DOI QR코드

DOI QR Code

Effective machine learning-based haze removal technique using haze-related features

안개관련 특징을 이용한 효과적인 머신러닝 기반 안개제거 기법

  • Lee, Ju-Hee (Dept. of Electronic Engineering, Dong-A University) ;
  • Kang, Bong-Soon (Dept. of Electronic Engineering, Dong-A University)
  • Received : 2021.02.22
  • Accepted : 2021.03.23
  • Published : 2021.03.31

Abstract

In harsh environments such as fog or fine dust, the cameras' detection ability for object recognition may significantly decrease. In order to accurately obtain important information even in bad weather, fog removal algorithms are necessarily required. Research has been conducted in various ways, such as computer vision/data-based fog removal technology. In those techniques, estimating the amount of fog through the input image's depth information is an important procedure. In this paper, a linear model is presented under the assumption that the image dark channel dictionary, saturation ∗ value, and sharpness characteristics are linearly related to depth information. The proposed method of haze removal through a linear model shows the superiority of algorithm performance in quantitative numerical evaluation.

자율주행 및 인공지능 CCTV는 안개와 같은 악조건 상황에서 주변의 사물과 사람인식에 대한 카메라의 가시성 및 검출 능력이 저하된다. 이러한 악조건 상황에서도 중요한 정보를 정확하게 얻기 위해서 안개 제거 알고리즘에 대한 연구가 필요하다. 과거부터 현재까지 안개 제거 기술은 컴퓨터 비전/ 데이터 기반 등 다양한 방법을 이용한 연구가 진행되고 있다. 안개 제거 기술 중에서 입력영상에 대한 깊이 정보를 통한 안개 전달량을 추정하는 방법이 중요하다. 본 논문에서는 영상의 특징 DCP, saturation∗value, sharpness가 깊이정보와 선형관계에 있다는 가정을 통해 선형모델을 제시한다. 제안한 선형모델을 통한 안개제거방법은 기존의 방법들과 정량적 수치평가에서 평균적으로 10% 향상된 결과를 보여주며 알고리즘의 성능의 우수성을 증명하였다.

Keywords

References

  1. 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, pp.2341-2353, 2011. DOI: 10.1109/TPAMI.2010.168
  2. D. Ngo, G. D. Lee, and B. S. Kang, "Improved color attenuation prior for single-image haze removal," Appl. Sci., vol.9, no.19, pp.4011, 2019. DOI: 10.3390/app9194011
  3. P. Xia and X. Liu, "Image dehazing technique based on polarimetric spectral analysis," Optik, vol.127, no.18, pp.7350-7358, 2016. DOI: 10.1016/j.ijleo.2016.05.071
  4. Ngo, D.; Lee, S.; Kang, B. "Robust Single-Image Haze Removal Using Optimal Transmission Map and Adaptive Atmospheric Light," Remote Sens. Vol.12, pp.2233. 2020. https://doi.org/10.3390/rs12142233
  5. Ngo, D.; Lee, S.; Nguyen, Q.-H.; Ngo, T. M.; Lee, G.-D.; Kang, B. "Single Image Haze Removal from Image Enhancement Perspective for Real-Time Vision-Based Systems," Sensors, Vol.20, pp.5170, 2020. https://doi.org/10.3390/s20185170
  6. J. P. Tarel and N. Hautiere, "Fast visivility restoration from a single color or gray level image," in Proc. of the 2009 IEEE International Conference on Computer Vision, pp.2201-2208, 2009. DOI: 10.1109/ICCV.2009.5459251
  7. G. Kim, S. Lee, and B. Kang, "Single Image Haze Removal Using Hazy Particle Maps," IEICE Trans. Fundam. Electron. Commun. Comput.Sci., vol.101, no.11, pp.1999-2002, 2018. DOI: 10.1587/transfun.E101.A.1999
  8. Q. Zhu, J. Mai, and L. Shao, "A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior," IEEE Trans. Image Process., vol.24, no.11, pp.3522-3533, 2015. DOI: 10.1109/TIP.2015.2446191
  9. Y. Jiang, C. Sun, Y. Zhao and L. Yang, "Fog Density Estimation and Image Defogging Based on Surrogate Modeling for Optical Depth," in IEEE Transactions on Image Processing, vol.26, no.7, pp.3397-3409, 2017. DOI: 10.1109/TIP.2017.2700720.
  10. D. Ngo, G. D. Lee, and B. S. Kang, "Improved color attenuation prior for single-image haze removal," Appl. Sci., vol.9, no.19, pp.4011, 2019. DOI: 10.3390/app9194011