结合天空分割和超像素级暗通道的图像去雾算法
|
摘要
为了提升去雾图像质量,提出了一种基于天空分割和超像素级暗通道的单幅图像去雾方法。首先提出一种简单有效的多阈值天空分割方法,可将图像划分为天空区域和非天空区域;其次,根据天空区域估计大气光值;然后分别估计两类区域的透射率,对天空区域利用该区域无雾和有雾时暗通道值间的线性关系直接估计其透射率,对非天空区域则通过计算超像素级暗通道值来估计透射率;最后根据大气散射模型恢复无雾图像。实验结果表明,与现有方法相比,本文方法能更准确地分割天空且阈值自适应性强,大气光和透射率估计也更准确高效。采用本文方法得到的去雾图像具有对比度高、颜色自然、细节清晰等优点。
In order to improve the quality of restored images,a single image dehazing approach based on sky segmentation and superpixel-level dark channel model is proposed. First,a simple but effective multithreshold sky segmentation method is presented,which divides the image into sky area and non-sky area.Second,the atmospheric light is estimated in sky area. Third,the transmission maps of the two types of areas are estimated respectively. For sky area, the transmission is directly estimated by the linear relationship between the dark channel values of clear images and the corresponding hazy images. For nonsky area,the transmission is estimated by superpixel-level dark channel values. Finally,the haze-free image can be restored by the atmospheric scattering model. Experimental results show that,compared with the existing methods,the proposed method can segment the sky more accurately with better adaption of the thresholds,and can estimate the atmospheric light and the transmission map with higher accuracy and efficiency. Moreover,the dehazed images obtained by the proposed method have many advantages such as high contrast,natural color and abundant details.
In order to improve the quality of restored images,a single image dehazing approach based on sky segmentation and superpixel-level dark channel model is proposed. First,a simple but effective multithreshold sky segmentation method is presented,which divides the image into sky area and non-sky area.Second,the atmospheric light is estimated in sky area. Third,the transmission maps of the two types of areas are estimated respectively. For sky area, the transmission is directly estimated by the linear relationship between the dark channel values of clear images and the corresponding hazy images. For nonsky area,the transmission is estimated by superpixel-level dark channel values. Finally,the haze-free image can be restored by the atmospheric scattering model. Experimental results show that,compared with the existing methods,the proposed method can segment the sky more accurately with better adaption of the thresholds,and can estimate the atmospheric light and the transmission map with higher accuracy and efficiency. Moreover,the dehazed images obtained by the proposed method have many advantages such as high contrast,natural color and abundant details.
引文
[1]Fattal R.Single image dehazing[J].ACM Transactions on Graphics,2008,27(3):19.
[2]Tarel J P,Hautiere N.Fast visibility restoration from a single color or gray level image[C]∥IEEE International Conference on Computer Vision,Xi'an,China,2009:22012208.
[3]He Kaiming,Sun Jian,Tang Xiaoou.Single image haze removal using dark channel prior[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2011,33(12):23412353.
[4]Zhu Qingsong,Mai Jiaming,Shao Ling.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):35223533.
[5]Cui Tong,Qu Liangqiong,Tian Jiandong,et al.Single image haze removal based on luminance weight prior[C]∥IEEE International Conference on Cyber Technology in Automation,Control,and Intelligent Systems,Chengdu,China,2016:332336.
[6]毕笃彦,眭萍,何林远,等.基于Color Lines先验的高阶马尔科夫随机场去雾[J].电子与信息学报,2016,38(9):24052409.Bi Duyan,Sui Ping,He Linyuan,et al.Higherorder Markov random fields defogging based on Color Lines[J].Journal of Electronics&Information Technology,2016,38(9):24052409.
[7]Bui T M,Tran H N,Kim W,et al.Segmenting dark channel prior in single image dehazing[J].Electronics Letters,2014,50(7):516518.
[8]汪云飞,刘华伟,赵搏欣.融合超像素的黄金暗通道单幅图像去雾方法[J].西安电子科技大学学报,2017,44(5):147152.Wang Yunfei,Liu Huawei,Zhao Boxin.Superpixelsbased golden dark channel for single image fog removal[J].Journal of Xidian University,2017,44(5):147152.
[9]Zhu Qingsong,Wu Di,Xie Yaoqin,et al.Quick shift segmentation guided single image haze removal algorithm[C]∥IEEE International Conference on Robotics and Biomimetics,Bali,2014:113117.
[10]郑良缘,王平,高颖慧.基于超像素分割的图像去雾算法[J].重庆理工大学学报,2015,29(6):100106.Zheng Liangyuan,Wang Ping,Gao Yinghui.Single image dehazing based on superpixels segmentation[J].Journal of Chongqing University of Technology,2015,29(6):100106.
[11]王睿,李蕊,廉小亲.基于大气多散射模型和超像素分割的图像去雾[J].光子学报,2016,45(4):124130.Wang Rui,Li Rui,Lian Xiaoqin.Multiple scattering model based image dehazing with superpixel[J].Acta Photonica Sinica,2016,45(4):124130.
[12]蒋建国,侯天峰,齐美彬.改进的基于暗原色先验的图像去雾算法[J].电路与系统学报,2011,16(2):712.Jiang Jianguo,Hou Tianfeng,Qi Meibin.Improved algorithm on image haze removal using dark channel prior[J].Journal of Circuits and Systems,2011,16(2):712.
