混合残差学习与导向滤波算法在图像去雾中的应用

陈清江; 张雪

doi:doi:10.3788/ope.20192712.2702

光学精密工程, 2019, 27 (12): 2702, 网络出版: 2020-05-12

混合残差学习与导向滤波算法在图像去雾中的应用

Application of hybrid residual learning and guided filtering algorithm in image defogging

论文大纲

陈清江 ^*张雪

作者单位

西安建筑科技大学理学院, 陕西西安 710055

图像去雾残差网络大气散射模型导向滤波 image defogging residual networks atmospheric scattering model guided filter

摘要

为解决雾天场景图像恢复过程中图像清晰度和对比度下降的问题, 提出了一种结合残差学习和导向滤波的单幅图像去雾算法。使用雾天图像与对应的清晰图像构建残差网络; 采用多尺度卷积提取更多细节的雾霾特征; 利用导向滤波各向异性的优点, 对残差网络去雾后的图像进行滤波以保持图像边缘特性, 得到更加清晰的无雾图像。通过与DCP算法、CAP算法、SRCNN算法、DehazeNet算法和MSCNN算法相比, 在合成雾天图像上, 峰值信噪比值最高达到31.951 8 dB, 结构相似度值最高达到0.979 6, 在自然雾天图像上的运行时间最低达到了0.4 s, 主观评价和客观评价均优于其它对比算法。实验结果表明, 所提去雾算法不仅去雾效果较优, 而且速度较快, 具有较强的实用价值。

Abstract

To solve the problem of image clarity and contrast degradation in fog scene image restoration, a single image defogging algorithm based on residual learning and guided filtering was proposed. A residual network was first constructed by using foggy images and corresponding clear images. Multi-scale convolution was then used to extract more detailed haze features. Taking advantage of the anisotropy of the guided filter, the algorithm then obtained a clearer fog-free image after the residual network was filtered to maintain image edge characteristics. Experiments produced the following results as compared with the dark channel prior, CAP, super-resolution convolutionalneuralnetwork, DehazeNet, and multi-scale convolutional neural network algorithms.On synthetic foggy images, the peak signal-to-noise ratio reacheda maximum of 27.840 3 dB, the structural similarity index measurereacheda maximum of 0.979 6, and the runtime on natural foggy images was as low as 0.4 s.In addition, the subjective and objective evaluations proved to be better than those of the other comparison algorithms.Thus, the proposed defogging algorithm not only produces a better defogging effectbut is also faster, there by offering a greater practical valuefor defogging applications than the other algorithms.

参考文献

[1] TAN R T.Visibility in bad weather from a single image ［C］.Computer Vision and Pattern Recognition, 2008.CVPR 2008.IEEE Conference on.Anchorage, AK, USA: IEEE, 2008: 1-8.

[2] HE K, SUN J, TANG X O.Single image haze removal using dark channel prior ［J］.IEEE Transactions on Pattern Analysis & Machine Intelligence, 2011, 33(12): 2341-2353.

[3] ZHU Q, MAI J, SHAO L.A fast single image haze removal algorithm using color attenuation prior ［J］.IEEE Transactions on Image Processing, 2015, 24(11): 3522-3533.

[4] 刘万军, 赵庆国, 曲海成.变差函数和形态学滤波的图像去雾算法［J］.中国图象图形学报, 2016, 21(12): 1610-1622.

LIU W J, ZHAO Q G, QU H CH.Image defog algorithm based on variogram and morphological filter ［J］.Journal of Image and Graphics, 2016, 21(12): 1610-1622.(in Chinese)

[5] 李喆, 李建增, 胡永江, 等.混合先验与加权引导滤波的图像去雾算法［J］.中国图象图形学报, 2019, 24(2): 170-179.

LI ZH, LI J Z, HU Y J, et al.. Mixed prior and weighted guided filter image dehazing algorithm ［J］.Journal of Image and Graphics, 2019, 24(2): 170-179.(in Chinese)

[6] 沈逸云, 邵雅琪, 刘春晓, 等.结合天空检测与纹理平滑的图像去雾［J］.中国图象图形学报, 2017, 22(7): 897-905.

