한국전자통신학회논문지 (The Journal of the Korea institute of electronic communication sciences)

한국전자통신학회 (Korea Institute of Electronic Communication Science)
권호 표지
DOI QR코드

DOI QR Code

픽셀 기반 Joint BDCP와 계층적 양방향 필터를 적용한 단일 영상 기반 안개 제거 기법

Single Image Haze Removal Technique via Pixel-based Joint BDCP and Hierarchical Bilateral Filter

  • 오원근 (순천대학교 멀티미디어공학과) ;
  • 김종호 (순천대학교 멀티미디어공학과)
  • 투고 : 2018.12.20
  • 심사 : 2019.02.15
  • 발행 : 2019.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 픽셀 기반 joint BDCP (bright and dark channel prior)와 계층적 양방향 필터를 적용하여 저 복잡도를 갖는 단일 영상 기반 안개 제거 기법을 제안한다. 픽셀 기반 joint BDCP는 기존의 패치 기반 DCP에 비해 연산량을 감소시키고, 픽셀 단위의 안개값 예측을 가능하게 하여 전달량 추정의 정확성을 높인다. 또한 에지를 보존하면서 평탄화 성능이 우수한 양방향 필터를 사용하여 전달량을 정련함으로써 후광 효과(halo effect)를 줄이고, 에지 성분에 대한 계층적 적용을 통해 반복 적용에 의한 연산량의 증가를 방지한다. 안개 성분이 포함된 다양한 영상에 대해 수행한 실험 결과는 제안하는 기법이 기존의 기법에 비해 우수한 안개 제거 성능을 보이면서 저 복잡도로 실행되어 다양한 분야에 응용될 수 있음을 나타낸다.

This paper presents a single image haze removal method via a pixel-based joint BDCP (bright and dark channel prior) and a hierarchical bilateral filter in order to reduce computational complexity and memory requirement while improving the dehazing performance. Pixel-based joint BDCP reduces the computational complexity compared to the patch-based DCP, while making it possible to estimate the atmospheric light in pixel unit and the transmission more accurately. Moreover the bilateral filter, which can smooth an image effectively while preserving edges, refines the transmission to reduce the halo effects, and its hierarchical structure applied to edges only prevents the increase of complexity from the iterative application. Experimental results on various hazy images show that the proposed method exhibits excellent haze removal performance with low computational complexity compared to the conventional methods, and thus it can be applied in various fields.

키워드

KCTSAD_2019_v14n1_257_f0001.png 이미지

그림 1. 안개 영상 획득의 광학적 모델 Fig. 1 Optical model for hazy image acquisition

KCTSAD_2019_v14n1_257_f0002.png 이미지

그림 2. Manhattan 영상에 대한 안개 제거 결과. (a) 안개 영상, (b) Tan의 방법, (c) Fattal의 방법, (d) He의 방법, (e) 제안한 방법 Fig. 2 Haze removal results for Manhattan image. (a) Input hazy image, (b) Tan's method, (c) Fattal's method, (d) He's method, (e) Proposed method

KCTSAD_2019_v14n1_257_f0003.png 이미지

그림 3. Yosemite 영상에 대한 안개 제거 결과. (a) 안개 영상, (b) Tan의 방법, (c) Fattal의 방법, (d) He의 방법, (e) 제안한 방법 Fig. 3 Haze removal results for Yosemite image. (a) Input hazy image, (b) Tan's method, (c) Fattal's method, (d) He's method, (e) Proposed method

표 1. 안개 제거 기법의 실행시간 비교 Table 1. Execution time comparison of each haze removal method

