基于加权引导滤波的快速自适应图像去雾
|
摘要
针对有雾天气下传统去雾方法对天空明亮区域大气光值和透射率的估计不足,导致去雾后图像颜色失真,细节信息丢失等问题,提出一种基于加权引导滤波的快速自适应图像去雾算法。首先,天空区域部分将被分割和分开处理,避免在处理图像时由于暗通道原理对天空区域免疫引起结果图像的色彩偏移和伪影。然后,通过暗通道图像粗略估计获取透射率图,采用快速加权引导滤波结合上采样和下采样优化透射率;最后,利用亮度和饱和度调整去雾后的结果图。结果表明:本文算法对于大气光值和透射率的估计准确性得到较大提高,恢复的无雾图像的清晰度和细节增强方面得到了明显提升,具有较高的鲁棒性,适用于智能交通、目标识别等领域。
The traditional dehazing method is not enough to estimate the atmospheric light value and transmittance in the bright area under foggy weather, which leads to the image color distortion and the loss of detailed information after defogging. A fast adaptive image defogging based on weighted guided filtering is proposed. Firstly, the sky region will be segmented and segmented to avoid the color offset and artifacts of the resulting image caused by the immunity to the sky region due to the dark channel principle. Then, the transmittance map is obtained by rough estimation of dark channel image, and the transmittance is optimized by fast weighted guided filtering combined with up-sampling and down-sampling. Finally, the results of defogging are adjusted by brightness and saturation. The results show that the accuracy of estimating the atmospheric light value and transmittance is greatly improved, and the clarity and details of the recovered fog-free image are obviously improved. The algorithm has high robustness and is suitable for intelligent transportation, target recognition and other fields.
The traditional dehazing method is not enough to estimate the atmospheric light value and transmittance in the bright area under foggy weather, which leads to the image color distortion and the loss of detailed information after defogging. A fast adaptive image defogging based on weighted guided filtering is proposed. Firstly, the sky region will be segmented and segmented to avoid the color offset and artifacts of the resulting image caused by the immunity to the sky region due to the dark channel principle. Then, the transmittance map is obtained by rough estimation of dark channel image, and the transmittance is optimized by fast weighted guided filtering combined with up-sampling and down-sampling. Finally, the results of defogging are adjusted by brightness and saturation. The results show that the accuracy of estimating the atmospheric light value and transmittance is greatly improved, and the clarity and details of the recovered fog-free image are obviously improved. The algorithm has high robustness and is suitable for intelligent transportation, target recognition and other fields.
引文
[1]S.G Narasimhan.Contrast restoration of weather degraded images[J].Pattern Analysis and Machine Intelligence,200325(6):713-724.
[2]Jobson D J,Rahman Z,Woodell GA.Properties and performance of a center/surround retinex[J].IEEE Transactions on Image Processing,1997,6(3):451-462.
[3]Shwartz S,Namer E,Schechner Y Y.Blind haze separation[C]//Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Los Alamitos IEEE Computer Society Press,2006,2:1984-1991.
[4]Fattal R.Single image dehazing[J].ACM Transaction on Graphics(TOG),New York,USA,2008,27(3):1-9.
[5]陈功,王唐,周荷琴.基于物理模型的雾天图像复原新方法[J].中国图象图形学报,2008,27(5):1-10.
[6]祝培,朱虹等.一种有雾天气图像景物影像的清晰化方法[J].中国图象图形学报,2004,9(1):124-128.
[7]He K M,Sun J.Single image haze removal using dark channel prior[C].Computer Vision and Pattern Recognition(CVPR),2009,Proceedings.,IEEE Conference on.Miami USA:IEEE,2009,1956-1963.
[8]RUSSO F.An image enhancement technique combining sharpening and noise reduction[J].IEEE Transactions on Instrumentation and Measurement,2002,51(4):824-828.
[9]Gibson K B,Nguyen T Q.An investigation of dehazing effects on image and video coding[J].IEEE Transactions on Image Processing,2012,21(2):662-673.
[10]嵇晓强,图像快速去雾与清晰度恢复技术研究:[博士学位论文].吉林:中国科学院长春光学精密机械与物理研究所,2012.
[11]孙小明,孙俊喜,赵立荣等.暗原色先验单幅图像去雾改进算法[J].中国图象图形学报,2014,19(3):381-385.
[12]楚君,王华彬,陶亮,等.基于引导滤波器的单幅雾天图像复原算法[J].计算机工程与应用,2015,51(19):155-160.
