Title :
Fast image dehazing using guided filter
Author :
Qiang Zhang; Xiaorun Li
Author_Institution :
College of Electrical Engineering, Zhejiang University, Hangzhou, 310027, China
Abstract :
Images acquired in bad weather, such as haze and fog, are seriously degraded by the scatting of the atmosphere. In this paper, a novel fast image dehazing method using guided filter is proposed. Before guided filter processing, the rough transmission map and the guidance image employ nearest neighbor interpolation down-sampling, to zoom out on the input images of guided filter and reduce the processing of guided filter time complexity. After guided filter processing, the guided filter output image employs bilinear interpolation up-sampling, to zoom in on the output image of guided filter and get the refining transmission map. Results demonstrate that the proposed method achieves good dehazing effect as well as speeds up the dehazing processing. With the improvements, the proposed method may be applied in video surveillance, intelligent transportation system and remote sensing.
Keywords :
"Artificial intelligence","Interpolation","Image edge detection","Pattern recognition"
Conference_Titel :
Communication Technology (ICCT), 2015 IEEE 16th International Conference on
Print_ISBN :
978-1-4673-7004-2
DOI :
10.1109/ICCT.2015.7399820