基于色调映射和暗通道融合的弱光图像增强
|
摘要
针对阴天或夜晚等弱光条件下拍摄的图像具有亮度低、对比度低和细节模糊等问题,提出了一种基于色调映射和暗通道融合的弱光图像增强方法.首先,根据弱光及其反转图像的特点,提出面向弱光图像的透射率估计方法,进而获得场景深度信息,并将其融入色调映射函数设计;同时利用暗通道图像区分光源区域,以修正色调映射函数参数,使其能够根据场景深度自适应调整图像亮度;另一方面,增强后的暗通道图可有效突出图像的细节信息,将经过色调映射后的V通道图像和暗通道图进行加权融合,得到最后的增强结果.实验结果表明,本文方法不仅显著改善图像亮度、增强对比度、恢复出更多的图像细节,还能有效去除块效应和晕轮伪影,视觉效果理想.
Images captured at night or under low light conditions have the problems of low intensity,low contrast and blurring of details.This paper proposed a new low-light image enhancement method based on tone mapping and dark channel fusion.Firstly,an improved transmission estimation method was presented to obtain the depth information by using the statistics characteristics of low light image and its inversion.Then,the tone mapping function was designed by incorporating the scene depth.In addition,the pixel-wise dark channel was used to recognize the light source region with the purpose of modifying the parameter of the tone mapping function,and so the image brightness can be adjusted adaptively.In order to preserve more image details,the pixel-wise dark channel was enhanced and fused with the enhanced V-channel image to get the final results.Experimental results show that the proposed method not only improves the image brightness and contrast with more details,but also removes block effects and halo artifacts with ideal visual effects.
Images captured at night or under low light conditions have the problems of low intensity,low contrast and blurring of details.This paper proposed a new low-light image enhancement method based on tone mapping and dark channel fusion.Firstly,an improved transmission estimation method was presented to obtain the depth information by using the statistics characteristics of low light image and its inversion.Then,the tone mapping function was designed by incorporating the scene depth.In addition,the pixel-wise dark channel was used to recognize the light source region with the purpose of modifying the parameter of the tone mapping function,and so the image brightness can be adjusted adaptively.In order to preserve more image details,the pixel-wise dark channel was enhanced and fused with the enhanced V-channel image to get the final results.Experimental results show that the proposed method not only improves the image brightness and contrast with more details,but also removes block effects and halo artifacts with ideal visual effects.
引文
[1]Chen S D,Ramli A R.Preserving brightness in histogram equalization based contrast enhancement techniques[J].Digital Signal Process,2004,14(5):413-428.
[2]Rahman Z,Jobson D J,Woodell G A.Multi-scale retinex for color image enhancement[C]//International Conference on Image Processings.Lausanne,Switzerland,1996:1003-1006.
[3]Wang Wen,Li Bo,Zheng Jin,et al.A fast multi-scale retinex algorithm for color image enhancement[C]//International Conference on Wavelet Analysis and Pattern Recognition.New Jersey,USA,2008:80-85.
[4]Jin X.Image enhancement based on selective retinex fusion algorithm[J].Journal of Software,2012,7(6):1187-1194.
[5]Drago F,Myszkowski K,Annen T,et al.Adaptive loga-rithmic mapping for displaying high contrast scenes[J].Computer Graphics Forum,2010,22(3):419-426.
[6]Zhou Zhigang,Sang Nong,Hu Xinrong.Global brightness and local contrast adaptive enhancement for low illumination color image[J].Optik,2014,125(6):1795-1799.
[7]Dong Xuan,Wang Guan,Pang Yi,et al.Fast efficient al-gorithm for enhancement of low lighting video[J].Journal of Information and Computation Science,2011,10(7):1-6.
[8]He Kaiming,Sun Jian,Tang Xiaoou.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[9]Narasimhan S G,Nayar S K.Vision and the atmosphere[J].International Journal of Computer Vision,2002,48(3):233-254.
[10]Kratz L,Nishino K.Factorizing scene albedo and depth from a single foggy image[C]//International Conference on Computer Vision.Kyoto,Japan,2009:1701-1708.
[11]Jiang X,Yao H,Zhang S,et al.Night video enhancement using improved dark channel prior[C]//International Conference on Image Processing.Melbourne,Australia,2013:553-557.
[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):7-12.Jiang Jianguo,Hou Tianfeng,Qi Meibin.Improved algorithm on single image haze removal using dark channel prior[J].Journal of Circuits and Systems,2011,16(2):7-12(in Chinese).
[13]Anderes E.Robust adaptive wiener filtering[C]//International Conference on Image Processing.Quebec,Canada,2012:3081-3084.
[14]Zhu Q,Mai J,Shao L,et al.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):3522-3533.
[15]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.
[2]Rahman Z,Jobson D J,Woodell G A.Multi-scale retinex for color image enhancement[C]//International Conference on Image Processings.Lausanne,Switzerland,1996:1003-1006.
[3]Wang Wen,Li Bo,Zheng Jin,et al.A fast multi-scale retinex algorithm for color image enhancement[C]//International Conference on Wavelet Analysis and Pattern Recognition.New Jersey,USA,2008:80-85.
[4]Jin X.Image enhancement based on selective retinex fusion algorithm[J].Journal of Software,2012,7(6):1187-1194.
[5]Drago F,Myszkowski K,Annen T,et al.Adaptive loga-rithmic mapping for displaying high contrast scenes[J].Computer Graphics Forum,2010,22(3):419-426.
[6]Zhou Zhigang,Sang Nong,Hu Xinrong.Global brightness and local contrast adaptive enhancement for low illumination color image[J].Optik,2014,125(6):1795-1799.
[7]Dong Xuan,Wang Guan,Pang Yi,et al.Fast efficient al-gorithm for enhancement of low lighting video[J].Journal of Information and Computation Science,2011,10(7):1-6.
[8]He Kaiming,Sun Jian,Tang Xiaoou.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[9]Narasimhan S G,Nayar S K.Vision and the atmosphere[J].International Journal of Computer Vision,2002,48(3):233-254.
[10]Kratz L,Nishino K.Factorizing scene albedo and depth from a single foggy image[C]//International Conference on Computer Vision.Kyoto,Japan,2009:1701-1708.
[11]Jiang X,Yao H,Zhang S,et al.Night video enhancement using improved dark channel prior[C]//International Conference on Image Processing.Melbourne,Australia,2013:553-557.
[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):7-12.Jiang Jianguo,Hou Tianfeng,Qi Meibin.Improved algorithm on single image haze removal using dark channel prior[J].Journal of Circuits and Systems,2011,16(2):7-12(in Chinese).
[13]Anderes E.Robust adaptive wiener filtering[C]//International Conference on Image Processing.Quebec,Canada,2012:3081-3084.
[14]Zhu Q,Mai J,Shao L,et al.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):3522-3533.
[15]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.