基于高斯权重衰减的迭代优化去雾算法
|
摘要
针对暗通道先验算法最小滤波使用的不足,提出一种基于高斯权重衰减的迭代优化去雾方法.该方法首先利用Kirsch算子滤波构造高斯函数逼近暗通道操作,然后用交叉双边滤波消除纹理效应,其次,在透射率为最优的前提下,利用高斯暗通道来简化大气散射模型,从而得到粗略透射率;为了得到最优透射率,使用Kirsch和Laplacian算子构成的一组高阶滤波器进行迭代处理,从而获得最优效果;最后,结合大气散射模型复原无雾图像.通过大量实验测试验证,所提假设成立,复原的图像细节明显,明亮度适宜,并且在客观评价中也体现出了优势.
Aiming at the shortcoming of the minimum filtering of dark channel prior algorithm, an iterative optimization defogging algorithm using the Gaussian weight decay is proposed. This method uses the Kirsch operator to construct a Gaussian function to approximate the dark channel operation and eliminate the texture effect by cross-bilateral filters.Secondly, under the optimal transmission, the proposed Gaussian dark channel is used to simplify the atmospheric scattering model to result in a rough transmission. In order to obtain the optimal transmission, a set of high-order filters composed of Kirsch and Laplacian operators are used to iterate towards the optimal effect. Finally, the atmospheric scattering model is used to recover the haze free image. Through a large number of experimental tests it is verified that the proposed hypothesis is valid and restoration of image details is obvious, bright and appropriate. Moreover, it also performs well in the objective evaluation.
Aiming at the shortcoming of the minimum filtering of dark channel prior algorithm, an iterative optimization defogging algorithm using the Gaussian weight decay is proposed. This method uses the Kirsch operator to construct a Gaussian function to approximate the dark channel operation and eliminate the texture effect by cross-bilateral filters.Secondly, under the optimal transmission, the proposed Gaussian dark channel is used to simplify the atmospheric scattering model to result in a rough transmission. In order to obtain the optimal transmission, a set of high-order filters composed of Kirsch and Laplacian operators are used to iterate towards the optimal effect. Finally, the atmospheric scattering model is used to recover the haze free image. Through a large number of experimental tests it is verified that the proposed hypothesis is valid and restoration of image details is obvious, bright and appropriate. Moreover, it also performs well in the objective evaluation.
引文
1 Xu Y, Wen J, Fei L K, Zhang Z. Review of video and image defogging algorithms and related studies on image restoration and enhancement. In:Proceedings of the IEEE 2016Access. 2016, 4:165-188
2 Yang Yan, Chen Gao-Ke. Single image visibility restoration using optical compensation and pixel-by-pixel transmission estimation. Journal on Communications, 2017, 38(5):48-56(杨燕,陈高科.基于光补偿和逐像素透射率的图像复原算法.通信学报, 2017, 38(5):48-56)
3 He L Y, Zhao J Z, Zheng N N, Bi D Y. Haze removal using the difference-structure-preservation prior. IEEE Transactions on Image Processing, 2017, 26(3):1063-1075
4 He K M, Sun J, Tang X O. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353
5 Ancuti C O, Ancuti C. Single image dehazing by multiscale fusion. IEEE Transactions on Image Processing, 2013,22(8):3271-3282
6 Tan R T. Visibility in bad weather from a single image. In:Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA:IEEE,2008. 1-8
7 Fattal R. Single image dehazing. ACM Transactions on Graphics, 2008, 27(3):Article No. 72
8 Meng G F, Wang Y, Duan J Y, Xiang S M, Pan C H. Efficient image dehazing with boundary constraint and contextual regularization. In:Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney, NSW,Australia:IEEE, 2013. 617-624
9 Sun W, Wang H, Sun C H, Guo B L, Jia W Y, Sun M G. Fast single image haze removal via local atmospheric light veil estimation. Computers and Electrical Engineering, 2015, 46:371-383
10 He K M, Sun J, Tang X O. Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence,2013, 35(6):1397-1409
11 Sulami M, Glatzer I, Fattal R, Werman M. Automatic recovery of the atmospheric light in hazy images. In:Proceedings of the 2014 IEEE International Conference on Computational Photography. Santa Clara, CA, USA:IEEE, 2014:1-11
12 Zhu Q S, Mai J M, Shao L. A fast single image haze removal algorithm using color attenuation prior. IEEE Transactions on Image Processing, 2015, 24(11):3522-3533
13 Cai B L, Xu X M, Jia K, Qing C M, Tao D C. Dehaze Net:an end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 2016,25(11):5187-5198
14 Ren W Q, Liu S, Zhang H, Pan J S, Cao X C, Yang M H. Single image dehazing via multi-scale convolutional neural networks. In:Proceedings of the 2016 Computer Vision,Lecture Notes in Computer Science, 2016, 9906:154-164
15 Wang Z, Bovik A C, Sheikh H R. Structural similarity based image quality assessment. Digital Video Image Quality and Perceptual Coding. Boca Raton, FL:CRC Press, 2005.
