Polarization Image Restoration Method Based on Sky Region Separation and Adaptive Median Filtering

Abstract

Abstract: This paper proposes an improved method to restore polarization image based on based on sky separation technology in order to solve the problems of traditional polarization image defogging methods, such as inconvenient parameter calculation, noise and color distortion. Firstly, we use the method of image registration fusion to deal with polarization image fusion. Then, we separate the polarized haze image scene and sky region by sky separation technology and calculate the atmospheric light intensity. We optimize the atmospheric scattered light and calculate the image transmission rate by the method of adaptive median filter. Finally, we remove the image haze by the polarized image defogging model. We use the images obtained by SLR camera and KENKO CPL67MM polarizing filters for experimental recovery test. The image restored by the proposed method retains the rich edge details and makes great improvement in the evaluation indexes of information entropy and average gradient ratio. The method effectively improves the quality of haze image, overcomes the noise problem in the sky area, and solves the inconvenience in manual calculation of parameters.

Key words: polarized image restoration, atmospheric physics mode, atmospheric light, transmission map, evaluating indicator

CLC Number:

TP391

PENG Wenzhu. Polarization Image Restoration Method Based on Sky Region Separation and Adaptive Median Filtering[J]. Journal of Qujing Normal University, 2023, 42(3): 33-38.

References

[1]李红莉,张智斌,徐玄冀.基于在线估计的视觉SLAM低光照图像增强算法[J].光电子·激光,2021,32(9):945-952.
[2]郭青山,黄玉清.基于DehazeNet与边缘检测均值引导滤波图像去雾算法[J].传感器与微系统, 2020, 39(1) :150-153.
[3]YU H, LI X, LOU Q, et al. Underwater image enhancement based on color-line model and homomorphic filtering [J]. Signal, Image and Video Processing, 2022, 16(1): 83-91.
[4]聂新蕾,张长胜,钱俊兵.基于非局部先验的雾线优化图像去雾算法[J].光电子·激光,2023,34(2):140-146.
[5]杨燕,张金龙,张浩文.基于区间估计与透射率自适应约束的去雾算法[J].北京航空航天大学学报, 2022, 48(1): 15-26.
[6]杨燕,王志伟.基于均值不等关系优化的自适应图像去雾算法[J].电子与信息学报, 2020, 42(3): 755-763.
[7]QIN X, WANG Z, BAI Y, et al. FFA-Net: Feature fusion attention network for single image dehazing [C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(7): 11908-11915.
[8]ZHAO S,ZHANG L,SHEN Y, et al.RefineDNet: A weakly supervised refinement framework for single image dehazing [J]. IEEE Transactions on Image Processing, 2021, 30: 3391-3404.
[9]SCHECHNER Y Y, NARASIMHAN S G,NAYAR S K. Instant Dehazing of Images Using Polarization [C]// Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR). Kauai: IEEE, 2001: 325-332.
[10]SCHECHNER Y Y,NARASIMHAN S G,NAYAR S K.Polarization-based Vision through Haze [J]. Applied Optics, 2003, 42(3):511-525.
[11]MCCARTHEY E J.Optics of the atmosphere: scattering by molecules and particles [M].New York: John Wiley and Sons, 1976:23-32.
[12]NARASIMHAN S G, NAYAR S K.Vision and the Atmosphere [J]. International Journal of computer vision, 2002, 48(3):233-254.
[13]杨威.基于Stokes矢量的双相机偏振成像技术研究[D].长春:长春理工大学,2021.
[14]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.
[15]YUAN H Z,ZHANG X Q,FENG Z L. Horizon Detection in Foggy Aerial Image [C]// Proceedings of the 2010 International Conference on Image Analysis and Signal Processing. Zhejiang: IEEE, 2010:191-194.
[16]王云艳,周志刚,罗冷坤.基于Sobel算子滤波的图像增强算法[J].计算机应用与软件,2019,36(12):184-188.
[17]张庆鹏,曹宇.一种融合光照和彩色信息的图像匹配算法[J].激光与光电子学进展,2019,56(19):120-126.
[18]张晓玲,许炎,王晓忠,等.基于薄雾偏振特性的图像融合方法[J].厦门大学学报,2011, 50(3):520-524.
[19]TAN R T. Visibility in Bad Weather from a Single Image [C]// 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008: 1-8.
[20]TAREL J P,NICOLAS N. Fast Visibility Restoration from a Single Color or Gray Level Image [C]// Proceedings of 2009 IEEE 12th International Conference on Computer Vision. Kyoto: IEEE, 2009: 2201-2208.
[21]李大鹏,禹晶,肖创柏,等. 图像去雾的无参考客观质量评测方法[J].中国图像图形学报, 2011,16(9):1753-1757.
[22]王振东,靖旭,孙国栋,等.基于区域对比度约束的暗通道图像去雾[J].中国激光,2019,46(8):276-281.