DocumentCode :
594734
Title :
Single image dehazing with optimal transmission map
Author :
Yi-Shuan Lai ; Yi-Lei Chen ; Chiou-Ting Hsu
Author_Institution :
Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
fYear :
2012
fDate :
11-15 Nov. 2012
Firstpage :
388
Lastpage :
391
Abstract :
The challenge of single image dehazing mainly comes from the double uncertainty of scene depth and scene radiance. Approximation of the transmission, which encodes the scene depth information, is the most significant step to solve the dehazing problem. In this paper, we propose to derive an optimal transmission map under a heuristic assumption in the dehazing model. The proposed objective function guarantees to have a global optimal solution, and the obtained transmission map accurately preserves the depth-consistency of the same object. Using the optimal transmission map, our method recovers haze-free images with excellent performance.
Keywords :
image processing; depth consistency; double uncertainty; global optimal solution; heuristic assumption; objective function; optimal transmission map; scene depth information; scene radiance; single image dehazing; transmission approximation; Atmospheric modeling; Computer vision; Image color analysis; Image restoration; Linear programming; Pattern recognition; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
ISSN :
1051-4651
Print_ISBN :
978-1-4673-2216-4
Type :
conf
Filename :
6460153
Link To Document :
بازگشت