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

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

DOI QR Code

효율적인 구현을 위한 안개 제거 방법의 최적화

Optimization of Dehazing Method for Efficient Implementation

  • Kim, Minsang (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Park, Yongmin (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Kim, Byung-O (School of Electronics and Information Engineering, Korea Aerospace University) ;
  • Kim, Tae-Hwan (School of Electronics and Information Engineering, Korea Aerospace University)
  • 투고 : 2016.08.12
  • 심사 : 2016.09.26
  • 발행 : 2016.10.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 안개 제거의 수행 시간을 단축하기 위한 최적화 기법들을 제안하고, 이를 기반으로 하는 효율적인 안개 제거 방법을 제시한다. 제안하는 최적화 기법으로, 다크 채널을 동일 크기의 영역으로 분할하여 분산 정렬을 적용하여 대기 강도를 추정함으로써 대기 강도 추정에 필요한 정렬의 연산을 간소화하였고, 대기 강도를 단색으로 가정하여 전달량 추정에 필요한 영상 정규화 과정을 간소화하였다. 또한, 메디안 다크 채널을 도입하여 안개 제거 품질을 유지하면서도 전달량 보정 과정을 효과적으로 제거하였다. 제안하는 기법들을 바탕으로 효율적인 안개 제거 방법을 제시하였고, 이의 우수성을 입증하기 위해 프로토타입 시스템을 개발하여 성능을 분석하였다. 제안하는 안개 제거 방법은 기존 방법과 비교하여 대등한 안개 제거 품질을 보이면서도 수행 시간을 최대 65% 단축하였다.

This paper presents optimization techniques to reduce the processing time of the dehazing method and proposes an efficient dehazing method based on them. In the proposed techniques, the atmospheric light is estimated based on the distributed sorting of the dark channel pixels, so as to reduce the computations. The normalization process required in the transmission estimation is simplified by the assumption that the atmospheric light is monochromatic. In addition, the dark channel is modified into the median dark channel in order to eliminate the transmission refinement process while achieving a comparable dehazing quality. The proposed dehazing method based on the optimization techniques is presented and its performance is investigated by developing a prototype system. When compared to the previous method, the proposed dehazing method reduces the processing time by 65% while maintaining the dehazing quality.

키워드

참고문헌

  1. S. K. Nayar and S. G. Narasimhan, "Vision in bad weather," in Proc. of IEEE Conf. on Computer Vision, vol.2, pp. 820-827, Kerkyra, Greece, Sept., 1999.
  2. S. G. Narasimhan and S. K. Nayar, "Chromatic framework for vision in bad weather," in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 598-605, Jun. 2000.
  3. Y.Y. Schechner, S.G. Narasimhan and S.K. Nayar, "Instant Dehazing of Images Using Polarization," in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 325-332, Kauai, USA, 2001.
  4. S. G. Narasimhan and S. K. Nayar, "Contrast restoration of weather degraded images," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 6, pp. 713-724, Jun. 2003. https://doi.org/10.1109/TPAMI.2003.1201821
  5. R. T. Tan, "Visibility in bad weather from a single image," in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1-8, Anchorage, USA, Jun. 2008.
  6. R. Fattal, "Single image dehazing," ACM Trans. Graphics, vol. 27, no. 3, pp. 72, Aug. 2008. https://doi.org/10.1145/1360612.1360671
  7. K. He, J. Sun, and X. Tang, "Single image haze removal using dark channel prior," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2341-2353, Dec. 2011. https://doi.org/10.1109/TPAMI.2010.168
  8. W. T. Kim, H. W. Bae and T. H. Kim, "Fast and High-Quality Haze Removal Method Based on Transmission Correction," Journal of The Institute of Electronics and Information Engineers, vol. 51, no. 11, pp 165-173, Nov. 2014. https://doi.org/10.5573/ieie.2014.51.11.165
  9. W. T. Kim and T. H. Kim, "High-Speed and High-Quality Haze Removal Method Using Dual Dark Channels," The summer conference of Institute of Electronics and Information Engineers, pp. 655-658, Jun. 2015.
  10. H. Koschmieder, Theorie der horizontalen Sichtweite: Kontrast und Sichtweite, Keim & Nemnich, 1925.
  11. K. He, J. Sun, and X. Tang, "Guided image filtering," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 35, no. 6, pp. 1397-1409, Jun. 2013. https://doi.org/10.1109/TPAMI.2012.213
  12. K. B. Gibson, and D. T. Vo, and T. Q. Nguyen, "An investigation of dehazing effects on image and video coding," IEEE Trans. Image Processing, vol. 21, no. 2, pp. 662-673, Feb. 2012. https://doi.org/10.1109/TIP.2011.2166968

피인용 문헌

  1. OpenCL 기반의 상위 수준 합성 기술을 이용한 고성능 안개 제거 시스템의 소프트웨어-하드웨어 통합 설계 vol.54, pp.8, 2017, https://doi.org/10.5573/ieie.2017.54.8.45