基于改进循环生成式对抗网络的图像去雾方法

doi:10.19678/j.issn.1000-3428.0064162

摘要/Abstract

摘要： 针对现有图像去雾方法存在的颜色失真、细节丢失以及去雾效果不自然等问题，提出一种改进的循环生成式对抗网络用于图像去雾。通过添加多尺度鉴别器作为判别器来改进原始网络结构，增强判别能力，引导网络产生更精细自然的无雾图像。同时重新设计损失函数，使用最小二乘代替交叉熵作为对抗损失，引入循环感知损失，结合原始循环一致性损失组成新的复合损失函数，提高图像颜色与细节恢复的质量。在D-HAZY和SOTS数据集上的实验结果表明：该方法能够生成较为自然的无雾图像，其主观效果和客观指标均优于对比方法，具有更好的去雾能力；与原始循环生成式对抗网络相比，峰值信噪比从19.052 dB提高至23.128 dB，结构相似性指数从0.787提高至0.867。与DehazeNet、AOD-Net与GCANet等主流去雾方法相比，峰值信噪比和结构相似性指数比排名第二的方法分别提升7.1%和4.3%。

关键词: 图像去雾, 循环生成式对抗网络, 多尺度鉴别器, 对抗损失, 循环感知损失

Abstract: Aiming at the problems of color distortion, loss of detail, and unnatural defogging effects in the existing image defogging methods, an image defogging method based on improved Cycle-consistent Adversarial Network(CycleGAN) is proposed.This method improves the original network structure and enhances the discrimination ability by adding a multi-scale discriminator to guide the network to produce a finer and more natural fog-free image.Meanwhile, the loss function is redesigned, the least squares method is used to replace the cross-entropy as the counter loss, and the cyclic perception loss is introduced.Combined with the original cyclic consistency loss, a new composite loss function is constructed to improve the quality of the image color and detail restoration.Experimental results on D-HAZY and SOTS datasets show that the proposed method can generate more natural fog-free images, and its subjective effect and objective index are better than those of other methods and has better defogging ability.Compared with the original CycleGAN, the Peak Signal to Noise Ratio(PSNR) of the method is improved from 19.052 dB to 23.128 dB and the Structure Similarity Index(SSIM) is improved from 0.787 to 0.867.Compared with mainstream defogging methods such as DehazeNet, AOD-Net and GCANet, the PSNR and SSIM of this method are approximately 7.1% and 4.3% higher than those of the second-ranking algorithm, respectively.

Key words: image defogging, Cycle-consistent Adversarial Network(CycleGAN), multi-scale discriminator, adversarial loss, cyclic perceptual loss

中图分类号:

TP391.41

黄山, 贾俊. 基于改进循环生成式对抗网络的图像去雾方法[J]. 计算机工程, 2022, 48(12): 218-223,231.

HUANG Shan, JIA Jun. Image Defogging Method Based on Improved Cycle-Consistent Adversarial Network[J]. Computer Engineering, 2022, 48(12): 218-223,231.