SHEN Y Y, SHAO Y Q, LIU CH X, et al.. Integrating sky detection with texture smoothing for image defogging ［J］.Journal of Image and Graphics, 2017, 22(7): 897-905.(in Chinese)

[7] 张秀, 周巍, 段哲民, 等.基于卷积稀疏自编码的图像超分辨率重建［J］.光学精密工程, 2019, 48(1): 324-330.

ZHANG X, ZHOU W, DUAN ZH M, et al.. Convolutional sparse auto-encoder for image super-resolution reconstruction ［J］.Opt.Precision Eng., 2019, 48(1): 324-330.(in Chinese)

[8] 李传朋, 秦品乐, 张晋京.基于深度卷积神经网络的图像去噪研究［J］.计算机工程, 2017, 43(3): 253-260.

LI CH P, QIN P L, ZHANG J J.Research on image denoising based on deep convolutional neural network ［J］.Computer Engineering, 2017, 43(3): 253-260.(in Chinese)

[9] 刘超, 张晓晖.超低照度下微光图像的深度卷积自编码网络复原［J］.光学精密工程, 2018, 26(4): 951-961.

LIU CH, ZHANG X H.Deep convolutional autoencoder networks approach to low-light level image restoration under extreme low-light illumination ［J］.Opt.Precision Eng., 2018, 26(4): 951-961.(in Chinese)

[10] 刘峰, 沈同圣, 马新星, 等.基于多波段深度神经网络的舰船目标识别［J］.光学精密工程, 2017, 25(11): 2939-2946.

LIU F, SHEN T SH, MA X X, et al.. Ship recognition based on multi-band deep neural Network ［J］.Opt.Precision Eng., 2017, 25(11): 2939-2946.(in Chinese)

[11] 谢冰, 段哲民, 郑宾, 等.基于迁移学习SAE的无人机目标识别算法研究［J］.红外与激光工程, 2018, 47(6): 224-230.

XIE B, DUAN ZH M, ZHENG B, et al.. Research on UAV target recognition algorithm based on transfer learning SAE ［J］.Infrared and Laser Engineering, 2018, 47(6): 224-230.(in Chinese)

[12] REN W Q, LIU S, ZHANG H, et al.. Single Image Dehazing Via Multi-scale Convolutional Neural Networks ［M］.Computer Vision-ECCV 2016.Berlin: Springer International Publishing, 2016: 154-169.

[13] LI C Y, GUO J C, FU H Z, et al.. A cascaded convolutional neural network for single image dehazing ［J］.IEEE Access, 2018: 24877-24887.

[14] HE K, ZHANG X, REN S, et al.. Identity mappings in deep residual networks［C］.Proc.Eur. Conf.Comput.Vis., 2016: 630-645.

[15] ZHANG K, ZUO W, CHEN Y, et al.. Beyond a gaussian denoiser: residual learning of deep CNN for image denoising ［J］. IEEE Trans.Image Process, 2016, 26(7): 3142-315.

[16] 廖建尚, 王立国.两类空间信息融合的高光谱图像分类方法［J］.激光与光电子学进展, 2017, 54(8): 081002.

LIAO J SH, WANG L G.Hyperspectral image classification method based on fusion with two kinds of spatial information ［J］.Laser & Optoelectronics Progress, 2017, 54(8): 081002. (in Chinese)

[17] DONG C, HE K, TANG X, et al.. Image super-resolution using deep convolutional networks ［J］.IEEE Trans Pattern Anal Mach Intell, 2016, 38(2): 295-307.

[18] NARASIMHAN S G, NAYAR S K. Contrast restoration of weather degraded images ［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2003, 25(6): 713-724.

陈清江, 张雪. 混合残差学习与导向滤波算法在图像去雾中的应用[J]. 光学精密工程, 2019, 27(12): 2702. CHEN Qing-jiang, ZHANG Xue. Application of hybrid residual learning and guided filtering algorithm in image defogging[J]. Optics and Precision Engineering, 2019, 27(12): 2702.

混合残差学习与导向滤波算法在图像去雾中的应用

关于本站 Cookie 的使用提示

全站搜索

混合残差学习与导向滤波算法在图像去雾中的应用

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索