单张图像去雾研究
|
摘要
户外的摄影以及一些计算机视觉任务常常会受到恶劣天气的影响。在几乎任何一个户外场景中,从物体表面反射的光线,在到达相机之前,都会或多或少被空气散射所影响。这主要是因为空气中悬浮着许多小颗粒,比如尘埃,小水滴,烟雾颗粒等,这些颗粒的存在改变了光线原本的传播过程。在远距离或者有雾场景中进行摄影时,这个过程对形成的图像有着不可忽视的影响,直接导致图像的可辨性降低,并且使远处物体的表面模糊褪色。本文提出了基于单张图像的快速去雾算法,可以简单高效地去除雾效果。对于输入的一幅有雾图像,利用一个线性模型对成像过程建模,并且估算出全局的环境光,然后从基于单个像素以及邻域信息两个思路出发计算图像的光线传输率,并利用像素饱和度将其结合,为了去除计算过程中的块状效应以及边缘处的光晕痕迹,再用一个交义双边滤波器来平滑传输率,最后根据平滑后的传输率恢复无雾图像。由十整个过程的并行性非常好,可以借助于图形处理器的硬件加速从而达到实时应用的目的。与其他现有方法相比,我们的方法可以得出相似或者更优的结果,所需的处理时间却少得多。这种方法可以进一步应用于户外监控,遥感系统,以及智能交通等领域。此外,场景的深度信息也可以作为副产品得到。
Outdoor photography and some computer vision tasks often suffer from bad weather conditions, observed objects lose visibility and contrast due to the presence of atmospheric haze, fog, and smoke. Here we propose a new method for real-time image dehazing. Based on a linear haze imaging model, for a single input image, we can esti-mate the global atmospheric light and extract the scene objects transmission from both single pixel and patch, and then combined by pixel saturation. To prevent artifacts, we refine the transmission using a cross-bilateral filter, and finally the haze-free frame can be restored. The whole process is highly parallelized, and can be easily implemented on modern GPUs to achieve real-time performance. Comparing with existing methods, our approach provides similar or better results with much less processing time. The proposed method can be further used for many applications such as outdoor surveil-lance, remote sensing, and intelligent vehicles. In addition, rough depth information of the scene can be obtained as a by-product.
Outdoor photography and some computer vision tasks often suffer from bad weather conditions, observed objects lose visibility and contrast due to the presence of atmospheric haze, fog, and smoke. Here we propose a new method for real-time image dehazing. Based on a linear haze imaging model, for a single input image, we can esti-mate the global atmospheric light and extract the scene objects transmission from both single pixel and patch, and then combined by pixel saturation. To prevent artifacts, we refine the transmission using a cross-bilateral filter, and finally the haze-free frame can be restored. The whole process is highly parallelized, and can be easily implemented on modern GPUs to achieve real-time performance. Comparing with existing methods, our approach provides similar or better results with much less processing time. The proposed method can be further used for many applications such as outdoor surveil-lance, remote sensing, and intelligent vehicles. In addition, rough depth information of the scene can be obtained as a by-product.
引文
[1]J. Chen, S. Paris, and F. Durand. Real-time edge-aware image processing with the bilateral grid. SIGGRAPH,2007.
[2]Yong Du, B. Guindon, and J. Cihlar. Haze detection and removal in high resolu-tion satellite image with wavelet analysis. Geoscience and Remote Sensing, IEEE Transactions on,40(1):210-217, January 2002.
[3]E. Eisemann and F. Durand. Flash photography enhancement via intrinsic relight-ing. SIGGRAPH,2004.
[4]M. Elad. On the bilateral filter and ways to improve it. IEEE Transactions On Image Processing,11:1141-1151,2002.
[5]R. Fattal. Single image dehazing. SIGGRAPH, pages 1-9,2008.
[6]Raanan Fattal, Maneesh Agrawala, and Szymon Rusinkiewicz. Multiscale shape and detail enhancement from multi-light image collections. SIGGRAPH,26, July 2007.
[7]K. He, J. Sun, and X. Tang. Guided image filtering. ECCV, pages 1-14,2010.