https://www.ecice06.com/CN/Y2022/V48/I12/218

图/表 8

20230112184033

20230112184036

20230112184040

20230112184043

20230112184046

20230112184049

20230112184053

20230112184057

参考文献

[1] SINGH D, KUMAR V.Defogging of road images using gain coefficient-based trilateral filter[J].Journal of Electronic Imaging, 2018, 27(1):013004.
[2] HUANG Z L, DUMITRU C O, PAN Z X, et al.Classification of large-scale high-resolution SAR images with deep transfer learning[J].IEEE Geoscience and Remote Sensing Letters, 2021, 18(1):107-111.
[3] LIU X, ZHAO D, XU L, et al.A distributed video management cloud platform using Hadoop[J].IEEE Access, 2015, 3:2637-2643.
[4] CHOI S, LE T, NGUYEN Q, et al.Toward self-driving bicycles using state-of-the-art deep reinforcement learning algorithms[J].Symmetry, 2019, 11(2):290.
[5] 王道累, 张天宇.图像去雾算法的综述及分析[J].图学学报, 2020, 41(6):861-870. WANG D L, ZHANG T Y.Review and analysis of image defogging algorithm[J].Journal of Graphics, 2020, 41(6):861-870.(in Chinese)
[6] JU M Y, DING C, ZHANG D Y, et al.Gamma-correction-based visibility restoration for single hazy images[J].IEEE Signal Processing Letters, 2018, 25(7):1084-1088.
[7] LIANG W, LONG J, LI K C, et al.A fast defogging image recognition algorithm based on bilateral hybrid filtering[J].ACM Transactions on Multimedia Computing, Communications, and Applications, 2021, 17(2):42.
[8] SENGUPTA D, BISWAS A, GUPTA P.Non-linear weight adjustment in adaptive Gamma correction for image contrast enhancement[J].Multimedia Tools and Applications, 2021, 80(3):3835-3862.
[9] TANG Q F, YANG J, HE X J, et al.Nighttime image dehazing based on Retinex and dark channel prior using Taylor series expansion[J].Computer Vision and Image Understanding, 2021, 202:103086.
[10] LIANG J, JU H J, REN L Y, et al.Generalized polarimetric dehazing method based on low-pass filtering in frequency domain[J].Sensors, 2020, 20(6):1729.
[11] CHEN Z X, OU B N.Visibility detection algorithm of single fog image based on the ratio of wavelength residual energy[J].Mathematical Problems in Engineering, 2021, 2021:1-13.
[12] THANH L T, THANH D N H, HUE N M, et al.Single image dehazing based on adaptive histogram equalization and linearization of Gamma correction[C]//Proceedings of the 25th Asia-Pacific Conference on Communications.Washington D.C., USA:IEEE Press, 2019:36-40.
[13] FAN T H, LI C L, MA X, et al.An improved single image defogging method based on Retinex[C]//Proceedings of the 2nd International Conference on Image, Vision and Computing.Washington D.C., USA:IEEE Press, 2017:410-413.
[14] ZHANG B W, WANG M L, SHEN X B.Image haze removal algorithm based on nonsubsampled contourlet transform[J].IEEE Access, 2021, 9:21708-21720.
[15] 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.
[16] JIANG Z Y, SUN X D, WANG X C.Image defogging algorithm based on sky region segmentation and dark channel prior[J].Journal of Systems Science and Information, 2020, 8(5):476-486.
[17] PAN Y P, CHEN Z X, LI X M, et al.Single-image dehazing via dark channel prior and adaptive threshold[J].International Journal of Image and Graphics, 2021, 21(4):2150053.
[18] WANG F P, WANG W X.Road extraction using modified dark channel prior and neighborhood FCM in foggy aerial images[J].Multimedia Tools and Applications, 2019, 78(1):947-964.
[19] 薛文丹, 赵凤群.涉及景深的雾天图像增强的偏微分方程模型[J].计算机工程与应用, 2017, 53(19):192-197. XUE W D, ZHAO F Q.Partial differential equation model involving depth of scene for hazy image enhancement[J].Computer Engineering and Applications, 2017, 53(19):192-197.(in Chinese)
[20] CHEN D D, HE M M, FAN Q N, et al.Gated context aggregation network for image dehazing and deraining[C]//Proceedings of IEEE Winter Conference on Applications of Computer Vision.Washington D.C., USA:IEEE Press, 2019:1375-1383.
[21] CAI B L, XU X M, JIA K, et al.DehazeNet:an end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing, 2016, 25(11):5187-5198.
[22] LI B Y, PENG X L, WANG Z Y, et al.AOD-net:all-in-one dehazing network[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:4780-4788.
[23] QIN X, WANG Z L, BAI Y C, et al.FFA-net:feature fusion attention network for single image dehazing[J].Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7):11908-11915.
[24] WANG B, NIU B, ZHAO P, et al.Review of single image defogging[J].International Journal of Sensor Networks, 2021, 35(2):111-120.
[25] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al.Generative adversarial nets[C]//Proceedings of Annual Conference on Neural Information Processing Systems.Berlin, Germany:Springer, 2014:2672-2680.
[26] LEE M, SEOK J.Controllable generative adversarial network[J].IEEE Access, 2019, 7:28158-28169.
[27] ZHU J Y, PARK T, ISOLA P, et al.Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2242-2251.
[28] CRESWELL A, WHITE T, DUMOULIN V, et al.Generative adversarial networks:an overview[J].IEEE Signal Processing Magazine, 2018, 35(1):53-65.
[29] MAO X D, LI Q, XIE H R, et al.Least Squares generative adversarial networks[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2813-2821.
[30] ANCUTI C, ANCUTI C O, DE VLEESCHOUWER C.D-HAZY:a dataset to evaluate quantitatively dehazing algorithms[C]//Proceedings of IEEE International Conference on Image Processing.Washington D.C., USA:IEEE Press, 2016:2226-2230.
[31] YUAN F, HUANG H.Image haze removal via reference retrieval and scene prior[J].IEEE Transactions on Image Processing, 2018, 27(9):4395-4409.
[32] HUYNH-THU Q, GHANBARI M.Scope of validity of PSNR in image/video quality assessment[J].Electronics Letters, 2008, 44(13):800.
[33] WANG Z, BOVIK A C, SHEIKH H R, et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing, 2004, 13(4):600-612.

选择文件类型/文献管理软件名称

选择包含的内容