Journal of Broadcast Engineering (방송공학회논문지)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지
DOI QR코드

DOI QR Code

Advanced Seam Finding Algorithm for Stitching of 360 VR Images

개선된 Seam Finder를 이용한 360 VR 이미지 스티칭 기술

  • Son, Hui-Jeong (Sejong University, Dept. of Electrical Engineering) ;
  • Han, Jong-Ki (Sejong University, Dept. of Electrical Engineering)
  • 손희정 (세종대학교 전자정보통신공학과) ;
  • 한종기 (세종대학교 전자정보통신공학과)
  • Received : 2018.07.11
  • Accepted : 2018.08.21
  • Published : 2018.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

VR (Virtual Reality) is one of the important research topics in the field of multimedia application system. The quality of the visual data composed from multiple pictures depends on the performance of stitching technique. The stitching module consists of feature extraction, mapping of those, warping, seam finding, and blending. In this paper, we proposed a preprocessing scheme to provide the efficient mask for seam finder. Incorporating of the proposed mask removes the distortion, such as ghost and blurring, in the stitched image. The simulation results show that the proposed algorithm outperforms other conventional techniques in the respect of the subjective quality and the computational complexity.

스티칭 기술은 고화질의 360 VR 영상을 제작하는 과정에서 가장 중요한 요소 기술들 중의 하나이다. 스티칭 기술의 성능을 저하시키는 원인들에는 특징점 추출 과정의 오류, seam finding 과정에서 사용되는 마스크의 왜곡으로 발생하는 오류, 각 영상들의 밝기 보상 오류 등 다양한 원인들이 존재한다. 본 논문에서는 합성되는 각 영상들 간의 시차(View Disparity)가 존재함으로써 스티칭 성능이 저하되는 현상을 분석하고, 이 문제를 해결하기 위해 이음부 탐색(seam finding)의 전처리 과정에서 사용되는 효율적인 알고리즘을 제안한다. 본 논문에서 제안하는 기술을 통해 기존 방법보다 개선된 마스크들을 제작하여 효율적인 이음부 탐색(seam finding)이 수행되도록 하고, 그 결과 개선된 화질을 갖는 360 VR 영상을 얻을 수 있음을 설명한다. 본 논문에서 실시된 다양한 실험들을 통해, 제안된 기술이 시차 왜곡이 존재하는 영상 신호들을 합성하는 과정에 효율적이면서 동작 복잡도도 높지 않음을 보이고 있다.

Keywords

References

  1. Chang-Hoon Kang, "Flow of next generation broadcast video, Present and Future of VR contents," The Korea Contents Association Review, Vol. 14, No. 2, pp. 14-18, 2016, June.
  2. J. G. Andrews et al., "What Will 5G Be?," in IEEE Journal on Selected Areas in Communications, vol. 32, no. 6, pp. 1065-1082, June, 2014. https://doi.org/10.1109/JSAC.2014.2328098
  3. ITU-T/ISO/IEC JVET, "Results of the Joint Call for Evidence on Video Compression with Capability beyond HEVC", JVET-G1004-v2, July, 2017.
  4. ITU-T/ISO/IEC JVET, "Algorithm descriptions of projection format conversion and video quality metrics in 360Lib", JVET-E1003, January, 2017.
  5. ITU-T/ISO/IEC JVET, "Common Test Conditions and Evaluation Procedures for HDR/WCG Video Coding", JVET-D1020, October, 2016.
  6. M. Domański, O. Stankiewicz, K. Wegner and T. Grajek, "Immersive visual media -MPEG-I: 360 video, virtual navigation and beyond," 2017 International Conference on Systems, Signals and Image Processing (IWSSIP), Poznan,pp. 1-9, May, 2017.
  7. W. Li, C. B. Jin, M. Liu, H. Kim and X. Cui, "Local similarity refinement of shape-preserved warping for parallax-tolerant image stitching," in IET Image Processing, vol. 12, no. 5, pp. 661-668, May, 2018. https://doi.org/10.1049/iet-ipr.2017.0037
  8. N. Li, Y. Xu and C. Wang, "Quasi-Homography Warps in Image Stitching," in IEEE Transactions on Multimedia, vol. 20, no. 6, pp. 1365-1375, June 2018. https://doi.org/10.1109/TMM.2017.2771566
  9. K. Y. Lee and J. Y. Sim, "Stitching for Multi-View Videos With Large Parallax Based on Adaptive Pixel Warping," in IEEE Access, vol. 6, pp. 26904-26917, 2018. https://doi.org/10.1109/ACCESS.2018.2835659
  10. M.Brown, D. G. Lowe, "Automatic Panoramic Image Stitching using Invariant Features",International Journal of Computer Vision, Volume 74 Issue 1, Pages 59 - 73, August 2007. https://doi.org/10.1007/s11263-006-0002-3
  11. M. Uyttendaele, A. Eden and R. Skeliski, "Eliminating ghosting and exposure artifacts in image mosaics," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, pp. II-509-II-516 vol.2, December, 2001.
  12. Vladan Rankov, Rosalind J. Locke, Richard J. Edens, Paul R. Barber, Borivoj Vojnovic, "An algorithm for image stitching and blending", SPIE 5701, Three-Dimensional and Multidimensional Microscopy: Image Acquisition and Processing XII, March 2005.
  13. Muthukrishnan.R, M.Radha," Edge detection techniques for image segmentation",International Journal of Computer Science & Information Technology (IJCSIT) Vol 3, No 6, Pages 259 - 267,December, 2011. https://doi.org/10.5121/ijcsit.2011.3620
  14. Chetan Arora, Subhashis Banerjee, Prem Kalra, and S. Maheshwari. An efficient graph cut algorithm for computer vision problems. In Computer Vision ECCV 2010, volume 6313 of Lecture Notes in Computer Science, pages 552-565. Springer Berlin / Heidelberg, 2010.
  15. Y. Boykov and V. Kolmogorov, "An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 9, pp. 1124-1137, Sept. 2004. https://doi.org/10.1109/TPAMI.2004.60