一种自适应线性透射率估计去雾算法
|
摘要
为了有效复原雾霾天气下退化的图像,文章提出了一种自适应线性透射率估计去雾算法。建立有雾图像与无雾图像最小值通道之间的线性变换模型;利用有雾图像的混合通道得到自适应参数,结合自适应参数和线性变换模型估计出透射率,通过有雾图像的最小值通道构造高斯函数来补偿估计明亮区域透射率,提升该区域透射率的准确度,再使用交叉双边滤波器消除纹理效应得到优化透射率;最后,结合大气散射模型复原出无雾图像。实验结果表明,该方法有效降低了时间复杂度,且复原的图像细节明显,明亮度适宜。
In order to effectively restore the degraded images in hazy weather, an adaptive linear transmission estimation dehazing algorithm was proposed. Firstly, we created a linear transformation model between the hazy image and the dehazing image minimum channel. Secondly, the adaptive parameters were obtained by using the mixed channel of the hazy image, and the transmission was estimated by combining the adaptive parameter and the linear transformation model. Then, a Gaussian function was constructed by the minimum channel of the hazy image to compensate the estimated transmission of the bright region, and the accuracy of the transmission of this region was improved, and the cross-bilateral filter was used to eliminate the texture effect to obtain the optimized transmission. Finally, a dehazing image was restored in combination with the atmospheric scattering model. The experimental results show that the method can effectively reduce the time complexity, and the restored image has obvious details and appropriate brightness.
In order to effectively restore the degraded images in hazy weather, an adaptive linear transmission estimation dehazing algorithm was proposed. Firstly, we created a linear transformation model between the hazy image and the dehazing image minimum channel. Secondly, the adaptive parameters were obtained by using the mixed channel of the hazy image, and the transmission was estimated by combining the adaptive parameter and the linear transformation model. Then, a Gaussian function was constructed by the minimum channel of the hazy image to compensate the estimated transmission of the bright region, and the accuracy of the transmission of this region was improved, and the cross-bilateral filter was used to eliminate the texture effect to obtain the optimized transmission. Finally, a dehazing image was restored in combination with the atmospheric scattering model. The experimental results show that the method can effectively reduce the time complexity, and the restored image has obvious details and appropriate brightness.
引文
[1] XU Y,WEN J,FEI L K,et al.Review of video and image defogging algorithms and related studies on image restoration and enhancement[J].IEEE Access,2016,4:165-188.
[2] GUO Han,XU Xiaoting,LI Bo.Study on image dehazing methods based on dark channel prior[J].Acta Optica Sinica,2018,38(4):113-122.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):113-122.
[3] HUANG Lihong.Fog-degraded image enhancement based on single-scale Retinex[J].Journal of Applied Optics,2010,31(5):728-733.黄黎红.一种基于单尺度Retinex的雾天降质图像增强新算法[J].应用光学,2010,31(5):728-733.
[4] ZHANG Xiaogang,TANG Meiling,CHEN Hua,et al.A dehazing method in single image based on double-area filter and image fusion[J].Acta Automatica Sinica,2014,40(8):1733-1739.
[5] CAI Bolun ,XU Xiangmin ,JIA Kui ,et al.DehazeNet:an end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198.
[6] ZHU Q S,MAI J M,SHAO L.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):3522-3533.
[7] WANG Yuankai,FAN Chingtang.Single image defogging by multiscale depth fusion[J].IEEE Transactions on Image Processing ,2014,23(11):4826.
[8] HE K M,SUN J,TANG X O.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[9] NARASIMHAN Srinivasa,NAYAR Shree.Vision and the atmosphere[J].International Journal of Computer Vision,2002,48(3):233-254.
[10] LAND Eh,MCCANN Jj.Lightness and retinex theory[J].Journal of the Optical Society of America,1971,61(1):1.
[11] WANG Wencheng,YUNG Xiaohui,WU Xiaojing,et al.Fast image dehazing method based on linear transformation[J].IEEE Transactions on Multimedia,2017,19(6):1142-1155.
[12] HE Kaiming,SUN Jian,TANG Xiaoou.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[13] MENG Gaofeng,WANG Ying,DUAN Jiangyong.Efficient image dehazing with boundary constraint and contextual regularization[C].//The IEEE International Conference on Computer Vision (ICCV),Sydney,NSW:IEEE,2013:617-624.
[14] SUN Wei,WANG Hao,SUN Changhao,et al.Fast single image haze removal via local atmospheric light veil estimation.[J].Computers & Electrical Engineering,2015,46:371-383.
[15] HAUTIER Nicolas.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis & Stereology Journal,2008,27(2):87-95.
[2] GUO Han,XU Xiaoting,LI Bo.Study on image dehazing methods based on dark channel prior[J].Acta Optica Sinica,2018,38(4):113-122.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):113-122.
[3] HUANG Lihong.Fog-degraded image enhancement based on single-scale Retinex[J].Journal of Applied Optics,2010,31(5):728-733.黄黎红.一种基于单尺度Retinex的雾天降质图像增强新算法[J].应用光学,2010,31(5):728-733.
[4] ZHANG Xiaogang,TANG Meiling,CHEN Hua,et al.A dehazing method in single image based on double-area filter and image fusion[J].Acta Automatica Sinica,2014,40(8):1733-1739.
[5] CAI Bolun ,XU Xiangmin ,JIA Kui ,et al.DehazeNet:an end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198.
[6] ZHU Q S,MAI J M,SHAO L.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):3522-3533.
[7] WANG Yuankai,FAN Chingtang.Single image defogging by multiscale depth fusion[J].IEEE Transactions on Image Processing ,2014,23(11):4826.
[8] HE K M,SUN J,TANG X O.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[9] NARASIMHAN Srinivasa,NAYAR Shree.Vision and the atmosphere[J].International Journal of Computer Vision,2002,48(3):233-254.
[10] LAND Eh,MCCANN Jj.Lightness and retinex theory[J].Journal of the Optical Society of America,1971,61(1):1.
[11] WANG Wencheng,YUNG Xiaohui,WU Xiaojing,et al.Fast image dehazing method based on linear transformation[J].IEEE Transactions on Multimedia,2017,19(6):1142-1155.
[12] HE Kaiming,SUN Jian,TANG Xiaoou.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[13] MENG Gaofeng,WANG Ying,DUAN Jiangyong.Efficient image dehazing with boundary constraint and contextual regularization[C].//The IEEE International Conference on Computer Vision (ICCV),Sydney,NSW:IEEE,2013:617-624.
[14] SUN Wei,WANG Hao,SUN Changhao,et al.Fast single image haze removal via local atmospheric light veil estimation.[J].Computers & Electrical Engineering,2015,46:371-383.
[15] HAUTIER Nicolas.Blind contrast enhancement assessment by gradient ratioing at visible edges[J].Image Analysis & Stereology Journal,2008,27(2):87-95.