融合双尺度暗通道的单图像去雾方法
|
摘要
针对使用单一尺度滤波窗口计算暗通道的去雾方法会使去雾图像产生光晕的问题,提出融合双尺度暗通道的单图像去雾方法。该方法使用大、小两种尺度滤波窗口,分别计算两个暗通道及其最大值滤波结果,并实现了大尺度暗通道与两个最大值滤波结果的融合,以融合后的暗通道计算透射率,并进行幂函数调整和向导滤波,最后以优化后的透射率实现图像去雾。实验结果表明,该方法能很好地消除景深边缘的光晕及天空区域的彩色斑块,恢复后的图像有理想的亮度和对比度,且算法实现简单。
In allusion to the problem that the image dehazing method using the single-scale filtering window to calculate dark channels makes dehazed images produce halos,a single image dehazing method based on the fusion of double-scale dark channels is proposed. In the method,two dark channels and their maximum value filtering results are calculated respectively by using two filtering windows with different scales. The fusion of the big-scale dark channel with two maximum value filtering re-sults is realized. The transmittance is calculated by using the fused dark channel. The power function adjustment and guided fil-tering are performed. The image dehazing is realized by using the optimized transmittance. The experimental results show that the method can well eliminate the halos on depth-edge and the color patches in the sky scope,the recovered image has an ideal brightness and contrast,and the algorithm is simple to be implemented.
In allusion to the problem that the image dehazing method using the single-scale filtering window to calculate dark channels makes dehazed images produce halos,a single image dehazing method based on the fusion of double-scale dark channels is proposed. In the method,two dark channels and their maximum value filtering results are calculated respectively by using two filtering windows with different scales. The fusion of the big-scale dark channel with two maximum value filtering re-sults is realized. The transmittance is calculated by using the fused dark channel. The power function adjustment and guided fil-tering are performed. The image dehazing is realized by using the optimized transmittance. The experimental results show that the method can well eliminate the halos on depth-edge and the color patches in the sky scope,the recovered image has an ideal brightness and contrast,and the algorithm is simple to be implemented.
引文
[1]NARASIMHAN S G,NAYAR S K.Chromatic framework for vision in bad weather[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Hilton Head Island:IEEE,2000:598-605.
[2]NARASIMHAN S G,NAYAR S K.Contrast restoration of weather degraded images[J].IEEE transactions on pattern analysis and machine intelligence,2003,25(6):713-724.
[3]HE K M,SUN J,TANG X O.Single image haze removal using dark channel prior[J].IEEE transactions on pattern analysis&machine intelligence,2011,33(12):2341-2353.
[4]HE K M,SUN J,TANG X O.Guided image filtering[J].IEEEtransactions on pattern analysis&machine intelligence,2013,35(6):1397-1409.
[5]KOU F,LI Z G,WEN C Y,et al.Multi-scale exposure fusion via gradient domain guided image filtering[C]//Proceedings of IEEE International Conference on Multimedia and Expo.Hong Kong:IEEE,2017:1105-1110.161
[6]ZHAN Y L,GU Y Z,HUANG K,et al.Accurate image-guided stereo matching with efficient matching cost and disparity refinement[J].IEEE transactions on circuits and systems for video technology,2016,26(9):1632-1645.
[7]FENG Z,HAO S J.Low-light image enhancement by refining illumination map with self-guided filtering[C]//Proceedings of IEEE International Conference on Big Knowledge.Hefei:IEEE,2017:183-187.
[8]HSIEH C H,CHEN C Y,DAI Y J.Single image dehazing based on pixel minimum channel[C]//Proceedings of IEEESymposium Series on Computational Intelligence.Athens:IEEE,2016:1-5.
[9]王卫星,肖翔,陈良琴.结合最小滤波和引导滤波的暗原色去雾[J].光学精密工程,2015,23(7):2100-2108.WANG Weixing,XIAO Xiang,CHEN Liangqin.Image dark channel prior haze removal based on minimum filtering and guided filtering[J].Optics and precision engineering,2015,23(7):2100-2108.
