DOI QR코드

DOI QR Code

영상에서 주파수 기반의 초점/비초점 분석을 이용한 깊이 지도 생성 기법

A Depth Creation Method Using Frequency Based Focus/Defocus Analysis In Image

  • Received : 2014.09.08
  • Accepted : 2014.11.20
  • Published : 2014.11.28

Abstract

본 논문에서는 초점/비초점 영상에서 깊이 지도를 효율적으로 추출하기 위하여 그래프 컷(Graph Cut)과 이산 웨이블릿 변환(Discrete Wavelet Transform)을 이용한 깊이 지도 생성 기법을 제안한다. 제안하는 방법은 우선 해당 영상을 영역 별로 처리하기 위해 그래프 컷 방법으로 각 픽셀 간의 유사도를 이용하여 분할한다. 그 다음 분할 영역을 레이블링 하여 원 영상의 분할 영역 정보를 생성한다. 그리고 이산 웨이블릿 변환을 이용하여 원 영상 내의 주파수 정보를 나타내는 LL, LH, HH, HL 부대역(Subband)을 생성한다. 마지막으로 4개의 부대역 중 영상의 초점/비초점 영역을 분석할 단서가 되는 HH, HL 대역을 이용하여 주파수 지도를 생성한 뒤 분할 영역에 따라 깊이 정보를 계산함으로써 깊이 지도를 추출한다. 제안하는 방법은 초점 정보인 블러(Blur)의 양에 따라 동적인 깊이의 할당이 가능하여 효율적인 깊이 지도의 생성이 가능하였다. 실험으로 PSNR(Peak Signal to Noise Ratio) 방법을 통해 제안하는 방법의 성능을 평가하였다.

In this paper, we propose an efficient detph map creation method using Graph Cut and Discrete Wavelet Transform. First, we have segmented the original image by using Graph Cut to process with its each areas. After that, the information which describes segmented areas of original image have been created by proposed labeling method for segmented areas. And then, we have created four subbands which contain the original image's frequency information. Finally, the depth map have been created by frequency map which made with HH, HL subbands and depth information calculation along the each segmented areas. The proposed method can perform efficient depth map creation process because of dynamic allocation using depth information. We also have tested the proposed method using PSNR(Peak Signal to Noise Ratio) method to evaluate ours.

Keywords

References

  1. Hyun-Ho Han, Gye-Dong Chung, Young-Soo Park, Sang-Hun Lee, Foreground Extraction and Depth Map Creation Method based on Analyzing Focus/Defocus for 2D/3D Video Conversion. The Journal of Digital Policy & Management, Vol. 11, No. 1, pp. 243-248, 2013.
  2. Sung-Ho Han, Yo-Sup Kim, Jong-Yong Lee, Sang-Hun Lee, 2D/3D conversion method using depth map based on haze and relative height cue. The Journal of Digital Policy & Management, Vol. 10, No. 9, pp. 351-356, 2012.
  3. Keyur R. Ranipa, M. V. Joshi, A practical approach for depth estimation and image restoration using defocus cue, Machine Learning for Signal Processing (MLSP), 2011 IEEE International Workshop on, pp.1-6, 2011.
  4. Edward H. Adelson, John Y. A. Wang, Single Lens Stereo with a Plenopic Camera, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 14, No.2, pp.99-106, 1992. https://doi.org/10.1109/34.121783
  5. Wei. Y, Zajli Dong, Wu. Chengdong, Global Depth from Defocus with Fixed Camera Parameters, Mechatronics and Automation, ICMA 2009, pp.1887-1892, 2009.
  6. Huadong Sun, Zhije Zhao, Xuesong Jin, Lianding Niu, Lizhi Zhang, Depth from defocus and blur for single image, Visual Communications and Image Processing (VCIP), pp. 1-5, 2013.
  7. Vladislav Skorpil, Jiri Stastny, Wavelet Transform for Image Analysis, Artificial Intelligence, 2009. JCAI '09 International Joint Conference on, pp. 480-483, 2009.
  8. Pedro F. Felzenszwalb, Daniel P. Huttenlocher, Efficient Graph-Based Image Segmentation, International Journal of Computer Vision, Kluwer Academic Publishers, Vol. 59, No. 2, pp. 167-181, 2004. https://doi.org/10.1023/B:VISI.0000022288.19776.77
  9. Yi Zhang, Hirakawa K, Blur Processing Using Double Discrete Wavelet Transform, Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp. 1091-1098, 2013.
  10. Chang-Min Choi, Tae-Sun Choi, Ying-Chang Chen, Depth From Defocus using Wavelet Transform, The Institute of Electronics Enginners of Korea, vol. 49-SC, No. 4, pp.19-26, 2005.
  11. Kwang-Hyun Kim, Seung-Seob Park, A Comparative Study on broadcasting video quality using PSNR in IPTV network adopted transition mechanism, The Journal of the Korea Institute of Maritime Information & Communication Sciences, The Korea Institue of Maritime Information & Communication Sciences, Vol. 14, No. 1, pp. 156-166, 2010.
  12. Valentina Pullano, Alessandro Vanelli-Coralli, Giovanni E. Corazza, PSNR evaluation and alignment recovery for mobile satellite video broadcasting, Advanced Satellite Multimedia Systems Conference (ASMS) and 12th Signal Processing for Space Communications Workshop (SPSC), 2012 6th, pp.176-181, 2012.