[8]Kaiming He, Jian Sun, and Xiaoou Tang. Single image haze removal using dark channel prior. IEEE Conference on Computer Vision and Pattern Recognition, 2009.
[9]A. Hyvrinen. Independent component analysis:Algorithms and applications. Neural Networks,13:411-430.,2000.
[10]Pat S. Chavez Jr. An improved dark-object subtraction technique for atmo-spheric scattering correction of multispectral data. Remote Sensing of Environ-ment,24(3):459-479,1988.
[11]J. Kopf, B. Neubert, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uytten-daele, and D. Lischinski. Deep photo:Model-based photograph enhancement and viewing. SIGGRAPH Asia,2008.
[12]H. Koschmieder. Theorie der horizontalen sichtweite. Beitr.Phys.Freien Atm., 12:171-181,1924.
[13]G.W. Larson, H. Rushmeier, and C. Piatko. A visibility matching tone reproduc-tion operator for high dynamic range scenes. Visualization and Computer Graph-ics, IEEE Transactions on,3(4):291-306,1997.
[14]A. Levin, D. Lischinski, and Y. Weiss. A closed form solution to natural image matting. IEEE Conference on Computer Vision and Pattern Recognition,1:61-68, 2006.
[15]A. Levin, R.Fergus, F. Durand, and W. T. Freeman. Image and depth from a conventional camera with a coded aperture. SIGGRAPH,26:70,2007.
[16]Ce Liu, William T. Freeman, Richard Szeliski, and Sing Bing Kang. Noise esti-mation from a single image. In IEEE Conference on Computer Vision and Pattern Recognition, pages 901-908, Washington, DC, USA,2006. IEEE Computer Soci-ety.
[17]Xingyong Lv, Wenbin Chen, and I-fan Shen. Real-time dehazing for image and video. In Proceedings of the 201018th Pacific Conference on Computer Graphics and Applications, PACIFIC GRAPHICS, pages 62-69, Washington, DC, USA, 2010. IEEE Computer Society.
[18]S. Narasimhan and S. Nayar. Interactive deweathering of an image using physical models. Workshop on Color and Photometric Methods in Computer Vision,2003.
[19]S.K. Nayar and S.G. Narasimhan. Vision in bad weather. In IEEE International Conference on Computer Vision,1999.
[20]J.P. Oakley and Hong Bu. Correction of simple contrast loss in color images. Image Processing, IEEE Transactions on,16(2):511-522,2007.
[21]S. Paris and F. Durand. A fast approximation of the bilateral filter using a signal processing approach. Europeon Conference on Computer Vision,2006.
[22]P. Perez. Markov random fields and images. CWI Quarterly,11:413-437,1998.
[23]G. Petschnigg, M. Agrawala, H. Hoppe, R. Szeliski, M. Cohen, and K. Toyama. Digital photography with flash and no-flash image pairs. SIGGRAPH,2004.
[24]T.Q. Pham and L.J. van Vliet. Separable bilateral filtering for fast video prepro-cessing. In Multimedia and Expo, IEEE International Conference on, page 4 pp., 2005.
[25]A. J. Preetham, Peter Shirley, and Brian Smits. A practical analytic model for daylight. In Proceedings of the 26th annual conference on Computer graphics and interactive techniques, SIGGRAPH'99, pages 91-100, New York, NY, USA, 1999. ACM Press/Addison-Wesley Publishing Co.
[26]Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar. Instant dehazing of images using polarization. IEEE Conference on Computer Vision and Pattern Recogni-tion, pages 1-325,2001.
[27]Yoav Y. Schechner and Yuval Averbuch. Regularized image recovery in scat-tering media. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29:1655-1660,2007.
[28]S. Shwartz, E. Namer, and Y.Y. Schechner. Blind haze separation. In Computer Vision and Pattern Recognition,2006.
[29]Kokkeong Tan and J.P. Oakley. Enhancement of color images in poor visibility conditions. In International Conference on Image Processing, volume 2, pages 788-791 vol.2,2000.
