基于大气多散射模型和超像素分割的图像去雾

王睿; 李蕊; 廉小亲

doi:doi:10.3788/gzxb20164504.0410002

光子学报, 2016, 45 (4): 0410002, 网络出版: 2016-05-11

基于大气多散射模型和超像素分割的图像去雾

Multiple Scattering Model Based Image Dehazing with Superpixel

论文大纲

王睿 ^1,*李蕊 ¹廉小亲 ²

作者单位

¹ 北京航空航天大学仪器科学与光电工程学院，北京 100191

² 北京工商大学计算机与信息工程学院北京 100048

摘要

通过分析大气粒子对光线的多次散射作用，利用大气点扩散函数作为卷积核，基于暗原色图像复原理论，建立了基于多次散射的雾天成像模型，并以函数形状相似性为依据，利用广义高斯分布定量估计出大气点扩散函数核函数在图像域下的相关参数.针对传统暗原色理论以固定大小图像区域估计透射率的不足，提出了基于超像素分割获得景深一致的图像分块方案，通过区域合并，获得更为精准的天空检测效果；基于暗原色先验理论分别估计天空和非天空区域的透射率，并对天空区域的透射率进行修正，不但减少了天空色彩失真，同时也消除了复原结果的光晕现象.本文从主观和客观两个方面将所提出的去雾方法和其他算法进行了对比，结果表明，本文提出的去雾算法能够在较短的运行时间内获得对比度较高、细节信息丰富的去雾结果，具有较好的鲁棒性.

Abstract

The formation pattern of hazy image based on multiple scattering, which is described by atmosphere point spread function (APSF), is modeled. The generalized Gaussian distribution was adopted to approximately formula the expression for APSF through the similarity in the shape and proper convolution operation. Aiming at enhancing the quality with reasonable time consuming, an improved dehazing method was proposed based on dark channel prior (DCP). The approach applies the superpixel algorithm to obtain image patches with similar depth for halo prevention, and based on this, the sky region was also detected more accurately by region merging. Therefore the transmission on the sky and non-sky region was separately estimated, the color distortion reduction in the sky region was achieved. Experimental results show that the proposed method can robustly recover a high-quality haze-free image with abundant details from both subjective and objective image-quality assessment.

参考文献

[1] 郭璠. 图像去雾方法和评价及其应用研究［D］. 长沙：中南大学, 2012: 10-15.

GUO Fan. Research on image defogging effect assessment and application［D］. Changsha: Central South University, 2012: 10-15.

[2] 庞春颖, 嵇晓强, 孙丽娜, 等. 一种改进的图像快速去雾新方法［J］. 光子学报,2013, 42(7): 872-877.

PANG Chun-ying, JI Xiao-qiang, SUN Li-na, et al. An improved method of image fast defogging［J］. Acta Photonica Sinica, 2013, 42(7): 872-877.

[3] 毕笃彦，葛渊, 李权合, 等. 单幅图像去雾方法研究［J］. 空军工程大学学报, 2013, 14(6): 46-53.

BI Du-yan, GE Yuan. A research on defogging methods with single image［J］. Journal of Air Force Engineering University, 2013, 14(6): 46-53.

[4] TAN R. Visibility in bad weather from a single image［C］. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Alaska, USA, 2008, 1-8.

[5] FATTAL R. Single image dehazing［J］. ACM Transactions on Graphics, 2008, 27(3): 1-9.

[6] HE Kai-ming, SUN Jian, TANG Xiao-ou. Single image haze removal using dark channel prior［C］. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009: 1956-1963.

[7] TAREL J P, HAUTIERE N. Fast visibility restoration from a single color or gray level image［C］. Proceedings of IEEE Conference on International Conference on Computer Vision, Kyoto, Japan, 2009, 10: 20-28.

[8] HE Kai-ming, SUN Jian, TANG Xiao-ou. Guided image filtering［C］. Proceedings of the 11th European Conference on Computer Vision, Heraklion, Greece, 2010: 1-14.

