数字图像去雾算法研究
|
摘要
户外空气中经常会有大量的水蒸气和微尘等颗粒物,这些颗粒物会导致光在传输过程中被折射、散射、吸收从而损失大量能量。自然界中的雾、灰霾等天气现象就是由于这种原因而产生的。户外拍摄的图像经常由于雾、灰霾等天气导致场景光在传输过程中能量衰减,图像对比度下降。对有雾图像进行去雾处理提高图像质量是对图像进行进一步处理和利用的必需步骤,具有非常重要的价值。
目前已有的图像去雾算法可以分为两类,一类采用多幅图像或者需要人为提供场景深度信息,这类方法由于需要大量人为提供信息而不具有广泛使用的价值。另一部分去雾算法首先基于暗通道先验知识得到一幅粗糙的图像深度信息图,然后通过进一步滤波来得到精确的深度信息。这类算法能得到较好的去雾效果,但是由于对整幅图像进行滤波,所以耗费时间较长,不能进行实时去雾。
本文主要分析了基于暗通道先验知识的去雾算法,并和其他去雾算法进行对比,在此基础上提出了一种基于暗通道先验知识的实时图像去雾算法。通过分析,我们发现粗糙雾浓度信息图的平滑部分是不需要滤波处理的,只有边缘部分的值由于误差太大而需要滤波处理。在此基础上,本论文提出了一种通过分析粗糙雾浓度信息图和单点暗通道信息图绝对差方法来得到粗糙信息图中需要进一步处理区域的位置信息,然后对这些位置的雾浓度信息重新估计,该方法大大减少了滤波计算量。跟已有算法比较,在保证去雾效果的前提下,该算法比已有算法速度提高28倍以上。
Images of outdoor scenes are usually degraded by the turbid medium (e.g., particles and water droplets) in the atmosphere. Haze, fog and smoke are such phenomena due to atmospheric absorption and scattering. Images of outdoor scenes lose visiblity and contrast due to the presence of atmospheric haze, fog and smoke. Haze removal can significantly increase the visiblity of the scene and correct the color shift caused by the airlight.
We introduced the widely used haze removal methods and make comparative analysis on them. Generally, there are two kinds of haze removal methods:one is relible to additional information and the other is only related to the given hazy image. Since the former one relys on much additional information, it is not pratical in most situations. The recently proposed dark channel prior-based approach can be categorized to the latter one which appears to be the most successful solution and produces the best result in most cases. However, this approach suffers from a complex depth map refinement process, which consumes much computational time.
In this paper, we propose a novel fast depth map approximation method using the dark channel prior. This approximation makes use of the pixel-wise depth map and the observation that most dehazing artifacts occur in the area in which the original estimated depth map has large difference from its pixel-wise depth map. For fast implementation, we simply replace these edge area depth information by the newly estimated depth information. Experiments show that comparing with the original dark channel approach, the proposed new method has a speedup gain of about28or more while at the same time produces similar or better results.
目前已有的图像去雾算法可以分为两类,一类采用多幅图像或者需要人为提供场景深度信息,这类方法由于需要大量人为提供信息而不具有广泛使用的价值。另一部分去雾算法首先基于暗通道先验知识得到一幅粗糙的图像深度信息图,然后通过进一步滤波来得到精确的深度信息。这类算法能得到较好的去雾效果,但是由于对整幅图像进行滤波,所以耗费时间较长,不能进行实时去雾。
本文主要分析了基于暗通道先验知识的去雾算法,并和其他去雾算法进行对比,在此基础上提出了一种基于暗通道先验知识的实时图像去雾算法。通过分析,我们发现粗糙雾浓度信息图的平滑部分是不需要滤波处理的,只有边缘部分的值由于误差太大而需要滤波处理。在此基础上,本论文提出了一种通过分析粗糙雾浓度信息图和单点暗通道信息图绝对差方法来得到粗糙信息图中需要进一步处理区域的位置信息,然后对这些位置的雾浓度信息重新估计,该方法大大减少了滤波计算量。跟已有算法比较,在保证去雾效果的前提下,该算法比已有算法速度提高28倍以上。
Images of outdoor scenes are usually degraded by the turbid medium (e.g., particles and water droplets) in the atmosphere. Haze, fog and smoke are such phenomena due to atmospheric absorption and scattering. Images of outdoor scenes lose visiblity and contrast due to the presence of atmospheric haze, fog and smoke. Haze removal can significantly increase the visiblity of the scene and correct the color shift caused by the airlight.
