2.624

2020影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于误差回传机制的多尺度去雾网络

杨爱萍 李晓晓 张腾飞 王朝臣 王建

杨爱萍, 李晓晓, 张腾飞, 王朝臣, 王建. 基于误差回传机制的多尺度去雾网络. 自动化学报, 2021, 47(x): 1001−1011 doi: 10.16383/j.aas.c210264
引用本文: 杨爱萍, 李晓晓, 张腾飞, 王朝臣, 王建. 基于误差回传机制的多尺度去雾网络. 自动化学报, 2021, 47(x): 1001−1011 doi: 10.16383/j.aas.c210264
Yang Ai-Ping, Li Xiao-Xiao, Zhang Teng-Fei, Wang Chao-Chen, Wang Jian. Multi-scale Dehazing Network Based on Error-backward Mechanism. Acta Automatica Sinica, 2021, 47(x): 1001−1011 doi: 10.16383/j.aas.c210264
Citation: Yang Ai-Ping, Li Xiao-Xiao, Zhang Teng-Fei, Wang Chao-Chen, Wang Jian. Multi-scale Dehazing Network Based on Error-backward Mechanism. Acta Automatica Sinica, 2021, 47(x): 1001−1011 doi: 10.16383/j.aas.c210264

基于误差回传机制的多尺度去雾网络

doi: 10.16383/j.aas.c210264
基金项目: 国家自然科学基金(62071323,61771329,61632018)资助
详细信息
    作者简介:

    杨爱萍:天津大学电气自动化与信息工程学院副教授. 主要研究方向为深度学习、图像处理以及计算机视觉. 本文通信作者. E-mail: yangaiping@tju.edu.cn

    李晓晓:天津大学电气自动化与信息工程学院硕士. 主要研究方向为图像去雾和深度学习. E-mail: leexx@tju.edu.cn

    张腾飞:天津大学电气自动化与信息工程学院硕士. 主要研究方向为图像风格转换和深度学习. E-mail: ztf951@gmail.com

    王朝臣:天津大学电气自动化与信息工程学院硕士. 主要研究方向为图像去雨和深度学习. E-mail: chen2019@tju.edu.cn

    王建:天津大学电气自动化与信息工程学院讲师. 主要研究方向为计算机视觉和认知计算. E-mail: jianwang@tju.edu.cn

Multi-scale Dehazing Network Based on Error-backward Mechanism

Funds: Supported by National Natural Science Foundation of China (62071323,61771329,61632018)
More Information
    Author Bio:

    YANG Ai-Ping Associate Professor at the College of Electrical and Information Engineering, Tianjin University. Her research interest mainly focuses on deep learning, image processing, computer vision. Corresponding author of this paper

    LI Xiao-Xiao Master student at College of Electrical and Information Engineering, Tianjin University. Her research interest covers on image dehazing and deep learning

    ZHANG Teng-Fei Master student at College of Electrical and Information Engineering, Tianjin University. His research interest covers on image style transfer and deep learning

    WANG Chao-Chen Master student at College of Electrical and Information Engineering, Tianjin University. His research interest covers on image deraining and deep learning

    WANG Jian Master student at College of Electrical and Information Engineering, Tianjin University. His research interest covers on computer vision and cognitive computing

  • 摘要: 针对现有图像去雾方法因空间上下文信息丢失而无法准确估计大尺度目标特征, 导致图像结构被破坏或去雾不彻底等问题, 本文提出了一种基于误差回传机制的多尺度去雾网络. 网络由误差回传多尺度去雾群组(Error-backward Multi-scale Dehazing Group, EMDG)、门控融合模块和优化模块组成. 其中EMDG包括误差回传模块和雾霾感知单元, 误差回传模块度量相邻尺度网络特征图之间的差异, 并将生成的差值图回传至上一尺度, 实现对结构信息和上下文信息的有效复用; 雾霾感知单元是各尺度子网络的核心, 其由残差密集块和雾浓度自适应检测块组成, 可充分提取局部信息并能够根据雾浓度实现自适应去雾. 不同于已有融合方法直接堆叠各尺度特征, 提出的门控融合模块逐像素学习每个子网络特征图对应的最优权重, 有效避免了干扰信息对图像结构和细节信息的破坏. 再经优化模块, 可得最终的无雾图像. 在合成数据集和真实数据集上的大量实验表明, 本文方法优于目前的主流去雾方法, 尤其是对远景雾气去除效果更佳.
  • 图  1  直接融合策略和误差回传策略示意图

