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

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

Feature-based Disparity Correction for the Visual Discomfort Minimization of Stereoscopic Video Camera

입체영상의 시각 피로 최소화를 위한 특징기반 시차 보정

  • Jung, Eun-Kyung (School of Electrical and Electronic Engineering, Kyungpook National University) ;
  • Kim, Chang-Il (School of Electrical and Electronic Engineering, Kyungpook National University) ;
  • Baek, Seung-Hae (School of Electrical and Electronic Engineering, Kyungpook National University) ;
  • Park, Soon-Yong (School of Computer Science and Engineering, Kyungpook National University)
  • 정은경 (경북대학교 전자전기컴퓨터공학부) ;
  • 김창일 (경북대학교 전자전기컴퓨터공학부) ;
  • 백승해 (경북대학교 전자전기컴퓨터공학부) ;
  • 박순용 (경북대학교 IT대학 컴퓨터학부)
  • Received : 2011.09.03
  • Published : 2011.11.25
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a disparity correction technique to reduce the inherent visual discomfort while watching stereoscopic videos. The visual discomfort must be solved for commercial 3D display systems to provide natural stereoscopic videos to human eyes. The proposed disparity correction technique consists of horizontal and vertical disparity corrections. The horizontal disparity correction is implemented by controlling the depth budget of stereoscopic video using the geometric relations of a stereoscopic camera system. In addition, the vertical disparity correction is implemented by using a feature-based stereo matching algorithm. Conventional vertical disparity corrections have been done by only using camera calibration parameters, which still cause systematic errors in vertical disparities. In this paper, we minimize the vertical disparity as small as possible by using a feature-based correction algorithm. Through the comparisons of conventional feature-based correction algorithms, we analyze the performance of the proposed technique.

본 논문에서는 입체영상을 시청할 때 흔히 발생할 수 있는 시각 피로를 최소화하기 위한 시차 보정 기술을 제안한다. 시각 피로는 3차원 TV의 상용화에 있어 반드시 풀어야 할 문제이다. 본 논문에서 제안하는 시차 보정 기술은 좌, 우 입체카메라의 기하학적 분석을 통하여 영상의 깊이감을 조정하는 수평시차 보정과 특징 정합 기반의 수직시차 보정으로 구성된다. 기존의 시차 보정은 주로 입체영상 카메라의 기하적 관계를 캘리브레이션(calibration) 과정을 거쳐 구하고 그 결과값을 이용하였다. 그러나 캘리브레이션의 오류로 인한 시차의 오차가 여전히 발생하는 문제가 있었다. 본 연구에서는 수평시차는 입체카메라의 캘리브레이션 정보를 사용하는 반면 수직시차는 특징점 정합 기반의 보정 알고리즘을 사용하여 수직시차의 오차를 최소화하였다. 유사한 특징점 정합 기반의 보정 알고리즘과의 비교를 통하여 제안 알고리즘의 성능을 분석하였다.

Keywords

References

  1. T. M. Lambooij, W. A. Ijsselsteijn and I. Heynderickx, "Visual Discomfort in Stereoscopic Displays: A Review," in Proc. SPIE, vol. 6490, pp.649001, 2007.
  2. D. F. McAllister, "Display Technology : stereo & 3D Display Technologies," Encyclopedia of Imaging Science and Technology, vol.2, pp.1327-1344, 2002.
  3. A. J. Woods, K. L. Yuen and K. S. Karvinen, "Characterizing Crosstalk in Anaglyphic Stereoscopic Images on LCD," Society for Information Display, Vol. 15, pp.889-898, 2007. https://doi.org/10.1889/1.2812989
  4. 이형철, "3D 비디오 영상과 휴먼팩터," 전자공학회논문지, 제37권, 제9호 84-92쪽, 2010년 9월.
  5. C. I. Kim and S. Y. Park, "Feature based Stereo matching using a Feature Window," The 26th ICROS Annual Conference, 2011.
  6. A. Fusiello, E. Trucco, and A. Verri. "A compact Algorithm for Rectification of Stereo Pairs," Machine Vision and Applications, vol. 12, No.1, pp. 16-22, 2000. https://doi.org/10.1007/s001380050120
  7. F. Zilly, M. Muller, P. Eisert and P. Kauff, "Joint Estimation of Epipolar Geometry and Rectification Parameters using Point Correspondences for Stereoscopic TV Sequences," Proc. 3DPVT, Paris, France, 2010.
  8. M. Lang, A. Hornung, O. Wang, S. Poulakos, A. Smolic, M. Gross, D. R. Zurich and E. Zurich, "Nonlinear Disparity Mapping for Stereoscopic 3D," Proc. Of the ACM SIGGRAPH, vol.29, No. 3, pp.25-29, 2010.
  9. Z. W. Gao, W. K. Lin, Y. S. Shen, C. Y. Lin and W. C. Kao, "Design of Signal Processing Pipeline for Stereoscopic Cameras," Transactions on Consumer Electronics, vol. 56, No.2, pp.324-331, 2010. https://doi.org/10.1109/TCE.2010.5505935
  10. S. Kumar, C. Micheloni, C.Piciarelli and G. L. Foresti, "Stereo Rectification of Uncalibrated and Heterogeneous Images," Pattern Recognition Letters, vol.31, pp.1445-1452, 2010. https://doi.org/10.1016/j.patrec.2010.03.019
  11. Lowe, David G. "Object recognition from local scale-invariant features," Proceedings of the International Conference on Computer Vision. pp. 1150-1157, 1999.
  12. N. Blenn, N. V. Feestenberg, M. Spehr and S. Gumhold, "A Tool For Automatic Preprocessing Stereoscopic-Video," in Proc. SPIE, vol.7524, pp. 75241J-75241J-9, 2010.
  13. G. Jones, D. Lee, N. Holliman, and D. Ezra, "Controlling perceived depth in stereoscopic images," in Stereoscopic Displays and Virtual Reality Systems VIII, Proceedings of SPIE 4297A, 2001.
  14. Z. Zhang, O. Faugeras and R. Deriche, "An Effective Technique for Calibrating a Binocular Stereo Through Projective Reconstruction Using Both a Calibration Object and the Environment," Journal of Computer Vision Research, Vol. 1, No. 1, pp.58-68, 1997.
  15. Nvidia,http://developer.nvidia.com/category/zone /cuda-zone.
  16. H. Bay, A. Ess, T. Tuytelaars and L. V. Gool, "Speeded-Up Robust Features", Computer Vision and Understanding, pp.346-359, 2008.
  17. C. Tomasi and T. Kanade, "Detection and Tracking of point Features," International journal of Computer Vision, vol. 9, pp.137-154, 1991.