16 Hauti′ere N, Tarel J P, Aubert D, Dumont′E. Blind contrast enhancement assessment by gradient ratioing at visible edges. Image Analysis and Stereology Journal, 2008, 27(2):87-95
2 Yang Yan, Chen Gao-Ke. Single image visibility restoration using optical compensation and pixel-by-pixel transmission estimation. Journal on Communications, 2017, 38(5):48-56(杨燕,陈高科.基于光补偿和逐像素透射率的图像复原算法.通信学报, 2017, 38(5):48-56)
3 He L Y, Zhao J Z, Zheng N N, Bi D Y. Haze removal using the difference-structure-preservation prior. IEEE Transactions on Image Processing, 2017, 26(3):1063-1075
4 He K M, Sun J, Tang X O. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353
5 Ancuti C O, Ancuti C. Single image dehazing by multiscale fusion. IEEE Transactions on Image Processing, 2013,22(8):3271-3282
6 Tan R T. Visibility in bad weather from a single image. In:Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA:IEEE,2008. 1-8
7 Fattal R. Single image dehazing. ACM Transactions on Graphics, 2008, 27(3):Article No. 72
8 Meng G F, Wang Y, Duan J Y, Xiang S M, Pan C H. Efficient image dehazing with boundary constraint and contextual regularization. In:Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney, NSW,Australia:IEEE, 2013. 617-624
9 Sun W, Wang H, Sun C H, Guo B L, Jia W Y, Sun M G. Fast single image haze removal via local atmospheric light veil estimation. Computers and Electrical Engineering, 2015, 46:371-383
10 He K M, Sun J, Tang X O. Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence,2013, 35(6):1397-1409
11 Sulami M, Glatzer I, Fattal R, Werman M. Automatic recovery of the atmospheric light in hazy images. In:Proceedings of the 2014 IEEE International Conference on Computational Photography. Santa Clara, CA, USA:IEEE, 2014:1-11
12 Zhu Q S, Mai J M, Shao L. A fast single image haze removal algorithm using color attenuation prior. IEEE Transactions on Image Processing, 2015, 24(11):3522-3533
13 Cai B L, Xu X M, Jia K, Qing C M, Tao D C. Dehaze Net:an end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 2016,25(11):5187-5198
14 Ren W Q, Liu S, Zhang H, Pan J S, Cao X C, Yang M H. Single image dehazing via multi-scale convolutional neural networks. In:Proceedings of the 2016 Computer Vision,Lecture Notes in Computer Science, 2016, 9906:154-164
15 Wang Z, Bovik A C, Sheikh H R. Structural similarity based image quality assessment. Digital Video Image Quality and Perceptual Coding. Boca Raton, FL:CRC Press, 2005.
16 Hauti′ere N, Tarel J P, Aubert D, Dumont′E. Blind contrast enhancement assessment by gradient ratioing at visible edges. Image Analysis and Stereology Journal, 2008, 27(2):87-95
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |