基于透射率融合与多重导向滤波的单幅图像去雾
|
摘要
为了避免图像去雾后细节模糊和噪声放大,将图像分解为结构层和纹理层,并只对其结构层进行去雾。基于频域滤波思想提出透射率融合方法,解决了现有透射率估计方法中普遍存在的块效应问题和复原图像中存在的晕轮伪影问题。针对透射率优化过程中存在的计算量大、透射率平滑与细节保持之间难以平衡等问题,提出了多重导向滤波透射率优化方法。同时,针对目前大气光估计易受图像中白色物体的影响,提出自适应大气光估计方法。实验结果表明,该算法得到的图像去雾彻底、细节清晰、颜色自然,不仅有效抑制噪声和晕轮伪影,而且显著提高场景对比度、饱和度。
In order to avoid the details blurring and noise amplification,the image is decomposed as structural layer and texture layer,and the dehazing operation is only performed on the structural layer.The transmission fusion method based on the idea of frequency domain filtering is proposed to remove the block effects in the transmission image and the halo artifacts in the restored image.To solve the problems existed in the transmission optimization process such as the complex computation,being incapable of keeping the balance between the transmission smoothing and details preservation,we propose the multi-guided filtering method.At the same time,an adaptive atmospheric light estimation method is proposed which can be applicable to the scenes with large white objects.Experimental results show that the proposed algorithm can remove the haze effectively and the restored image has clear details and natural color.The noise and halo artifacts are suppressed remarkably,and the contrast and saturation of the scene are improved significantly.
In order to avoid the details blurring and noise amplification,the image is decomposed as structural layer and texture layer,and the dehazing operation is only performed on the structural layer.The transmission fusion method based on the idea of frequency domain filtering is proposed to remove the block effects in the transmission image and the halo artifacts in the restored image.To solve the problems existed in the transmission optimization process such as the complex computation,being incapable of keeping the balance between the transmission smoothing and details preservation,we propose the multi-guided filtering method.At the same time,an adaptive atmospheric light estimation method is proposed which can be applicable to the scenes with large white objects.Experimental results show that the proposed algorithm can remove the haze effectively and the restored image has clear details and natural color.The noise and halo artifacts are suppressed remarkably,and the contrast and saturation of the scene are improved significantly.
引文
[1] Guo H,Xu X T,Li B.Study on image dehazing methods based on dark channel prior[J].Acta Optica Sinica,2018,38(4):0410002.郭翰,徐晓婷,李博.基于暗原色先验的图像去雾方法研究[J].光学学报,2018,38(4):0410002.
[2] Xu H T,Zhai G T,Wu X L,et al.Generalized equalization model for image enhancement[J].IEEE Transactions on Multimedia,2014,16(1):68-82.
[3] Liu H B,Yang J,Wu Z P,et al.A fast single image dehazing method based on dark channel prior and Retinex theory[J].Acta Automatica Sinica,2015,41(7):1264-1273.刘海波,杨杰,吴正平,等.基于暗通道先验和Retinex理论的快速单幅图像去雾方法[J].自动化学报,2015,41(7):1264-1273.
[4] Fattal R.Single image dehazing[J].ACM Transactions on Graphics,2008,27(3):72-80.
[5] Liu K,Bi D Y,Wang S P,et al.Single image dehazing based on sparse feature extraction[J].Acta Optica Sinica,2018,38(3):0310001.刘坤,毕笃彦,王世平,等.基于稀疏特征提取的单幅图像去雾[J].光学学报,2018,38(3):0310001.
[6] Tarel J P,Hautière N.Fast visibility restoration from a single color or gray level image[C]∥IEEE International Conference on Computer Vision,2009:2201-2208.
[7] He K M,Sun J,Tang X O.Single image haze removal using dark channel prior[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009:1956-1963.
[8] 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.
[9] Han Z T,Lu W,Yang S Y,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.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.
[10] Park H,Park D,Han D K,et al.Single image haze removal using novel estimation of atmospheric light and transmission[C]∥IEEE International Conference on Image Processing(ICIP),2014:4502-4506.
[11] Meng G F,Wang Y,Duan J Y,et al.Efficient image dehazing with boundary constraint and contextual regularization[C]∥IEEE International Conference on Computer Vision,2013:617-624.
[12] Ren W Q,Liu S,Zhang H,et al.Single image dehazingviamulti-scaleconvolutionalneural networks[C]∥European Conference on Computer Vision,2016:154-169.
[13] Cai B L,Xu X M,Jia K,et al.DehazeNet:an endto-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198.
[14] Li B Y,Peng X L,Wang Z Y,et al.AOD-net:allin-one dehazing network[C]∥IEEE International Conference on Computer Vision(ICCV),2017:4780-4788.
[15] Narasimhan S G, Nayar S K.Vision and the atmosphere[J].International Journal of Computer Vision,2002,48(3):233-254.
[16] Li Y,Guo F F,Tan R T,et al.A contrast enhancementframeworkwithJPEGartifacts suppression[M].Lecture Notes in Computer Science.Heidelberg:Springer,2014,8690:174-188.
[17] Xu L,Yan Q,Xia Y,et al.Structure extraction from texture via relative total variation[J].ACM Transactions on Graphics,2012,31(6):139-148.
[18] Wang Z L, Feng Y.Fast single haze image enhancement[J].Computers&Electrical Engineering,2014,40(3):785-795.1210001-10
[19] Wang J B,Lu K,Xue J,et al.Single image dehazing basedonthephysicalmodelandMSRCR algorithm[J].IEEE Transactions on Circuits and Systems for Video Technology,2018,28(9):2190-2199.
[20] Hautière N,Tarel J P,Aubert D,et al.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis&Stereology,2008,27(2):87-95.
[21] Wang Y K,Fan C T.Single image defogging by multiscale depth fusion[J].IEEE Transactions on Image Processing,2014,23(11):4826-4837.
[22] Yu S Y,Zhu H,Fu Z F,et al.Single image dehazing using multiple transmission layer fusion[J].Journal of Modern Optics,2016,63(6):519-535.
[2] Xu H T,Zhai G T,Wu X L,et al.Generalized equalization model for image enhancement[J].IEEE Transactions on Multimedia,2014,16(1):68-82.
[3] Liu H B,Yang J,Wu Z P,et al.A fast single image dehazing method based on dark channel prior and Retinex theory[J].Acta Automatica Sinica,2015,41(7):1264-1273.刘海波,杨杰,吴正平,等.基于暗通道先验和Retinex理论的快速单幅图像去雾方法[J].自动化学报,2015,41(7):1264-1273.
[4] Fattal R.Single image dehazing[J].ACM Transactions on Graphics,2008,27(3):72-80.
[5] Liu K,Bi D Y,Wang S P,et al.Single image dehazing based on sparse feature extraction[J].Acta Optica Sinica,2018,38(3):0310001.刘坤,毕笃彦,王世平,等.基于稀疏特征提取的单幅图像去雾[J].光学学报,2018,38(3):0310001.
[6] Tarel J P,Hautière N.Fast visibility restoration from a single color or gray level image[C]∥IEEE International Conference on Computer Vision,2009:2201-2208.
[7] He K M,Sun J,Tang X O.Single image haze removal using dark channel prior[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009:1956-1963.
[8] 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.
[9] Han Z T,Lu W,Yang S Y,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.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.
[10] Park H,Park D,Han D K,et al.Single image haze removal using novel estimation of atmospheric light and transmission[C]∥IEEE International Conference on Image Processing(ICIP),2014:4502-4506.
[11] Meng G F,Wang Y,Duan J Y,et al.Efficient image dehazing with boundary constraint and contextual regularization[C]∥IEEE International Conference on Computer Vision,2013:617-624.
[12] Ren W Q,Liu S,Zhang H,et al.Single image dehazingviamulti-scaleconvolutionalneural networks[C]∥European Conference on Computer Vision,2016:154-169.
[13] Cai B L,Xu X M,Jia K,et al.DehazeNet:an endto-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198.
[14] Li B Y,Peng X L,Wang Z Y,et al.AOD-net:allin-one dehazing network[C]∥IEEE International Conference on Computer Vision(ICCV),2017:4780-4788.
[15] Narasimhan S G, Nayar S K.Vision and the atmosphere[J].International Journal of Computer Vision,2002,48(3):233-254.
[16] Li Y,Guo F F,Tan R T,et al.A contrast enhancementframeworkwithJPEGartifacts suppression[M].Lecture Notes in Computer Science.Heidelberg:Springer,2014,8690:174-188.
[17] Xu L,Yan Q,Xia Y,et al.Structure extraction from texture via relative total variation[J].ACM Transactions on Graphics,2012,31(6):139-148.
[18] Wang Z L, Feng Y.Fast single haze image enhancement[J].Computers&Electrical Engineering,2014,40(3):785-795.1210001-10
[19] Wang J B,Lu K,Xue J,et al.Single image dehazing basedonthephysicalmodelandMSRCR algorithm[J].IEEE Transactions on Circuits and Systems for Video Technology,2018,28(9):2190-2199.
[20] Hautière N,Tarel J P,Aubert D,et al.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis&Stereology,2008,27(2):87-95.
[21] Wang Y K,Fan C T.Single image defogging by multiscale depth fusion[J].IEEE Transactions on Image Processing,2014,23(11):4826-4837.
[22] Yu S Y,Zhu H,Fu Z F,et al.Single image dehazing using multiple transmission layer fusion[J].Journal of Modern Optics,2016,63(6):519-535.