- Volume 52 Issue 11
DOI QR Code
Image Dehazing Algorithm Using Near-infrared Image Characteristics
근적외선 영상의 특성을 활용한 안개 제거 알고리즘
- Yu, Jae Taeg (Agency for Defense Development) ;
- Ra, Sung Woong (Division of Electrical Engineering and Information & Communication Engineering, Chungnam National University) ;
- Lee, Sungmin (Division of Electronics and Electrical Engineering, Dongguk University) ;
- Jung, Seung-Won (Department of Multimedia Engineering, Dongguk University)
- Received : 2015.10.06
- Accepted : 2015.11.06
- Published : 2015.11.25
The infrared light is known to be less dependent on background light compared to the visible light, and thus many applications such as remote sensing and image surveillance use the infrared image. Similar to color images, infrared images can also be degraded by hazy weather condition, and consequently the performance of the infrared image-based applications can decrease. Nevertheless, infrared image dehazing has not received significant interest. In this paper, we analyze the characteristic of infrared images, especially near-infrared (NIR) images, and present an NIR dehazing algorithm using the analyzed characteristics. In particular, a machine learning framework is adopted to obtain an accurate transmission map and several post-processing methods are used for further refinement. Experimental results show that the proposed NIR dehazing algorithm outperforms the conventional color image dehazing method for NIR image dehazing.
적외선 영상은 외광의 밝기에 영향을 적게 받아서 원격 탐사 및 영상 보안 등의 응용에서 활발하게 활용되고 있다. 그러나 안개와 같은 기상 악화상황으로 인하여 해당 적외선 영상의 화질이 크게 저하되는 경우가 빈번하게 발생한다. 칼라 영상의 안개제거 기술이 다양하게 연구되어온 반면 적외선 영상의 안개제거 기술은 상대적으로 관심을 받지 못하고 있다. 본 논문에서는 근적외선 대역 영상에 대하여 적외선 영상의 통계학적 특징을 이용한 안개 제거 알고리즘을 제안한다. 기계학습 기법을 활용하여 전달량을 보정하고 다중 후처리 기법을 적용하여 정확한 전달량을 구하였다. 제안 기술을 이용하여 복원한 적외선 영상이 기존 칼라영상에 기반한 알고리즘을 적외선 영상에 적용하여 얻은 결과보다 화질이 좋다는 것을 확인하였다.
Grant : 인터랙티브 스마트 콘텐츠 고급인력양성 사업팀
- S. K. Kim, K. H. Choi and S. Y. Park, "A framework for object detection by haze removal," Journal of The Institute of Electronics and Information Engineers, 51, 5, 168-176, May 2014. https://doi.org/10.5573/ieie.2014.51.5.168
- E. H. Han, J. W. An, S. I. Hahn and H. T. Cha, "A study of improving fog image quality," in Proc. of The Institute of Electronics and Information Engineers Conference, 647-650, JeJu, Korea, 2011.
- W. T. Kim and T. H. Kim, "High-speed and high-quality haze removal method using dual dark channels" in Proc. of The Institute of Electronics and Information Engineers Conference, 655-658, JeJu, Korea, 2015.
- Z. Li, and J. Zheng, W. Yao, and Z. Zhu, "Single image haze removal via a simplified dark channel," in Proc. of IEEE Conf. on Acoustics, Speech and Signal Processing, pp. 1608-1612, April 2015.
- 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, June 2003. https://doi.org/10.1109/TPAMI.2003.1201821
- S. K. Nayar and S. G. Narasimhan, "Vision in bad weather," in Proc. of IEEE Conf. on Computer Vision, pp. 820-827, Kerkyra, Greece, September 1999.
- K. He, J. Sun and X. Tang, "Single image haze removal using dark channel prior, " in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1956-1963, Miami, USA, June 2009.
- 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, June 2008.
- L. Schaul, C. Fredembach, and S. Susstrunk, "Color image dehazing using the near-infrared," in Proc. of IEEE Conf. on Image Processing, pp. 1609-1612, Cairo, Egypt, November 2009.
- K. He, J. Sun and X. Tang, "Guided Image Filtering," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 35, no.6 pp. 1397-1409, 2013. https://doi.org/10.1109/TPAMI.2012.213
- X. Pan, F Xie and J. Yin, "Haze removal for a single remote sensing," IEEE Signal Processing Letters, Vol. 22, no.10, pp.1806-1810. 2015. https://doi.org/10.1109/LSP.2015.2432466
- T. H. Kil, S. H. Lee and N. I. Cho, "Single image dehazing based on reliability map of dark channel prior," in Proc. of IEEE International Conf. on Image Processing, pp. 882-885, Melbourne, Australia, September 2013.