KCTSAD_2019_v14n1_257_t0001.png 이미지

참고문헌

  1. S. Lee, S. Yun, J. Nam, C. Won, and S. Jung, "A Review on Dark Channel Prior based Image Dehazing Algorithms," The European Association for Signal Processing (EURASIP) J. on Image and Video Processing, vol. 2016, no. 4, Dec. 2016, pp. 1-23.
  2. C. Yeh, L. Kang, M. Lee, and C. Lin, "Haze Effect Removal from Image via Haze Density Estimation in Optical Model," Optics Express, vol. 21, no. 22, Nov. 2013, pp. 27127-27141. https://doi.org/10.1364/OE.21.027127
  3. S. Kim and G. Seok, "Effective Eye Detection for Face Recognition to Protect Medical Information," J. of the Korea Institute of Electronic Communication Sciences, vol. 12, no. 5, Oct. 2017, pp. 923-932. https://doi.org/10.13067/JKIECS.2017.12.5.923
  4. Y. Schechner, S. Narasimhan, and S. Nayer, "Instant Dehazing of Images Using Polarization," In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Kauai, USA, Dec. 2001, pp. 325-332.
  5. S. Shwartz, E. Namer, and Y. Schechner, "Blind Haze Separation," In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), New York, USA, June 2006, pp. 1984-1991.
  6. S. Narasimhan and S. Nayer, "Contrast Restoration of Weather Degraded Images," IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 6, June 2003, pp. 713-724. https://doi.org/10.1109/TPAMI.2003.1201821
  7. S. Nayer and S. Narasimhan, "Vision in Bad Weather," In Proc. IEEE Int. Conf. on Computer Vision (ICCV), Kerkyra, Greece, Sept. 1999, pp. 820-827.
  8. J. Kopf, B. Neubert, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uyttendaele, and D. Lischinski, "Deep Photo: Model-Based Photograph Enhancement and Viewing," ACM Trans. Graphics, vol. 27, no. 5, Dec. 2008, pp. 116:1-116:10.
  9. R. Tan, "Visibility in Bad Weather from a Single Image," In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Anchorage, USA, June 2008, pp. 1-8.
  10. R. Fattal, "Single Image Dehazing," ACM Trans. Graphics, vol. 27, no. 3, Aug. 2008, pp. 1-9. https://doi.org/10.1145/1360612.1360671
  11. J. Tarel and N. Hautiere, "Fast Visibility Restoration from a Single Color or Gray Level Images," In Proc. IEEE Int. Conf. on Computer Vision (ICCV), Kyoto, Japan, Sept. 2009, pp. 2201-2208.
  12. K. He, J. Sun, and X. Tang, "Single Image Haze Removal Using Dark Channel Prior," IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 12, Dec. 2011, pp. 2341-2353. https://doi.org/10.1109/TPAMI.2010.168
  13. J. Kim, "Histogram Modification based on Additive Term and Gamma Correction for Image Contrast Enhancement," J. of the Korea Institute of Electronic Communication Sciences, vol. 13, no. 5, Oct. 2018, pp. 1117-1124. https://doi.org/10.13067/JKIECS.2018.13.5.1117
  14. J. Kim, "Single Image Haze Removal Algorithm using Dual DCP and Adaptive Brightness Correction," J. of the Korea Academia-Industrial cooperation Society, vol. 19, no. 11, Nov. 2018, pp. 31-37. https://doi.org/10.5762/KAIS.2018.19.10.31
  15. Z. Mi, H. Zhou, Y. Zheng, and M. Wang, "Single Image Dehazing via Multi-scale Gradient Domain Contrast Enhancement," IET Image Process., vol. 10, no. 3, Mar. 2016, pp. 206-214. https://doi.org/10.1049/iet-ipr.2015.0112
  16. A. Levin, D. Lischinski, and Y. Weiss, "A Closed Form Solution to Natural Image Matting," IEEE Trans. Pattern Anal. Mach. Intell., vol. 30, no. 2, Feb. 2008, pp. 228-242. https://doi.org/10.1109/TPAMI.2007.1177
  17. C. Tomasi and R. Manduchi, "Bilateral Filtering for Gray and Color Images," In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Bombay, India, Jan. 1998, pp. 839-846.