[10]ZHANG T,YU Y K,SUN Z M,et al.Robust image dehazing using a guided filter[C]//Proceedings of 12th International Conference on Fuzzy Systems and Knowledge Discovery.Zhangjiajie:IEEE,2015:1971-1975.
[11]韩正汀,路文,杨舒羽,等.基于导向滤波优化的自然图像去雾新方法[J].计算机科学与探索,2015,9(10):1256-1262.HAN Zhengting,LU Wen,YANG Shuyu,et al.Improved natural image dehazing algorithm based on guided filtering[J].Journal of frontiers of computer science and technology,2015,9(10):1256-1262.
[12]ZHANG X Y,SHI M P,TAO W,et al.Refined transmission map using guided filter[C]//Proceedings of IEEE International Conference on Communication Problem-Solving.Guilin:IEEE,2015:157-160.
[13]LI Z G,ZHENG J H,ZHU Z J,et al.Weighted guided image filtering[J].IEEE transactions on image processing,2015,24(1):120-129.
[2]NARASIMHAN S G,NAYAR S K.Contrast restoration of weather degraded images[J].IEEE transactions on pattern analysis and machine intelligence,2003,25(6):713-724.
[3]HE K M,SUN J,TANG X O.Single image haze removal using dark channel prior[J].IEEE transactions on pattern analysis&machine intelligence,2011,33(12):2341-2353.
[4]HE K M,SUN J,TANG X O.Guided image filtering[J].IEEEtransactions on pattern analysis&machine intelligence,2013,35(6):1397-1409.
[5]KOU F,LI Z G,WEN C Y,et al.Multi-scale exposure fusion via gradient domain guided image filtering[C]//Proceedings of IEEE International Conference on Multimedia and Expo.Hong Kong:IEEE,2017:1105-1110.161
[6]ZHAN Y L,GU Y Z,HUANG K,et al.Accurate image-guided stereo matching with efficient matching cost and disparity refinement[J].IEEE transactions on circuits and systems for video technology,2016,26(9):1632-1645.
[7]FENG Z,HAO S J.Low-light image enhancement by refining illumination map with self-guided filtering[C]//Proceedings of IEEE International Conference on Big Knowledge.Hefei:IEEE,2017:183-187.
[8]HSIEH C H,CHEN C Y,DAI Y J.Single image dehazing based on pixel minimum channel[C]//Proceedings of IEEESymposium Series on Computational Intelligence.Athens:IEEE,2016:1-5.
[9]王卫星,肖翔,陈良琴.结合最小滤波和引导滤波的暗原色去雾[J].光学精密工程,2015,23(7):2100-2108.WANG Weixing,XIAO Xiang,CHEN Liangqin.Image dark channel prior haze removal based on minimum filtering and guided filtering[J].Optics and precision engineering,2015,23(7):2100-2108.
[10]ZHANG T,YU Y K,SUN Z M,et al.Robust image dehazing using a guided filter[C]//Proceedings of 12th International Conference on Fuzzy Systems and Knowledge Discovery.Zhangjiajie:IEEE,2015:1971-1975.
[11]韩正汀,路文,杨舒羽,等.基于导向滤波优化的自然图像去雾新方法[J].计算机科学与探索,2015,9(10):1256-1262.HAN Zhengting,LU Wen,YANG Shuyu,et al.Improved natural image dehazing algorithm based on guided filtering[J].Journal of frontiers of computer science and technology,2015,9(10):1256-1262.
[12]ZHANG X Y,SHI M P,TAO W,et al.Refined transmission map using guided filter[C]//Proceedings of IEEE International Conference on Communication Problem-Solving.Guilin:IEEE,2015:157-160.
[13]LI Z G,ZHENG J H,ZHU Z J,et al.Weighted guided image filtering[J].IEEE transactions on image processing,2015,24(1):120-129.