[30]R. Tan. Visibility in bad weather from a single image. IEEE Conference on Computer Vision and Pattern Recognition,2008.
[31]Jean-Philippe Tarel and Nicolas Hautiere. Fast visibility restoration from a single color or gray level image. International Comference on Computer Vision, pages 2201-2208,2009.
[32]C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images. Inter-national Comference on Computer Vision, pages 839-846,1998.
[33]M. van Herk. A fast algorithm for local minimum and maximum filters on rectan-gular and octagonal kernels. Pattern Recogn. Lett.,13:517-521,1992.
[34]M. C. W. van Rossum and Th. M. Nieuwenhuizen. Multiple scattering of classical waves:microscopy, mesoscopy, and diffusion. Rev. Mod. Phys.,71(1):313-371, Jan 1999.
[35]A. Veeraraghavan, R. Raskar, A. Agrawal, A. Mohan, and J. Tumblin. Dappled photography:mask enhanced cameras for heterodyned light fields and coded aper-ture refocusing. SIGGRAPH,26:69,2007.
[36]Q. Yang, K. H. Tan, and N. Ahuja. Real-time o(1) bilateral filtering. IEEE Con-ference on Computer Vision and Pattern Recognition,2009.
[37]Lu Yuan, Jian Sun, Long Quan, and Heung-Yeung Shum. Image deblurring with blurred/noisy image pairs. SIGGRAPH,26, July 2007.
[38]Y. Zhang, B. Guindon, and J. Cihlar. An image transform to characterize and compensate for spatial variations in thin cloud contamination of landsat images. Remote Sensing of Environment,82(2-3):173-187,2002.
[2]Yong Du, B. Guindon, and J. Cihlar. Haze detection and removal in high resolu-tion satellite image with wavelet analysis. Geoscience and Remote Sensing, IEEE Transactions on,40(1):210-217, January 2002.
[3]E. Eisemann and F. Durand. Flash photography enhancement via intrinsic relight-ing. SIGGRAPH,2004.
[4]M. Elad. On the bilateral filter and ways to improve it. IEEE Transactions On Image Processing,11:1141-1151,2002.
[5]R. Fattal. Single image dehazing. SIGGRAPH, pages 1-9,2008.
[6]Raanan Fattal, Maneesh Agrawala, and Szymon Rusinkiewicz. Multiscale shape and detail enhancement from multi-light image collections. SIGGRAPH,26, July 2007.
[7]K. He, J. Sun, and X. Tang. Guided image filtering. ECCV, pages 1-14,2010.
[8]Kaiming He, Jian Sun, and Xiaoou Tang. Single image haze removal using dark channel prior. IEEE Conference on Computer Vision and Pattern Recognition, 2009.
[9]A. Hyvrinen. Independent component analysis:Algorithms and applications. Neural Networks,13:411-430.,2000.
[10]Pat S. Chavez Jr. An improved dark-object subtraction technique for atmo-spheric scattering correction of multispectral data. Remote Sensing of Environ-ment,24(3):459-479,1988.
[11]J. Kopf, B. Neubert, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uytten-daele, and D. Lischinski. Deep photo:Model-based photograph enhancement and viewing. SIGGRAPH Asia,2008.
[12]H. Koschmieder. Theorie der horizontalen sichtweite. Beitr.Phys.Freien Atm., 12:171-181,1924.
[13]G.W. Larson, H. Rushmeier, and C. Piatko. A visibility matching tone reproduc-tion operator for high dynamic range scenes. Visualization and Computer Graph-ics, IEEE Transactions on,3(4):291-306,1997.
[14]A. Levin, D. Lischinski, and Y. Weiss. A closed form solution to natural image matting. IEEE Conference on Computer Vision and Pattern Recognition,1:61-68, 2006.
[15]A. Levin, R.Fergus, F. Durand, and W. T. Freeman. Image and depth from a conventional camera with a coded aperture. SIGGRAPH,26:70,2007.
[16]Ce Liu, William T. Freeman, Richard Szeliski, and Sing Bing Kang. Noise esti-mation from a single image. In IEEE Conference on Computer Vision and Pattern Recognition, pages 901-908, Washington, DC, USA,2006. IEEE Computer Soci-ety.
