DOI QR코드

DOI QR Code

Low-light Image Enhancement Based on Frame Difference and Tone Mapping

프레임 차와 톤 매핑을 이용한 저조도 영상 향상

  • Jeong, Yunju (School of Computer Science & Eng., Graduate School, Kyungpook National University) ;
  • Lee, Yeonghak (Dept. of Computer Eng. Andong National University) ;
  • Shim, Jaechang (Dept. of Computer Eng. Andong National University) ;
  • Jung, Soon Ki (School of Computer Science & Eng., Graduate School, Kyungpook National University)
  • Received : 2018.01.25
  • Accepted : 2018.07.11
  • Published : 2018.09.30

Abstract

In this paper, we propose a new method to improve low light image. In order to improve the image quality of a night image with a moving object as much as the quality of a daytime image, the following tasks were performed. Firstly, we reduce the noisy of the input night image and improve the night image by the tone mapping method. Secondly, we segment the input night image into a foreground with motion and a background without motion. The motion is detected using both the difference between the current frame and the previous frame and the difference between the current frame and the night background image. The background region of the night image takes pixels from corresponding positions in the daytime image. The foreground regions of the night image take the pixels from the corresponding positions of the image which is improved by the tone mapping method. Experimental results show that the proposed method can improve the visual quality more clearly than the existing methods.

Keywords

References

  1. W.R. Lee, D.G. Hwang, and B.M. Jun, "Color Restoration of Low Light Level Images Using a Tone Mapping and the Retinex," Journal of Korea Institute on Information Scientists Engineers : Software and Applications, Vol. 40, No. 6, pp. 342-349, 2013.
  2. M. Kaur and S. Singh, "Night Enhancement using Hybrid of Good and Poor Images," International Journal of Computer Technology and Applications, Vol. 3 No. 4, pp. 1613-1618, 2012.
  3. Y. Cai, K. Huang, and T. Tan, "Context Enhancement of Nighttime Surveillance by Image Fusion," Proceeding of the IEEE 8th International Conference on Pattern Recognition, pp. 980-983, 2006.
  4. J.S. Oh, "Fast MOG Algorithm Using Object Prediction," Journal of the Korea Institute of Information and Communication Engineering, Vol. 18, No. 11, pp. 2721-2726, 2014. https://doi.org/10.6109/jkiice.2014.18.11.2721
  5. H.T. Kim and J.S. Park, "Fire Detection in Outdoor Using Characteristics of Smoke," The Journal of the Korea Institute of Electronic Communication Sciences, Vol. 9, No. 2, pp. 149-154, 2014. https://doi.org/10.13067/JKIECS.2014.9.2.149
  6. A. Yamasaki, H. Takauji, and S. Kaneko, "Denighting: Enhancement of Nighttime Images for a Surveillance Camera," Proceeding of 19th International Conference on Pattern Recognition, pp. 1-4, 2008.
  7. J.H. Han, The Bilateral Filter Performance Analysis of Noise and Signal by Modeling Gaussian Probability Density Function, Master's Thesis, Department of Electric Engineering, Ewha Womans University, 2011.
  8. S.Y. Lee, H.G. Ha, K.W. Song, and Y.H. Ha, "Gamma Correction for Local Brightness and Detail Enhancement of HDR Image," Journal of Korea Multimedia Society, Vol. 19, No. 5, pp. 837-847, 2016. https://doi.org/10.9717/kmms.2016.19.5.837
  9. E.P. Bennett and L. McMillan, "Video Enhancement Using Per-Pixel Virtual Exposures," Proceeding of ACM Special Interest Group on Graphics and Interactive Techniques, Vol. 24, No. 3, pp. 845-852, 2005.