[9] 嵇晓强. 图像快速去雾与清晰度恢复技术研究［D］. 长春：中国科学院研究生院（长春光学精密机械与物理研究所）, 2012: 16-18.

JI xiao-qiang. Research on fast image defogging and visibility restoration［D］. Chang Chun: Changchun Institute of Optics, Fine Mechanics and Physics, 2012: 16-18.

[10] 刘楠, 程咏梅, 赵永强. 基于加权暗通道的图像去雾方法［J］. 光子学报, 2012, 41(3): 320-325.

LIU Nan, CHENG Yong-mei, ZHAO Yong-qiang. An image dehazing method based on weighted dark channel prior［J］. Acta Photonica Sinica, 2012, 41(3): 320-325.

[11] 李权合, 毕笃彦, 许悦雷, 等. 雾霾天气下可见光图像场景再现［J］. 自动化学报, 2014, 40(04): 744-750.

LI Quan-he, BI Du-yan, XU Yue-lei, et al. Haze degraded image scene rendition［J］. Acta Automatica Sinica, 2014, 40(04): 744-750.

[12] GAO Yuan-yuan, HU Hai-miao, WANG Shu-hang, et al. A fast image dehazing algorithm based on negative correction［J］. Signal Processing, 2014, 103(2014): 380-398.

[13] HAUTIèRE N, TAREL J, AUBERT D, et al. Blind contrast restoration assessment by gradient rationing at visible edges［J］.Image Analysis and Stereology, 2008, 27(2): 87-95.

[14] 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(09): 1753-1757.

LI Da-peng, YU Jing, XIAO Chuang-bo. No-reference quality assessment method for defogged images［J］. Journal of Image and Graphics, 2011, 16(09): 1753-1757.

[15] 陶叔银. 基于大气物理特征的光学图像退化及补偿技术研究［D］. 浙江: 浙江大学, 2014: 20-35.

TAO Shu-yin. Research on image degradation and recovery based on physical properties of atmosphere［D］. Zhejiang: Zheiiang University, 2014: 20-35.

[16] MAHALATI R N, KAHN J M. Effect of fog on free-space optical links employing imaging receivers［J］. Optics Express, 2012, 20(2): 1649-1661.

[17] METARI S, DESCHENES F. A new convolution kernel for atmospheric point spread function applied to computer vision［C］. Proceedings of IEEE International Conference On Computer Vision, Rio De Janeiro, Brazil, 2007, 1-8.

[18] 陈露, 和红杰, 陈帆. 基于边界邻域最大值滤波的快速图像去雾算法［J］. 光子学报, 2014, 43(11): 1-6.

CHEN Lu, HE Hong-jie, CHEN Fan. A fast image defogging algorithm based on edge-maximum filter［J］. Acta Photonica Sinica, 2014, 43(11): 1-6.

[19] ACHANTA R, SHAJI A, SMITH K, ET AL. SLIC superpixels compared to state-of-the-art superpixel methods［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.

[20] SAXENA A, CHUNG S H, NG A Y. 3-d depth reconstruction from a single still image［J］. International Journal of Computer Vision, 2008, 76(1): 53-69.

[21] SUN W, GUO B L, LI D J, ET AL. A fast single-image dehazing method for visible-light systems［J］. Optical Engineering, 2013, 52(9): 1-10.

王睿, 李蕊, 廉小亲. 基于大气多散射模型和超像素分割的图像去雾[J]. 光子学报, 2016, 45(4): 0410002. WANG Rui, LI Rui, LIAN Xiao-qin. Multiple Scattering Model Based Image Dehazing with Superpixel[J]. ACTA PHOTONICA SINICA, 2016, 45(4): 0410002.

基于大气多散射模型和超像素分割的图像去雾

关于本站 Cookie 的使用提示

全站搜索

基于大气多散射模型和超像素分割的图像去雾

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索