Abstract. The
quality of images of objects in the open area depends on the state of the
atmosphere (the presence of atmospheric formations, mainly hydrometeors). The
purpose of this work is to increase the degree of discernibility of objects in
the image, distorted by the presence of hydrometeors. The goal is achieved by a
method based on the Dark Channel Prior method. An important difference of the
method used is the refusal of the independence of the brightness of the
atmosphere from the position of the pixel. In addition, the estimation of the
atmospheric absorption coefficient is made on the basis of the statistical
brightness properties in the sprite with the center in the considered pixel. In
this paper, we consider the increase in contrast by converting the dynamic
range of image brightness based on an estimate of the atmospheric absorption
coefficient. To avoid the rapid growth of artifacts caused by the discreteness
of pixel brightness, a restriction on increasing the brightness range is
introduced. It is proposed to change the brightness normalization according to
the presented algorithm, which leads to a sharp increase in the degree of
distinguishability of objects in the image distorted by the action of
hydrometeors. In order to speed up image processing, bilinear interpolation is
used.
Key words: hydrometeors, digital images, dynamic range, enhancement of contrast, improvement
of distinguishability of objects.
References
1.
Mickhayluck Y. P., Nacharov D. V. The method of objects distinctiveness
improvement on images recorded in poor visibility conditions. Zhurnal
Radioelektroniki - Journal of Radio Electronics, 2015, No. 6, Available at:
http://jre.cplire.ru/jre/jun15/4/text.html . (In Russian)
2.
Manpreet K. S., Satbir S. A Review on Various Haze Removal Techniques for Image
Processing. International Journal of Current Engineering and Technology,
Vol.5, No.3 (June 2015). pp.1500-1505.
3.
V.Vembuselvi, T.Murugan. An Efficient Technique for Illumination Adjustment
Using CLAHE Algorithm. International Journal of Innovative Research in
Computer and Communication Engineering, Vol. 4, Issue 3, March 2016. pp.
4001-4006.
4.
Kanika Kapoor, Shaveta Arora. Colour image enhancement based on histogram
equalization. Electrical & Computer Engineering: An International
Journal (ECIJ). Vol.4, No.3, September 2015. pp. 73-82.
5.
Halmaoui H., Cord A., Hautière N. Contrast restoration of road images
taken in foggy weather. 2011 IEEE International Conference on Computer Vision
Workshops. 2011. pp. 2057—2063.
6.
Tripathi A.K., Mukhopadhyay S. Removal of fog from images: A review. IETE
Technical Review. 2012. Vol.29, No.2. pp.148—156.
7.
Kaiming He, Jian Sun, Xiaoou Tang, Single Image Haze Removal Using Dark Channel
Prior. IEEE Transaction on pattern analysis and machine intelligence, Vol.33,
No.12, December 2011, pp. 2341-2353.
8.
Kaiming He, Jian Sun, Xiaoou Tang, Final Project: Dark Channel Prior Haze
Removal, URL:
http://students.cec.wustl.edu/~jwaldron/559/project_final , 05.08.2012.
9.
Kokoshkin A. V., Korotkov V. A., Korotkov K. V., Novichihin E.P. Methods of
improving of objects distinguishability in the presence of hydrometeors. Zhurnal Radioelektroniki - Journal of Radio Electronics, 2015, No. 10, Available
at:
http://jre.cplire.ru/jre/jun15/10/text.html . (In Russian)