[17]Xingyong Lv, Wenbin Chen, and I-fan Shen. Real-time dehazing for image and video. In Proceedings of the 201018th Pacific Conference on Computer Graphics and Applications, PACIFIC GRAPHICS, pages 62-69, Washington, DC, USA, 2010. IEEE Computer Society.
[18]S. Narasimhan and S. Nayar. Interactive deweathering of an image using physical models. Workshop on Color and Photometric Methods in Computer Vision,2003.
[19]S.K. Nayar and S.G. Narasimhan. Vision in bad weather. In IEEE International Conference on Computer Vision,1999.
[20]J.P. Oakley and Hong Bu. Correction of simple contrast loss in color images. Image Processing, IEEE Transactions on,16(2):511-522,2007.
[21]S. Paris and F. Durand. A fast approximation of the bilateral filter using a signal processing approach. Europeon Conference on Computer Vision,2006.
[22]P. Perez. Markov random fields and images. CWI Quarterly,11:413-437,1998.
[23]G. Petschnigg, M. Agrawala, H. Hoppe, R. Szeliski, M. Cohen, and K. Toyama. Digital photography with flash and no-flash image pairs. SIGGRAPH,2004.
[24]T.Q. Pham and L.J. van Vliet. Separable bilateral filtering for fast video prepro-cessing. In Multimedia and Expo, IEEE International Conference on, page 4 pp., 2005.
[25]A. J. Preetham, Peter Shirley, and Brian Smits. A practical analytic model for daylight. In Proceedings of the 26th annual conference on Computer graphics and interactive techniques, SIGGRAPH'99, pages 91-100, New York, NY, USA, 1999. ACM Press/Addison-Wesley Publishing Co.
[26]Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar. Instant dehazing of images using polarization. IEEE Conference on Computer Vision and Pattern Recogni-tion, pages 1-325,2001.
[27]Yoav Y. Schechner and Yuval Averbuch. Regularized image recovery in scat-tering media. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29:1655-1660,2007.
[28]S. Shwartz, E. Namer, and Y.Y. Schechner. Blind haze separation. In Computer Vision and Pattern Recognition,2006.
[29]Kokkeong Tan and J.P. Oakley. Enhancement of color images in poor visibility conditions. In International Conference on Image Processing, volume 2, pages 788-791 vol.2,2000.
[30]R. Tan. Visibility in bad weather from a single image. IEEE Conference on Computer Vision and Pattern Recognition,2008.
[31]Jean-Philippe Tarel and Nicolas Hautiere. Fast visibility restoration from a single color or gray level image. International Comference on Computer Vision, pages 2201-2208,2009.
[32]C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images. Inter-national Comference on Computer Vision, pages 839-846,1998.
[33]M. van Herk. A fast algorithm for local minimum and maximum filters on rectan-gular and octagonal kernels. Pattern Recogn. Lett.,13:517-521,1992.
[34]M. C. W. van Rossum and Th. M. Nieuwenhuizen. Multiple scattering of classical waves:microscopy, mesoscopy, and diffusion. Rev. Mod. Phys.,71(1):313-371, Jan 1999.
[35]A. Veeraraghavan, R. Raskar, A. Agrawal, A. Mohan, and J. Tumblin. Dappled photography:mask enhanced cameras for heterodyned light fields and coded aper-ture refocusing. SIGGRAPH,26:69,2007.
[36]Q. Yang, K. H. Tan, and N. Ahuja. Real-time o(1) bilateral filtering. IEEE Con-ference on Computer Vision and Pattern Recognition,2009.
[37]Lu Yuan, Jian Sun, Long Quan, and Heung-Yeung Shum. Image deblurring with blurred/noisy image pairs. SIGGRAPH,26, July 2007.
[38]Y. Zhang, B. Guindon, and J. Cihlar. An image transform to characterize and compensate for spatial variations in thin cloud contamination of landsat images. Remote Sensing of Environment,82(2-3):173-187,2002.