[13]Zhu Qingsong,Mai Jiaming,Song Zhan,et al.Mean shiftbased single image dehazing with rerefined transmission map[C]∥IEEE International Conference on Systems,Man and Cybernetics,San Diego,USA,2014:40584064.
[14]Liu Haitao,Guo Jin,Sun Changyin.An improved dehazing method based on the transmission compensation[C]∥World Congress on Intelligent Control and Automation,Guilin,China,2016:27322737.
[15]Han Xiaoxu,Feng Hongwei,Bu Qirong,et al.Image dehazing based on twopeak channel prior[C]∥IEEE International Conference on Image Processing,Phoenix,2016:22362240.
[16]Yuan Hui,Liu Changchun,Guo Zhixin,et al.A regionwised medium transmission based image dehazing method[J].IEEE Access,2017,5:17351742.
[17]He Kaiming,Sun Jian,Tang Xiaoou.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):13971409.
[18]Wang Keyan,Zhang Shanshan,Li Yunsong.Haze removal via edge weighted pixeltopatch fusion[J].MobileNetworksandApplications,2017,22(3):464477.
[19]Achanta R,Shaji A,Smith K.SLIC superpixels compared to stateoftheart superpixel methods[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2012,34(11):22742281.
[20]Hautière N,Tarel J P,Aubert D,et al.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis and Stereology,2008,27(2):8795.
[2]Tarel J P,Hautiere N.Fast visibility restoration from a single color or gray level image[C]∥IEEE International Conference on Computer Vision,Xi'an,China,2009:22012208.
[3]He Kaiming,Sun Jian,Tang Xiaoou.Single image haze removal using dark channel prior[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2011,33(12):23412353.
[4]Zhu Qingsong,Mai Jiaming,Shao Ling.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):35223533.
[5]Cui Tong,Qu Liangqiong,Tian Jiandong,et al.Single image haze removal based on luminance weight prior[C]∥IEEE International Conference on Cyber Technology in Automation,Control,and Intelligent Systems,Chengdu,China,2016:332336.
[6]毕笃彦,眭萍,何林远,等.基于Color Lines先验的高阶马尔科夫随机场去雾[J].电子与信息学报,2016,38(9):24052409.Bi Duyan,Sui Ping,He Linyuan,et al.Higherorder Markov random fields defogging based on Color Lines[J].Journal of Electronics&Information Technology,2016,38(9):24052409.
[7]Bui T M,Tran H N,Kim W,et al.Segmenting dark channel prior in single image dehazing[J].Electronics Letters,2014,50(7):516518.
[8]汪云飞,刘华伟,赵搏欣.融合超像素的黄金暗通道单幅图像去雾方法[J].西安电子科技大学学报,2017,44(5):147152.Wang Yunfei,Liu Huawei,Zhao Boxin.Superpixelsbased golden dark channel for single image fog removal[J].Journal of Xidian University,2017,44(5):147152.
[9]Zhu Qingsong,Wu Di,Xie Yaoqin,et al.Quick shift segmentation guided single image haze removal algorithm[C]∥IEEE International Conference on Robotics and Biomimetics,Bali,2014:113117.
[10]郑良缘,王平,高颖慧.基于超像素分割的图像去雾算法[J].重庆理工大学学报,2015,29(6):100106.Zheng Liangyuan,Wang Ping,Gao Yinghui.Single image dehazing based on superpixels segmentation[J].Journal of Chongqing University of Technology,2015,29(6):100106.
[11]王睿,李蕊,廉小亲.基于大气多散射模型和超像素分割的图像去雾[J].光子学报,2016,45(4):124130.Wang Rui,Li Rui,Lian Xiaoqin.Multiple scattering model based image dehazing with superpixel[J].Acta Photonica Sinica,2016,45(4):124130.
[12]蒋建国,侯天峰,齐美彬.改进的基于暗原色先验的图像去雾算法[J].电路与系统学报,2011,16(2):712.Jiang Jianguo,Hou Tianfeng,Qi Meibin.Improved algorithm on image haze removal using dark channel prior[J].Journal of Circuits and Systems,2011,16(2):712.
[13]Zhu Qingsong,Mai Jiaming,Song Zhan,et al.Mean shiftbased single image dehazing with rerefined transmission map[C]∥IEEE International Conference on Systems,Man and Cybernetics,San Diego,USA,2014:40584064.
[14]Liu Haitao,Guo Jin,Sun Changyin.An improved dehazing method based on the transmission compensation[C]∥World Congress on Intelligent Control and Automation,Guilin,China,2016:27322737.
[15]Han Xiaoxu,Feng Hongwei,Bu Qirong,et al.Image dehazing based on twopeak channel prior[C]∥IEEE International Conference on Image Processing,Phoenix,2016:22362240.
[16]Yuan Hui,Liu Changchun,Guo Zhixin,et al.A regionwised medium transmission based image dehazing method[J].IEEE Access,2017,5:17351742.
[17]He Kaiming,Sun Jian,Tang Xiaoou.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):13971409.
[18]Wang Keyan,Zhang Shanshan,Li Yunsong.Haze removal via edge weighted pixeltopatch fusion[J].MobileNetworksandApplications,2017,22(3):464477.
[19]Achanta R,Shaji A,Smith K.SLIC superpixels compared to stateoftheart superpixel methods[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2012,34(11):22742281.
[20]Hautière N,Tarel J P,Aubert D,et al.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis and Stereology,2008,27(2):8795.