Journal of the Institute of Electronics and Information Engineers (전자공학회논문지)

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

DOI QR Code

Fast and High-Quality Haze Removal Method Based on Transmission Correction

전달량 보정을 통한 고속 고품질의 안개 제거 방법

  • Kim, Won-Tae (School of electronics, Telecommunication and computer engineering, Korea Aerospace University) ;
  • Bae, Hyun-Woo (School of electronics, Telecommunication and computer engineering, Korea Aerospace University) ;
  • Kim, Tae-Hwan (School of electronics, Telecommunication and computer engineering, Korea Aerospace University)
  • 김원태 (한국항공대학교 항공 전자 및 정보 통신 공학부) ;
  • 배현우 (한국항공대학교 항공 전자 및 정보 통신 공학부) ;
  • 김태환 (한국항공대학교 항공 전자 및 정보 통신 공학부)
  • Received : 2014.09.15
  • Accepted : 2014.11.03
  • Published : 2014.11.25
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a fast and high-quality haze removal method by the modification of the conventional transmission estimation process. In the conventional haze removal method, the halo and blocking artifacts arises while estimating the transmission. In order to effectively reduce the artifacts, the proposed method employs the maximum filter after the calculation of the dark channel. Because of the reduction of the artifacts, the proposed method can simplify the transmission refinement process without sacrificing the quality of the results: this paper proposes to use the single-channel guided filter instead of the multi-channel guided filter. The experimental results demonstrate that the quality of the dehazed results by the proposed transmission correction process is improved and the haze removal speed is increased by up to 59.6%, when compared to the conventional ones.

본 논문은 기존의 안개 제거 방법에서 전달량(transmission) 추정 과정을 변경한 고속 고품질의 안개 제거 방법을 제안한다. 기존의 안개 제거 방법에서는 전달량 추정 과정에서 dark channel 연산에 의해서 후광(halo) 및 블록 현상이 발생하는데, 제안하는 방법은 이런 현상들을 효과적으로 줄이기 위해서 dark channel 연산 이후에 최대값 필터를 적용한다. 그 결과, 기존의 안개 제거 방법에서 전달량을 정련하기 위해서 수행하는 복잡한 연산 과정을 결과 영상의 품질 저하 없이 간소화 시킬 수 있다. 본 논문은 기존의 다 채널 유도 필터를 단 채널의 유도 필터로 대체하여 사용하는 것을 제안한다. 실험 결과는 제안하는 전달량 보정 과정에 의한 결과 영상의 우수한 품질과 기존의 안개 제거 속도에 비해 최대 59.6% 까지 향상된 안개 제거 속도를 입증한다.

Keywords

References

  1. S. G. Narasimhan and S. K. Nayar, "Chromatic framework for vision in bad weather," Proc. IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 598-605, June 2000.
  2. S. K. Nayar and S.G. Narasimhan, "Vision in bad weather," Proc. IEEE International Conference on Computer Vision, vol. 2, pp. 820-827, Sep. 1999.
  3. S. G. Narasimhan and S. K. Nayar, "Contrast restoration of weather degraded images," IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 25, no. 6, pp. 713-724, June 2003. https://doi.org/10.1109/TPAMI.2003.1201821
  4. R. Tan, "Visibility in bad weather from a single image," Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, June 2008.
  5. R. Fattal, "Single image dehazing," ACM Transactions on Graphics, vol. 27, no. 3, pp. 1-9, Aug. 2008.
  6. K. He, J. Sun, and X. Tang, "Single image haze removal using dark channel prior," IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 33, no. 12, pp. 2341-2353, Dec. 2011. https://doi.org/10.1109/TPAMI.2010.168
  7. K. He, J. Sun, and X. Tang, "Guided image filtering," IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 35, no. 6, pp. 1397-1409, June 2013. https://doi.org/10.1109/TPAMI.2012.213
  8. H. Koschmieder, Theorie der horizontalen sichtweite: kontrast und Sichtweite. Keim & Nemnich, 1925.
  9. S. C. Pei, and T. Y. Lee, "Effective image haze removal using dark channel prior and post-processing," Proc. IEEE International Symposium on Circuit and Systems, pp. 2777-2780, May 2012.
  10. S. C. Pei, and T. Y. Lee, "Nighttime haze removal using color transfer pre-processing and dark channel prior," Proc. IEEE International Conference on Image Processing, pp. 957-960, Oct. 2012.
  11. R. Gao, X. Fan, J. Zhang and Z. Luo, "Haze filtering with aerial perspective," Proc. IEEE International Conference on Image Processing, pp. 989-992, Sept. 2012.
  12. K. Wang, E. Dunn, J. Tighe, and J.M. Frahm, "Combining semantic scene priors and haze removal for single image depth estimation," Proc. IEEE Winter Conference on Application of Computer Vision, pp. 800-807, March 2014.
  13. H. J. Park, D. B. Park, H. S. Ko, "Novel Defog Algorithm via Evaluation of Local Color Saturation," Journal of The Institute of Electronics and Information Engineers, Vol. 51, No. 3, pp. 119-128, Mar. 2014.