모의실험을 통해 제안된 방법이 합성된 동영상의 자연성 뿐만 아니라 수행 시간 면에서 우수함을 알 수 있었다.

Keywords

References

  1. J. Wang, P. Bhat, R. A. Colburn, M. Agrawala, and M. F. Cohen, "Interactive Video Cutout," ACM SIGGRAPH 2005, pp. 585-594, July 2005.
  2. P. F. Felzenszwalb and D. P. Huttenlocher, "Efficient Graph-Based Image Segmentation," International Journal of Computer Vision, vol. 59, no. 2, pp. 167-181, January 2004. https://doi.org/10.1023/B:VISI.0000022288.19776.77
  3. C. J. Armstrong, B. L. Price, and W. A. Barrett, "Interactive Segmentation of Image Volumes with Live Surface," Computer Graphics, vol. 31, no. 2, pp. 212-229, February 2007. https://doi.org/10.1016/j.cag.2006.11.015
  4. X. Bai, J. Wang, D. Simons, and G. Sapiro, "Video Snapcut: Robust Video Object Cutout Using Localized Classifiers," ACM Transactions on Graphics, vol. 28, no. 3, pp. 1-11, July 2009.
  5. M. Grundmann and V. Kwatra, "Efficient Hierarchical Graph-Based Video Segmentation," [Internet]. Available: https://www.cc.gatech.edu/cpl/projects/videosegmentation/.
  6. T. Chen, J. Y. Zhu, A. Shamir, and S.M. Hu, "Motion-Aware Gradient Domain Video Composition," IEEE Transactions on Image Processing, vol. 22, no. 7, pp. 2532-2544, July 2013. https://doi.org/10.1109/TIP.2013.2251642
  7. K. F. Hussain and R. M. Kamel, "Efficient Poisson Image Editing," Electronic Letters on Computer Vision and Image Analysis, vol. 14, no. 2, pp. 45-57, December 2015.
  8. Richard J. Radke, Computer Vision for Visual Effects, Cambridge University Press, New York, 2013.
  9. M. Afifi, K. F. Hussain, H. M. Ibrahim, and N. M. Omar, "Video Face Replacement System Using a Modified Poisson Blending Technique," International Symposium on Intelligent Signal Processing and Communication Systems, pp.1-5, December 2014.
  10. I. S. Sevcenco and P. Agathoklis, "Video Editing in Gradient Domain Using a Wavelet based 3-D Reconstruction Algorithm and an Iterative Poisson Solver," IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, pp. 205-209, August 2015.
  11. M. C. Jeong, S. R. Kim, and H. S. Kang, "Super-resolution Reconstruction Method for Plenoptic Images based on Reliability of Disparity," Journal of the Korea Institute of Information and Communication Engineering, vol. 22, no. 3, pp.425-433, March 2018. https://doi.org/10.6109/JKIICE.2018.22.3.425
  12. N. Arora, M. Martolia, and A. Ashok, "A Comparative Study of the Image Registration Process on the Multimodal Medical Images," Asia-pacific Journal of Convergent Research Interchange, vol. 3, no. 1, pp.1-17, March 2017.

Cited by

  1. 동영상 합성을 위한 혼합 블랜딩 vol.24, pp.2, 2018, https://doi.org/10.6109/jkiice.2020.24.2.231