改进大气散射模型实现的图像去雾算法
|
摘要
传统大气散射模型在图像去雾的求解过程中通常假设场景入射光为全局常量,然而这种假设并不合理,为此提出一种基于改进大气散射模型的图像去雾算法.首先基于亮通道先验和模糊聚类对雾图进行场景分类,并估计出各个场景的入射光照;然后根据光学辐射特性估计出场景结构,并利用雾气浓度估计模型进一步获得透射率的表达式;最后通过改进大气散射模型恢复出无雾图像.大量对比实验结果表明,该算法能够恢复出细节丰富、清晰自然的无雾图像,计算速度相对较快,能满足一般工程的实时性要求.
The scene incident light is always assumed to be a global constant when the traditional atmospheric scattering model is used in the image dehazing. However, the assumption is unreasonable. Thus, an image dehazing method based on an improved atmospheric scattering model is put forward. Firstly, a hazy image was classified into different scenes by the brightness channel prior and the fuzzy clustering. Secondly, the incident light of each scene was estimated. Then, the scene structure was estimated by the optical radiation characteristic. After that, the transmission can be calculated by the haze concentration estimation model. Finally, the hazy image is recovered with the improved atmospheric scattering model. A large number of comparative experimental results show that the proposed algorithm can recover a more detailed, clear and natural haze-free images. Besides, the calculation speed is relatively fast which can meet the real-time requirements of general engineering.
The scene incident light is always assumed to be a global constant when the traditional atmospheric scattering model is used in the image dehazing. However, the assumption is unreasonable. Thus, an image dehazing method based on an improved atmospheric scattering model is put forward. Firstly, a hazy image was classified into different scenes by the brightness channel prior and the fuzzy clustering. Secondly, the incident light of each scene was estimated. Then, the scene structure was estimated by the optical radiation characteristic. After that, the transmission can be calculated by the haze concentration estimation model. Finally, the hazy image is recovered with the improved atmospheric scattering model. A large number of comparative experimental results show that the proposed algorithm can recover a more detailed, clear and natural haze-free images. Besides, the calculation speed is relatively fast which can meet the real-time requirements of general engineering.
引文
[1]Lalonde J F,Efros A A,Narasimhan S G.Estimating the natural illumination conditions from a single outdoor image[J].International Journal of Computer Vision,2012,98(2):123-145
[2]Yun Haijiao,Wu Zhiyong,Wang Guanjun,et al.Enhancement of infrared image combined with histogram equalization and fuzzy set theory[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(8):1498-1505(in Chinese)(云海姣,吴志勇,王冠军,等.结合直方图均衡和模糊集理论的红外图像增强[J].计算机辅助设计与图形学学报,2015,27(8):1498-1505)
[3]Wu Di,Zhu Qingsong.The latest research progress of image dehazing[J].Acta Automatica Sinica,2015,41(2):221-239(in Chinese)(吴迪,朱青松.图像去雾的最新研究进展[J].自动化学报,2015,41(2):221-239)
[4]Xiao L M,Li C,Wu Z Z,et al.An enhancement method for X-ray image via fuzzy noise removal and homomorphic filtering[J].Neurocomputing,2016,195:56-64
[5]Liu H T,Lu H Q,Zhang Y.Image enhancement for outdoor long-range surveillance using IQ-learning multiscale Retinex[J].IET Image Processing,2017,11(9):786-795
[6]Ma Zhongli,Wen Jie.Single-scale Retinex sea fog removal algorithm fused the edge information[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(2):217-225(in Chinese)(马忠丽,文杰.融合边缘信息的单尺度Retinex海雾去除算法[J].计算机辅助设计与图形学学报,2015,27(2):217-225)
[7]Mi Z,Zhou H,Zheng Y J,et al.Single image dehazing via multi-scale gradient domain contrast enhancement[J].IET Image Processing,2016,10(3):206-214
[8]Fattal R.Single image dehazing[J].ACM Transactions on Graphics,2008,27(3):Article No.72
