
浏览全部资源
扫码关注微信
1.南京信息工程大学 电子与信息工程学院,江苏 南京 210044
2.江苏省气象探测与信息处理重点实验室,江苏 南京 210044
[ "乔丹(1995-),女,山东菏泽人,硕士研究生,2019年于滨州学院获得学士学位,主要研究方向为图像处理。 E-mail:dandan5015@126.com" ]
[ "张闯(1976-),女,江苏南京人,副教授,2008于南京理工大学获得博士学位,主要研究方向为光信息采集传感器与图像信息处理。 E-mail:957978664@qq.com" ]
收稿日期:2000-12-22,
修回日期:2021-02-24,
移动端阅览
乔丹, 张闯, 朱晨雨. 基于多尺度融合卷积神经网络的图像去雾算法[J/OL]. 液晶与显示, 2022,1-10.
QIAO DAN, ZHANG CHUANG, ZHU CHEN-YU. Image dehazing algorithm based on multi-scale concat convolutional neural network[J/OL]. Chinese journal of liquid crystals and displays, 2022, 1-10.
乔丹, 张闯, 朱晨雨. 基于多尺度融合卷积神经网络的图像去雾算法[J/OL]. 液晶与显示, 2022,1-10. DOI: 10.37188/CJLCD.4-yjyxs2020-0347.
QIAO DAN, ZHANG CHUANG, ZHU CHEN-YU. Image dehazing algorithm based on multi-scale concat convolutional neural network[J/OL]. Chinese journal of liquid crystals and displays, 2022, 1-10. DOI: 10.37188/CJLCD.4-yjyxs2020-0347.
为解决图像去雾后颜色偏暗以及去雾不彻底等问题,本文提出了一种基于多尺度融合卷积神经网络的图像去雾算法。以有雾图像为输入,首先经过预处理模块由单尺度卷积层提取有雾图像浅层信息,然后设计多尺度映射模块实现深度特征学习以及深、浅层特征融合,由反卷积模块还原图像尺寸,通过卷积操作得到有雾图像对应的粗透射率图。采用双边滤波法优化输出细透射率图,最后依据大气散射模型复原出无雾图像。实验结果表明:本文方法在合成有雾图像和自然有雾图像上均优于其他算法,其中合成有雾图像上的峰值信噪比(PSNR)、结构相似性(SSIM)能分别达到29.238、0.950。本文所提算法可以有效地避免去雾图像颜色偏暗、失真等不足,提高了图像去雾性能并体现出良好的视觉效果。
In order to solve the problem of dark color and incomplete defogging after image defogging, an image defogging algorithm based on multi-scale concat convolutional neural network is proposed in this paper. Taking the foggy image as the input, the shallow layer information of the image is extracted from the single scale convolution layer through the preprocessing module, and then the multi-scale mapping module is designed to realize the depth feature learning and the fusion of the deep and shallow layer features. The deconvolution module is used to restore the image size, and the coarse transmittance map corresponding to the foggy image is obtained through the convolution operation. Finally, the haze free image is restored according to the atmospheric scattering model. The experimental results show that the proposed method is superior to other algorithms in both synthetic and natural foggy images, and the peak signal-to-noise ratio (PSNR) and structure similarity (SSIM) can reach 29.238 and 0.9502 respectively. The proposed algorithm can effectively avoid the dark color and distortion of the image, improve the image defogging performance and show good visual effect.
MA R Q , ZHANG S J . An improved color image defogging algorithm using dark channel model and enhancing saturation [J]. Optik , 2019 , 180 : 997 - 1000 . doi: 10.1016/j.ijleo.2018.12.020 http://dx.doi.org/10.1016/j.ijleo.2018.12.020
王万国 , 王滨海 , 张晶晶 , 等 . 基于直方图规定化的图像去雾算法 [J]. 计算机技术与发展 , 2014 , 24 ( 9 ): 241 - 244 . doi: 10.1117/12.2179556 http://dx.doi.org/10.1117/12.2179556
WANG W G , WANG B H , ZHANG J J , et al . Image haze removal algorithm based on histogram specification [J]. Computer Technology and Development , 2014 , 24 ( 9 ): 241 - 244 . (in Chinese) . doi: 10.1117/12.2179556 http://dx.doi.org/10.1117/12.2179556
LAND E H , MCCANN J J . Lightness and retinex theory [J]. Journal of the Optical Society of America , 1971 , 61 ( 1 ): 1 - 11 . doi: 10.1364/josa.61.000001 http://dx.doi.org/10.1364/josa.61.000001
肖俊 , 宋寿鹏 , 丁丽娟 . 空域同态滤波算法研究 [J]. 中国图象图形学报 , 2008 , 13 ( 12 ): 2302 - 2306 . doi: 10.11834/jig.20081209 http://dx.doi.org/10.11834/jig.20081209
XIAO J , SONG S P , DING L J . Research on the fast algorithm of spatial homomorphic filtering [J]. Journal of Image and Graphics , 2008 , 13 ( 12 ): 2302 - 2306 . (in Chinese) . doi: 10.11834/jig.20081209 http://dx.doi.org/10.11834/jig.20081209
CANTOR A . Optics of the atmosphere-scattering by molecules and particles [J]. IEEE Journal of Quantum Electronics , 1978 , 14 ( 9 ): 698 - 699 . doi: 10.1109/jqe.1978.1069864 http://dx.doi.org/10.1109/jqe.1978.1069864
TAN R T . Visibility in bad weather from a single image [C]// IEEE Conference on Computer Vision and Pattern Recognition . Anchorage, AK, USA : IEEE , 2008 : 1 - 8 . doi: 10.1109/cvpr.2008.4587643 http://dx.doi.org/10.1109/cvpr.2008.4587643
FATTAL R . Single image dehazing [J]. ACM Transactions on Graphics , 2008 , 27 ( 3 ): 1 - 9 . doi: 10.1145/1360612.1360671 http://dx.doi.org/10.1145/1360612.1360671
HE K M , SUN J , TANG X O . Single image haze removal using darkchannel prior [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2011 , 33 ( 12 ): 2341 - 2353 .
