Recent years, China has launched a series of remote sensing satellites, such as HJ-1, FY3, GF-1, etc. Making the extreme rapid growth of high resolution remote sensing images. In this case, preliminary data processing is becoming more and more important, dehazing is an important step of radiometric processing in prfeliminary data processing. However, the existing dehazing methods are quite slow. In this paper, we are going to discuss a faster dehazing algorithm based on large-scale median filtering, by using the multi-resolution remote sensing image data of GF-1 satellite, we can highly optimize the algorithm itself..Parallel computing techniques are used to improve the processing speed, and the proposed algorithm is implemented in standard C++. On the computer with Intel core i7-3770 and CPU 3.4 GHz, our algorithm can decrease the dehazing time from one hour to less than five minutes for a 4-band, 10000×10000 pixel size, 16 bits unsigned integer data type image.
[1]
Jian Sun,et al.
Guided Image Filtering
,
2010,
ECCV.
[2]
Paul A. Viola,et al.
Rapid object detection using a boosted cascade of simple features
,
2001,
Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.
[3]
Ping Tang,et al.
Rapid dehazing algorithm based on large-scale median filtering for high-resolution visible near-infrared remote sensing images
,
2014,
Int. J. Wavelets Multiresolution Inf. Process..
[4]
Jean-Philippe Tarel,et al.
Fast visibility restoration from a single color or gray level image
,
2009,
2009 IEEE 12th International Conference on Computer Vision.