[9]Tarel J P,Hautiere N.Fast visibility restoration from a single color or gray level image[C]//Proceedings of the 12th IEEEInternational Conference on Computer Vision.Los Alamitos:IEEE Computer Society Press,2009:2201-2208
[10]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
[11]He K M,Sun J,Tang X O.Guided image filtering[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409
[12]Meng G F,Wang Y,Duan J Y,et al.Efficient image dehazing with boundary constraint and contextual regularization[C]//Proceedings of the IEEE International Conference on Computer Vision.Los Alamitos:IEEE Computer Society Press,2013:617-624
[13]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
[14]Yu Chunyan,Xu Xiaodan,Lin Huixiang,et al.Low-illumination image enhancement method based on a fog-degraded model[J].Journal of Image and Graphics,2017,22(9):1194-1205(in Chinese)(余春艳,徐小丹,林晖翔,等.应用雾天退化模型的低照度图像增强[J].中国图象图形学报,2017,22(9):1194-1205)
[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
[16]Yu Jing,Xu Dongbin,Liao Qingmin.Image defogging:a survey[J].Journal of Image and Graphics,2011,16(9):1561-1576(in Chinese)(禹晶,徐东彬,廖庆敏.图像去雾技术研究进展[J].中国图象图形学报,2011,16(9):1561-1576)
[17]Tan R T.Visibility in bad weather from a single image[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2008:1-8
[18]Bi G L,Ren J Y,Fu T J,et al.Image dehazing based on accurate estimation of transmission in the atmospheric scattering model[J].IEEE Photonics Journal,2017,9(4):Article No.7802918
[19]Nishiyama K,Endo S,Jinno K,et al.Identification of typical synoptic patterns causing heavy rainfall in the rainy season in Japan by a self-organizing map[J].Atmospheric Research,2015,83(2-4):185-200
[20]Zhou Chenxi,Liang Xun,Qi Jinshan.A semi-supervised agglomerative hierarchical clustering method based on dynamically updating constraints[J].Acta Automatica Sinica,2015,41(7):1253-1263(in Chinese)(周晨曦,梁循,齐金山.基于约束动态更新的半监督层次聚类算法[J].自动化学报,2015,41(7):1253-1263)
[21]Kang S H,Sandberg B,Yip A M.A regularized k-means and multiphase scale segmentation[J].Inverse Problems and Imaging,2011,5(2):407-429
[22]Qamar U.A dissimilarity measure based Fuzzy c-means(FCM)clustering algorithm[J].Journal of Intelligent and Fuzzy Systems,2014,26(1):229-238
[23]Li L R,Sang H S,Zhou G,et al.Instant haze removal from a single image[J].Infrared Physics&Technology,2017,83:156-163
[24]Wang J B,He N,Zhang L L,et al.Single image dehazing with a physical model and dark channel prior[J].Neurocomputing,2015,149:718-728
[25]Sulami M,Glatzer I,Fattal R,et al.Automatic recovery of the atmospheric light in hazy images[C]//Proceedings of the IEEEInternational Conference on Computational Photography.Los Alamitos:IEEE Computer Society Press,2014:1-11
[26]Berman D,Treibitz T,Avidan S.Non-local image dehazing[C]//Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEEComputer Society Press,2016:1674-1682
[27]Li Dapeng,Yu Jing,Xiao Chuangbai.No-reference quality assessment method for defogged images[J].Journal of Image and Graphics,2011,16(9):1753-1757(in Chinese)(李大鹏,禹晶,肖创柏.图像去雾的无参考客观质量评测方法[J].中国图象图形学报,2011,16(9):1753-1757)
[2]Yun Haijiao,Wu Zhiyong,Wang Guanjun,et al.Enhancement of infrared image combined with histogram equalization and fuzzy set theory[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(8):1498-1505(in Chinese)(云海姣,吴志勇,王冠军,等.结合直方图均衡和模糊集理论的红外图像增强[J].计算机辅助设计与图形学学报,2015,27(8):1498-1505)
[3]Wu Di,Zhu Qingsong.The latest research progress of image dehazing[J].Acta Automatica Sinica,2015,41(2):221-239(in Chinese)(吴迪,朱青松.图像去雾的最新研究进展[J].自动化学报,2015,41(2):221-239)
[4]Xiao L M,Li C,Wu Z Z,et al.An enhancement method for X-ray image via fuzzy noise removal and homomorphic filtering[J].Neurocomputing,2016,195:56-64
