Journal of Platform Technology

  • 제11권6호
  • /
  • Pages.68-78
  • /
  • 2023
  • /
  • 2289-0181(pISSN)
  • /
  • 2289-019X(eISSN)
ICT플랫폼학회 (ICT Platform Society)
권호 표지

안개가 포함된 영상에서의 색 왜곡 특성 분석

Analysis of Color Distortion in Hazy Images

  • 김정엽 (영산대학교 성심교양대학)
  • 투고 : 2023.10.19
  • 심사 : 2023.12.08
  • 발행 : 2023.12.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구에서는 안개(haze)가 존재하는 영상에서의 색상 왜곡에 대하여 분석하고자 한다. 장면에 안개가 포함되는 경우, 장면에서 반사되는 칼라 신호는 안개 성분에 따른 투과율의 영향으로 색상의 왜곡이 수반된다. 통상적인 안개 제거(de-hazing) 방법으로 안개의 영향을 배제하는 경우 색상의 왜곡이 충분히 해소되지 않는 경향이 있다. Khoury 등은 많은 연구에서 언급되는 안개 모델인 다크-채널-프라이어(dark channel prior) 기법을 이용하여 색상의 왜곡 정도를 파악하였다. 그러나 색 오차 값 등 왜곡의 경향성 만을 확인하였고, 구체적인 색 왜곡에 대한 분석을 하지 않았다. 본 논문에서는 색 왜곡의 형태를 분석하고, 색상의 왜곡을 줄일 수 있는 복원 방법을 제안하였다. Khoury 등이 사용한 데이터베이스의 입력 영상에는 표준 칼라 도구인 맥베스 칼라체커(Macbeth color checker)가 포함되어 있다. 맥베스 칼라체커(Macbeth color checker)의 칼라 값들을 이용하여 안개 농도의 변화에 따른 색상 왜곡을 분석하고, 모델링을 통하여 새로운 색상 왜곡 모델을 제시하였다. 제안한 방법은 안개 농도 변화에 따른 단계별 색도(chromaticity)의 변화와 기준 정보(ground truth)의 색도를 이용하여 사상(mapping) 함수를 구하는 것이다. 색 왜곡의 형태가 안개 농도에 비례하여 단계별로 차이가 있으므로 모든 단계에서 안정적으로 작동하는 통합적인 사상 함수를 구하는 것이 필요하다. 본 논문에서는 제안한 방법을 통한 색상 왜곡의 개선을 각도 오차(angular error)의 값을 기준으로 추정하였으며, 기존 방법에 비하여 15% 정도의 개선효과가 있음을 검증하였다.

In this paper, the color distortion in images with haze would be analyzed. When haze is included in the scene, the color signal reflected in the scene is accompanied by color distortion due to the influence of transmittance according to the haze component. When the influence of haze is excluded by a conventional de-hazing method, the distortion of color tends to not be sufficiently resolved. Khoury et al. used the dark channel priority technique, a haze model mentioned in many studies, to determine the degree of color distortion. However, only the tendency of distortion such as color error values was confirmed, and specific color distortion analysis was not performed. This paper analyzes the characteristic of color distortion and proposes a restoration method that can reduce color distortion. Input images of databases used by Khoury et al. include Macbeth color checker, a standard color tool. Using Macbeth color checker's color values, color distortion according to changes in haze concentration was analyzed, and a new color distortion model was proposed through modeling. The proposed method is to obtain a mapping function using the change in chromaticity by step according to the change in haze concentration and the color of the ground truth. Since the form of color distortion varies from step to step in proportion to the haze concentration, it is necessary to obtain an integrated thought function that operates stably at all stages. In this paper, the improvement of color distortion through the proposed method was estimated based on the value of angular error, and it was verified that there was an improvement effect of about 15% compared to the conventional method.

키워드

참고문헌

  1. K. He, J. Sun, and X. Tang, "Single Image Haze removal Using Dark Channel Prior," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, No. 12, pp. 2341-2353, 2011. https://doi.org/10.1109/TPAMI.2010.168
  2. G. Meng, Y. Wang, J. Duan, S. Xiang, and C. Pan, "Efficient Image Dehazing with Doundary Constraint and Contextual Regularization," Proceeding of IEEE International Conference on Computer Vision, pp. 617-624, 2013.
  3. D. Park, H. Park, D. Han, and H. Ko, "Single Image Dehazing with Image Entropy and Information Fidelity," Proceeding of IEEE International Conference on Image Processing, pp. 4037-4041, 2014.
  4. S. Gautam, T.K. Gandhi, and B.K. Panigrahi, "An Improved Air-light Estimation Scheme for Single Haze Images Using Color Constancy Prior," IEEE Signal Processing Letters, Vol. 27, pp. 1695-1699, 2020. https://doi.org/10.1109/LSP.2020.3025462
  5. R. Fattal, "Dehazing Using Color-lines," ACM Transactions on Graphics, Vol. 34, No. 1, pp.1-14, 2014. https://doi.org/10.1145/2651362
  6. M. Sulami, I. Geltzer, R. Fattal, and M. Werman, "Automatic Recovery of the Atmospheric Light in Hazy Images," Proceeding of IEEE International Conference on Computational Photography, pp. 1-11, 2014.
  7. Y. Bahat and M. Irani, "Blind Dehazing Using Internal Patch Recurrence," Proceeding of IEEE Conference on Computational Photography, pp. 1-9, 2016.
  8. D. Berman, T. Treibitz, and S. Avidan, "Single Image Dehazing Using Haze-Lines," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42, No. 3, pp. 720-734, 2020. https://doi.org/10.1109/TPAMI.2018.2882478
  9. C. W. Kim, "Airlight Estimation of a Single Hazy Image Using Patch-wise Bright Pixels (PBP)," Journal of Korea Multimedia Society Vol. 26, No. 2, pp.140-147, 2023 https://doi.org/10.9717/kmms.2023.26.2.140
  10. B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao, "DehazeNet: An End-to-end System for Single Image Haze Removal," IEEE Transactions on Image Processing, Vol. 25, No. 11, pp. 5187- 5198, 2016. https://doi.org/10.1109/TIP.2016.2598681
  11. H. Zhang and V.M. Patel, "Densely Connected Pyramid Dehazing Network," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3194-3203, 2018.
  12. Y. Wang, L.P. Chau, and X. Ma, "Airlight Estimation Based on Distant Region Segmentation," Proceedings of IEEE International Symposium on Circuits and Systems, pp. 1-5, 2019.
  13. J. E. Khoury, J. Thomas, A. Mansouri, "Colorimetric screening of the haze model limits," Procedings of International Conference on Image and Signal Processing : Image and Signal Processing, pp.481-489, 2018.
  14. J. Kim, N. Kim, "Adversarial Learning-Based Image Correction Methodology for Deep Learning Analysis of Heterogeneous Images," KIPS Trans. Software and Data Engineering, Vol.10, No.11, pp.457-464, 2021. https://doi.org/10.3745/KTSDE.2021.10.11.457