We introduced the widely used haze removal methods and make comparative analysis on them. Generally, there are two kinds of haze removal methods:one is relible to additional information and the other is only related to the given hazy image. Since the former one relys on much additional information, it is not pratical in most situations. The recently proposed dark channel prior-based approach can be categorized to the latter one which appears to be the most successful solution and produces the best result in most cases. However, this approach suffers from a complex depth map refinement process, which consumes much computational time.
In this paper, we propose a novel fast depth map approximation method using the dark channel prior. This approximation makes use of the pixel-wise depth map and the observation that most dehazing artifacts occur in the area in which the original estimated depth map has large difference from its pixel-wise depth map. For fast implementation, we simply replace these edge area depth information by the newly estimated depth information. Experiments show that comparing with the original dark channel approach, the proposed new method has a speedup gain of about28or more while at the same time produces similar or better results.
引文
[1]阮秋琦.数字图像处理学.电子工业出版社.2001.
[2]Kaiming He, Jian Sun and Xiaoou Tang. Single Image Haze Removal Using Dark Channel Prior. IEEE Transactions on pattern analysis and machine intelligence. VOL.33.2009.
[3]H. Koschmieder, "Theorie der Horizontalen Sichtweite," Beitr. Phys. Freien Atm. vol.12, pp, 171-181,1924.
[4]Y.Y. Schechner, S.G. Narasimhan, and S.K. Nayar, "Instant Dehazing of Images Using Polarization," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol.1, pp.325-332, 2001.
[5]S. Schwartz, E. Namer, and Y.Y Schechner,"Blind Haze Separation,"Proc. IEEE Conf. Computer Vision and Pattern Recognition. vol.2, pp.1984-1991,2006.
[6]S.G. Narasimhan, and S.K. Nayar, "Chromatic Framework for Vision in Bad Weather," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol.1, pp.598-605, June 2000.
[7]S.K. Nayar and S.G. Narasimhan, "Vision in Bad Weather." Proc. Seventh IEEE Int'l Conf. Computer Vision, vol.2, pp.820-827,1999.
[8]S.G. Narasimhan and S.K. Nayar, "Vision and the Atmosphere," Int'l J. Computer Vision, vol. 48, pp.233-254,2002.
[9]S.G. Narasimhan and S.G. Nayar, "Contrast Restoration of Weather Degraded Images," IEEE Trans. Pattern Analysis and Machine Intelligence, vol.25, no.6 pp.713-724, June 2003.
[10]J. Kopf, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uyttendaele, and D. Lischinski, "Deep Photo:Model-Based Photograph Enhancement and Viewing," ACM Trans. Graphics, vol.27, no.5, pp.116:1-116:10,2008.
[11]S.G. Narasimhan and S.K. Nayar, "Interactive Deweathering of an Image Using Physical Models," Proc. IEEE Workshop Color and Photometric Methods in Computer Vision, in Conjunction with IEEE Int'l Conf. Computer Vision, Oct.2003.
[12]R. Fattal, "Single Image Dehazing," Proc. ACM SIGGRAPH'08,2008.
[13]R. Tan, "Visiblity in Bad Weather from a Single Image," Proc. IEEE Conf. Computer Vision and Pattern Recognition, June.2008.
[14]K. He, J. Sun and X. Tang, "Single Linage Haze Removal Using Dark Channel Prior," IEEE Conference on Computer Vision and Pattern Recognition,2009.
[15]E.J. McCartney, "Optics of Atmosphere:Scattering by Molecules and Particles," New York: John Wiley and Sons, pp.23-32,1976.
[16]M. Van Herk, "A Fast Algorithm for Local Minimum and Maximum Filters on Rectangular and Octagonal Kernels," Pattern Recognition Letters, vol.13, pp.517-521,1992.