[5]Liu H T,Lu H Q,Zhang Y.Image enhancement for outdoor long-range surveillance using IQ-learning multiscale Retinex[J].IET Image Processing,2017,11(9):786-795
[6]Ma Zhongli,Wen Jie.Single-scale Retinex sea fog removal algorithm fused the edge information[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(2):217-225(in Chinese)(马忠丽,文杰.融合边缘信息的单尺度Retinex海雾去除算法[J].计算机辅助设计与图形学学报,2015,27(2):217-225)
[7]Mi Z,Zhou H,Zheng Y J,et al.Single image dehazing via multi-scale gradient domain contrast enhancement[J].IET Image Processing,2016,10(3):206-214
[8]Fattal R.Single image dehazing[J].ACM Transactions on Graphics,2008,27(3):Article No.72
[9]Tarel J P,Hautiere N.Fast visibility restoration from a single color or gray level image[C]//Proceedings of the 12th IEEEInternational Conference on Computer Vision.Los Alamitos:IEEE Computer Society Press,2009:2201-2208
[10]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
[11]He K M,Sun J,Tang X O.Guided image filtering[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409
[12]Meng G F,Wang Y,Duan J Y,et al.Efficient image dehazing with boundary constraint and contextual regularization[C]//Proceedings of the IEEE International Conference on Computer Vision.Los Alamitos:IEEE Computer Society Press,2013:617-624
[13]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
[14]Yu Chunyan,Xu Xiaodan,Lin Huixiang,et al.Low-illumination image enhancement method based on a fog-degraded model[J].Journal of Image and Graphics,2017,22(9):1194-1205(in Chinese)(余春艳,徐小丹,林晖翔,等.应用雾天退化模型的低照度图像增强[J].中国图象图形学报,2017,22(9):1194-1205)
[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
[16]Yu Jing,Xu Dongbin,Liao Qingmin.Image defogging:a survey[J].Journal of Image and Graphics,2011,16(9):1561-1576(in Chinese)(禹晶,徐东彬,廖庆敏.图像去雾技术研究进展[J].中国图象图形学报,2011,16(9):1561-1576)
[17]Tan R T.Visibility in bad weather from a single image[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2008:1-8
[18]Bi G L,Ren J Y,Fu T J,et al.Image dehazing based on accurate estimation of transmission in the atmospheric scattering model[J].IEEE Photonics Journal,2017,9(4):Article No.7802918
[19]Nishiyama K,Endo S,Jinno K,et al.Identification of typical synoptic patterns causing heavy rainfall in the rainy season in Japan by a self-organizing map[J].Atmospheric Research,2015,83(2-4):185-200
[20]Zhou Chenxi,Liang Xun,Qi Jinshan.A semi-supervised agglomerative hierarchical clustering method based on dynamically updating constraints[J].Acta Automatica Sinica,2015,41(7):1253-1263(in Chinese)(周晨曦,梁循,齐金山.基于约束动态更新的半监督层次聚类算法[J].自动化学报,2015,41(7):1253-1263)
[21]Kang S H,Sandberg B,Yip A M.A regularized k-means and multiphase scale segmentation[J].Inverse Problems and Imaging,2011,5(2):407-429
[22]Qamar U.A dissimilarity measure based Fuzzy c-means(FCM)clustering algorithm[J].Journal of Intelligent and Fuzzy Systems,2014,26(1):229-238
[23]Li L R,Sang H S,Zhou G,et al.Instant haze removal from a single image[J].Infrared Physics&Technology,2017,83:156-163
[24]Wang J B,He N,Zhang L L,et al.Single image dehazing with a physical model and dark channel prior[J].Neurocomputing,2015,149:718-728
[25]Sulami M,Glatzer I,Fattal R,et al.Automatic recovery of the atmospheric light in hazy images[C]//Proceedings of the IEEEInternational Conference on Computational Photography.Los Alamitos:IEEE Computer Society Press,2014:1-11
[26]Berman D,Treibitz T,Avidan S.Non-local image dehazing[C]//Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEEComputer Society Press,2016:1674-1682
[27]Li Dapeng,Yu Jing,Xiao Chuangbai.No-reference quality assessment method for defogged images[J].Journal of Image and Graphics,2011,16(9):1753-1757(in Chinese)(李大鹏,禹晶,肖创柏.图像去雾的无参考客观质量评测方法[J].中国图象图形学报,2011,16(9):1753-1757)