DOI QR코드

DOI QR Code

GPGPU based Depth Image Enhancement Algorithm

GPGPU 기반의 깊이 영상 화질 개선 기법

  • Han, Jae-Young (Department of Electronic Engineering, Kwangwoon University) ;
  • Ko, Jin-Woong (Department of Electronic Engineering, Kwangwoon University) ;
  • Yoo, Jisang (Department of Electronic Engineering, Kwangwoon University)
  • Received : 2013.08.05
  • Accepted : 2013.09.17
  • Published : 2013.12.31

Abstract

In this paper, we propose a noise reduction and hole removal algorithm in order to improve the quality of depth images when they are used for creating 3D contents. In the proposed algorithm, the depth image and the corresponding color image are both used. First, an intensity image is generated by converting the RGB color space into the HSI color space. By estimating the difference of distance and depth between reference and neighbor pixels from the depth image and difference of intensity values from the color image, they are used to remove noise in the proposed algorithm. Then, the proposed hole filling method fills the detected holes with the difference of euclidean distance and intensity values between reference and neighbor pixels from the color image. Finally, we apply a parallel structure of GPGPU to the proposed algorithm to speed-up its processing time for real-time applications. The experimental results show that the proposed algorithm performs better than other conventional algorithms. Especially, the proposed algorithm is more effective in reducing edge blurring effect and removing noise and holes.

본 논문에서는 3D 콘텐츠 생성 시 필요한 깊이 영상의 화질 개선을 위하여 잡음 제거 기법과 홀 채움 기법을 제안한다. 제안하는 기법에서는 컬러 영상과 깊이 영상을 모두 이용하게 된다. 먼저 입력된 컬러 영상을 RGB 색상계에서 HSI 색상계로 변환하여 밝기 영상을 생성한다. 그리고 깊이 영상에서 기준 화소와 주변 화소간의 거리 값, 깊이 값의 차이를 구하고 컬러 영상의 밝기 값 차이를 계산하여 제안하는 잡음 제거 기법에 이용한다. 이후 홀을 탐색하여 홀과 주변 화소간의 거리, 컬러 영상의 밝기 값 차이를 제안하는 홀 채움 기법을 적용하여 깊이 영상 내에 존재하는 홀을 채우게 된다. 마지막으로 실시간 환경에 적용하기 위하여 제안하는 기법을 GPU로 병렬화하여 속도 향상을 하고자 하였다. 실험을 통하여 제안한 기법이 기존 기법에서 발생하는 경계 부분의 흐려짐 현상을 줄이면서 홀을 채우는 것을 확인하였다.

Keywords

References

  1. J. Choi, D. Min, B. Ham and K. Sohn, "Spatial and temporal up-conversion technique for depth video," IEEE International Conference on Image Processing(ICIP), Cairo, pp. 3525-3528, Nov. 2009.
  2. O. P. Gangwal and R. P. Benetty, "Depth map post-processing for 3D-TV," Digest of Technical Papers International Conference on Consumer Electronics(ICCE), Las Vegas, NV, pp. 1-2, Jan. 2009.
  3. Y. Li and, L. Sun, "A novel up-sampling scheme for depth map compression in 3DTV system," Picture Coding Symposium(PCS), Nagoya, pp. 186-189, Dec. 2010.
  4. J. Park, H. Kim, Y. Tai, M. Brown, and I. Kweon, "High quality depth map up-sampling for 3D-TOF cameras," IEEE International Conference on Computer Vision (ICCV), Barcelona, pp. 1623-1630, Nov. 2011.
  5. J. Y. Han, Y. H. Seo, J. Yoo, "Depth map enhancement using advanced joint bilateral filter based on GPGPU," KICS Conference, Youngpyong, pp. 157-158, Jan. 2013.
  6. C. Tomasi and R. Manduchi, "Bilateral filtering for gray and color images," IEEE International Conference on Computer Vision, Bombay, pp.839-846, Jan. 1998.
  7. Sylvain Paris and Fredo Durand, "A fast approximation of the bilateral filter using a signal processing approach," Springer International Journal of Computer Vision, vol.81, no.1, pp.24-52, Jan. 2009 https://doi.org/10.1007/s11263-007-0110-8
  8. J. Kopf, M. Cohen, D. Kischinski and M. Uyttendaele, "Joint bilateral up-sampling," ACM Trans. on Graphics, vol.26, no.3, article 96, pp.2:1-2:9, July 2007. https://doi.org/10.1145/1276377.1276404
  9. S. Mattoccia, M. Viti and F. Ries, "Near real-time Fast Bilateral Stereo on the GPU," Computer Vision and Pattern Recognition Workshops(CVPRW), Colorado Springs, CO pp.136-143, June 2011.
  10. L. Wang, R. Yang, M. Gong and, M. Liao, "Real-time stereo using approximated joint bilateral filtering and dynamic programming," Journal of Real-Time Image Processing, pp.1-15, Sept. 2012.
  11. J. Wasza, S. Bauer and J. Hornegger, "Real-time preprocessing for dense 3-D range imaging on the GPU: Defect interpolation, bilateral temporal averaging and guided filtering," Computer Vision Workshops(ICCV Workshops), Barcelona, pp.1221-1227, Nov. 2011.
  12. J. Wasza, S. Bauer and J. Hornegger, "High Performance GPU-Based Preprocessing for Time-of-Flight Imaging in Medical Applications," Bildverarbeitung Fur Die Medizin 2011, Lubeck, pp.324-328, Mar. 2011.

Cited by

  1. Using Numerical Maps to Select Solar Panel Installation Sites no Expressway Slopes vol.17, pp.5, 2016, https://doi.org/10.6106/KJCEM.2016.17.5.071