HE K M , SUN J , TANG X O . Guided image filtering [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013 , 35 ( 6 ): 1397 - 1409 . doi: 10.1109/tpami.2012.213 http://dx.doi.org/10.1109/tpami.2012.213
邵明省 . 基于改进暗通道算法的图像去雾研究 [J]. 液晶与显示 , 2019 , 34 ( 7 ): 690 - 697 . doi: 10.3788/yjyxs20193407.0690 http://dx.doi.org/10.3788/yjyxs20193407.0690
SHAO M S . Image dehazing based on improved dark channel algorithm [J]. Chinese Journal of Liquid Crystals and Displays , 2019 , 34 ( 7 ): 690 - 697 . doi: 10.3788/yjyxs20193407.0690 http://dx.doi.org/10.3788/yjyxs20193407.0690
张峥 , 李奇 , 徐之海 , 等 . 结合颜色线和暗通道的遥感图像去雾 [J]. 光学 精密工程 , 2019 , 27 ( 1 ): 181 - 190 . doi: 10.3788/ope.20192701.0181 http://dx.doi.org/10.3788/ope.20192701.0181
ZHANG Z , LI Q , XU Z H , et al . Color-line and dark channel based dehazing for remote sensing images [J]. Optics and Precision Engineering , 2019 , 27 ( 1 ): 181 - 190 . doi: 10.3788/ope.20192701.0181 http://dx.doi.org/10.3788/ope.20192701.0181
MENG G F , WANG Y , DUAN J Y , et al . Efficient image dehazing with boundary constraint and contextual regulation [C]// 2013 IEEE International Conference on Computer Vision . Sydney, NSW, Australia : IEEE , 2013 : 617 - 624 . doi: 10.1109/iccv.2013.82 http://dx.doi.org/10.1109/iccv.2013.82
CAI B L , XU X M , JIA K , et al . DehazeNet: an end-to-end system for single image haze removal [J]. IEEE Transaction on Image Processing , 2016 , 25 ( 11 ): 5187 - 5198 . doi: 10.1109/tip.2016.2598681 http://dx.doi.org/10.1109/tip.2016.2598681
LI B Y , PENG X L , WANG Z Y , et al . AOD-Net: All-in-One dehazing network [C]// International Conference on Computer Vision . Venice, Italy : IEEE , 2017 : 4770 - 4778 . doi: 10.1109/iccv.2017.511 http://dx.doi.org/10.1109/iccv.2017.511
REN W Q , LIU S , ZHANG H , et al . Single image dehazing via multi-scale convolutional neural networks [C]// European Conference on Computer Vision . Amsterdam, The Netherlands : Springer , 2016 : 154 - 169 . doi: 10.1007/978-3-319-46475-6_10 http://dx.doi.org/10.1007/978-3-319-46475-6_10
陈清江 , 张雪 , 柴昱洲 . 基于卷积神经网络的图像去雾算法 [J]. 液晶与显示 , 2019 , 34 ( 2 ): 220 - 227 . doi: 10.3788/yjyxs20193402.0220 http://dx.doi.org/10.3788/yjyxs20193402.0220
CHEN Q J , ZHANG X , CHAI Y Z . Image defogging algorithms based on multiscale convolution neural network [J]. Chinese Journal of Liquid Crystals and Displays , 2019 , 34 ( 2 ): 220 - 227 . (in Chinese) . doi: 10.3788/yjyxs20193402.0220 http://dx.doi.org/10.3788/yjyxs20193402.0220
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 . doi: 10.1109/tpami.2003.1201821 http://dx.doi.org/10.1109/tpami.2003.1201821
NARASIMHAN S G , NAYAR S K . Vision and the atmosphere [J]. International Journal of Computer Vision , 2002 , 48 ( 3 ): 233 - 254 . doi: 10.1023/a:1016328200723 http://dx.doi.org/10.1023/a:1016328200723
LI B Y , REN W Q , FU D P , et al . Benchmarking single image dehazing and beyond [J]. IEEE Transactions on Image Processing , 2019 , 28 ( 1 ): 492 - 505 . doi: 10.1109/tip.2018.2867951 http://dx.doi.org/10.1109/tip.2018.2867951
0
浏览量
87
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621