[17]C. Tomasi and R. Manduchi, "Bilateral Filtering for Gray and Color Images," Proc. Sixth IEEE Int'l Conf. Computer Vision, p.839,1998.
[18]A. Levin, D. Lischinski, and Y. Weiss, "A Closed Form Solution to Natural Image Matting," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol.1, pp.61-68,2006.
[19]A. J. Preetham, P. Schirley, and B. Smits, "A Practical Analytic Model for Daylight," Proc. ACM SIGGRAPH'99,1999.
[20]P. Chave, "An Improved Dark-Object Subtraction Technique for Atmospheric Scattering Correction of Multispectral Data," Remote Sensing of Environment, vol.24, pp.450-479, 1988.
[2]Kaiming He, Jian Sun and Xiaoou Tang. Single Image Haze Removal Using Dark Channel Prior. IEEE Transactions on pattern analysis and machine intelligence. VOL.33.2009.
[3]H. Koschmieder, "Theorie der Horizontalen Sichtweite," Beitr. Phys. Freien Atm. vol.12, pp, 171-181,1924.
[4]Y.Y. Schechner, S.G. Narasimhan, and S.K. Nayar, "Instant Dehazing of Images Using Polarization," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol.1, pp.325-332, 2001.
[5]S. Schwartz, E. Namer, and Y.Y Schechner,"Blind Haze Separation,"Proc. IEEE Conf. Computer Vision and Pattern Recognition. vol.2, pp.1984-1991,2006.
[6]S.G. Narasimhan, and S.K. Nayar, "Chromatic Framework for Vision in Bad Weather," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol.1, pp.598-605, June 2000.
[7]S.K. Nayar and S.G. Narasimhan, "Vision in Bad Weather." Proc. Seventh IEEE Int'l Conf. Computer Vision, vol.2, pp.820-827,1999.
[8]S.G. Narasimhan and S.K. Nayar, "Vision and the Atmosphere," Int'l J. Computer Vision, vol. 48, pp.233-254,2002.
[9]S.G. Narasimhan and S.G. Nayar, "Contrast Restoration of Weather Degraded Images," IEEE Trans. Pattern Analysis and Machine Intelligence, vol.25, no.6 pp.713-724, June 2003.
[10]J. Kopf, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uyttendaele, and D. Lischinski, "Deep Photo:Model-Based Photograph Enhancement and Viewing," ACM Trans. Graphics, vol.27, no.5, pp.116:1-116:10,2008.
[11]S.G. Narasimhan and S.K. Nayar, "Interactive Deweathering of an Image Using Physical Models," Proc. IEEE Workshop Color and Photometric Methods in Computer Vision, in Conjunction with IEEE Int'l Conf. Computer Vision, Oct.2003.
[12]R. Fattal, "Single Image Dehazing," Proc. ACM SIGGRAPH'08,2008.
[13]R. Tan, "Visiblity in Bad Weather from a Single Image," Proc. IEEE Conf. Computer Vision and Pattern Recognition, June.2008.
[14]K. He, J. Sun and X. Tang, "Single Linage Haze Removal Using Dark Channel Prior," IEEE Conference on Computer Vision and Pattern Recognition,2009.
[15]E.J. McCartney, "Optics of Atmosphere:Scattering by Molecules and Particles," New York: John Wiley and Sons, pp.23-32,1976.
[16]M. Van Herk, "A Fast Algorithm for Local Minimum and Maximum Filters on Rectangular and Octagonal Kernels," Pattern Recognition Letters, vol.13, pp.517-521,1992.
[17]C. Tomasi and R. Manduchi, "Bilateral Filtering for Gray and Color Images," Proc. Sixth IEEE Int'l Conf. Computer Vision, p.839,1998.
[18]A. Levin, D. Lischinski, and Y. Weiss, "A Closed Form Solution to Natural Image Matting," Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol.1, pp.61-68,2006.
[19]A. J. Preetham, P. Schirley, and B. Smits, "A Practical Analytic Model for Daylight," Proc. ACM SIGGRAPH'99,1999.
[20]P. Chave, "An Improved Dark-Object Subtraction Technique for Atmospheric Scattering Correction of Multispectral Data," Remote Sensing of Environment, vol.24, pp.450-479, 1988.