[13]眭萍,毕笃彦,马时平,等.基于马尔可夫随机场框架的单幅图像去雾[J].计算机应用研究,2016,33(9):2844-2847.
[14]MiZetian,Zhou Huan,Zheng Yijun,et a1.Single image dehazing via multi-scale gradient domain contrast enhancement[J].1ET Image Processing,2016,10(3):206-214.
[15]王小元,张红英,吴亚东等.基于物理模型的低照度图像增强算法[J].计算机应用,2015,35(8):2301-2304.
[16]L.Caraffa and J.-P.Tarel,“Stereo reconstruction and contrast restoration in daytime fog”in Computer Vision(Lecture Notes in Computer Science),vol.7727.Heidelberg,Germany:Springer,2013,pp.13-25.
[17]陈龙,郭宝龙,毕娟,等.基于联合双边滤波的单幅图像去雾算法[J].北京邮电大学学报,2012,35(4):19-23.
[18]杨国强.图像和视频去雾技术的研究[D].天津大学,2010
[19]郭璠.图像去雾方法和评价及其应用研究[D].中南大学2012.
[20]Zhang Y,Sun G,Ren Q,Zhao D.Foggy Images Classification Based On Features Extraction and SVM[C]//Proceeding of 2013 International Conference on Software Engineering and Computer Science.Los Alamitos:IEEE Computer Society Press,2013.142-145
[2]Jobson D J,Rahman Z,Woodell GA.Properties and performance of a center/surround retinex[J].IEEE Transactions on Image Processing,1997,6(3):451-462.
[3]Shwartz S,Namer E,Schechner Y Y.Blind haze separation[C]//Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Los Alamitos IEEE Computer Society Press,2006,2:1984-1991.
[4]Fattal R.Single image dehazing[J].ACM Transaction on Graphics(TOG),New York,USA,2008,27(3):1-9.
[5]陈功,王唐,周荷琴.基于物理模型的雾天图像复原新方法[J].中国图象图形学报,2008,27(5):1-10.
[6]祝培,朱虹等.一种有雾天气图像景物影像的清晰化方法[J].中国图象图形学报,2004,9(1):124-128.
[7]He K M,Sun J.Single image haze removal using dark channel prior[C].Computer Vision and Pattern Recognition(CVPR),2009,Proceedings.,IEEE Conference on.Miami USA:IEEE,2009,1956-1963.
[8]RUSSO F.An image enhancement technique combining sharpening and noise reduction[J].IEEE Transactions on Instrumentation and Measurement,2002,51(4):824-828.
[9]Gibson K B,Nguyen T Q.An investigation of dehazing effects on image and video coding[J].IEEE Transactions on Image Processing,2012,21(2):662-673.
[10]嵇晓强,图像快速去雾与清晰度恢复技术研究:[博士学位论文].吉林:中国科学院长春光学精密机械与物理研究所,2012.
[11]孙小明,孙俊喜,赵立荣等.暗原色先验单幅图像去雾改进算法[J].中国图象图形学报,2014,19(3):381-385.
[12]楚君,王华彬,陶亮,等.基于引导滤波器的单幅雾天图像复原算法[J].计算机工程与应用,2015,51(19):155-160.
[13]眭萍,毕笃彦,马时平,等.基于马尔可夫随机场框架的单幅图像去雾[J].计算机应用研究,2016,33(9):2844-2847.
[14]MiZetian,Zhou Huan,Zheng Yijun,et a1.Single image dehazing via multi-scale gradient domain contrast enhancement[J].1ET Image Processing,2016,10(3):206-214.
[15]王小元,张红英,吴亚东等.基于物理模型的低照度图像增强算法[J].计算机应用,2015,35(8):2301-2304.
[16]L.Caraffa and J.-P.Tarel,“Stereo reconstruction and contrast restoration in daytime fog”in Computer Vision(Lecture Notes in Computer Science),vol.7727.Heidelberg,Germany:Springer,2013,pp.13-25.
[17]陈龙,郭宝龙,毕娟,等.基于联合双边滤波的单幅图像去雾算法[J].北京邮电大学学报,2012,35(4):19-23.
[18]杨国强.图像和视频去雾技术的研究[D].天津大学,2010
[19]郭璠.图像去雾方法和评价及其应用研究[D].中南大学2012.
[20]Zhang Y,Sun G,Ren Q,Zhao D.Foggy Images Classification Based On Features Extraction and SVM[C]//Proceeding of 2013 International Conference on Software Engineering and Computer Science.Los Alamitos:IEEE Computer Society Press,2013.142-145