    Fig.  1  Illustration of direct-integration strategy and error-backward strategy for multi-scale network

    图  2  基于误差回传机制的多尺度去雾网络

    Fig.  2  Architecture of Multi-scale Dehazing Network Based on Error-backward Mechanism

    图  3  误差回传模块结构

    Fig.  3  Architecture of the Error-backward Block

    图  4  雾霾感知单元结构

    Fig.  4  The Structure of the Haze Aware Unit

    图  5  残差密集块结构

    Fig.  5  The Structure of the Residual Dense Block

    图  6  雾浓度自适应检测块结构

    Fig.  6  The Structure of the Haze Density Adaptive Detection Block

    图  7  SOTS测试集的去雾结果图对比

    Fig.  7  The qualitative results of the state-of-the-art methods on SOTS

    图  8  HSTS测试集的去雾结果图对比

    Fig.  8  The qualitative results of the state-of-the-art methods on HSTS

    图  9  真实有雾图像的去雾结果对比

    Fig.  9  The qualitative results of the state-of-the-art methods on real hazy images

    图  10  部分区域色度偏暗的去雾图

    Fig.  10  Dehazed images with some darker areas

    表  1  SOTS室内测试集去雾结果的定量比较

    Table  1  Qualitative comparisons on SOTS indoor testset

    MethodDCP[4]DehazeNet[10]AODNet[13]EPDN[25]GCANet[14]
    PSNR16.6221.1419.0625.0630.23
    SSIM0.81790.84720.85040.92320.9800
    MethodGridDehazeNet[15]PFDN[16]Ynet[17]MSBDN[26]Ours
    PSNR32.1632.6819.0433.7933.83
    SSIM0.98360.97600.84650.98400.9834
    下载: 导出CSV

    表  2  SOTS室外测试集去雾结果的定量比较

    Table  2  Qualitative comparisons on SOTS outdoor testset

    MethodDCP[4]DehazeNet[10]MSCNN[11]AODNet[13]
    PSNR19.1322.4622.0620.29
    SSIM0.81480.85140.90780.8765
    MethodEPDN[25]GridDehazeNet[15]Ynet[17]Ours
    PSNR22.5730.8625.0231.10
    SSIM0.86300.98190.90120.9765
    下载: 导出CSV

    表  3  O-Haze数据集去雾结果定量比较

    Table  3  Qualitative comparisons on O-Haze dataset

    MethodDCP[4]MSCNN[11]AODNet[13]EPDN[25]GCANet[14]GridDehazeNet[15]Ours
    PSNR16.7817.2615.0316.0016.2818.9219.28
    SSIM0.65300.65010.53940.64130.64500.67210.6756
    下载: 导出CSV

    表  4  HSTS测试集去雾结果的定量比较

    Table  4  Qualitative comparisons on HSTS testset

    MethodDCP[4]DehazeNet[10]MSCNN[11]AODNet[13]EPDN[25]Ynet[17]CCDID[27]Ours
    PSNR14.8424.4818.6420.5523.3818.3717.2230.07
    SSIM0.76090.91530.81680.89730.90590.47250.82180.9658
    下载: 导出CSV

    表  5  不同模块对网络性能的影响

    Table  5  Comparisons on SOTS indoor testset for different configurations.

    5 RDB
    9 RDB
    GFN
    EB
    HDADB
    PSNR28.7929.5231.5332.4533.83
    下载: 导出CSV

    表  6  各方法平均运行时间对比

    Table  6  Average computing time comparision of various methods

    MethodCPU/GPUTime(s)
    DCP[4]CPU25.08
    DehazeNet[10]CPU2.56
    MSCNN[11]CPU2.45
    AODNet[13]GPU0.24
    GridDehazeNet[15]GPU0.59
    FFA[28]GPU1.23
    OursGPU0.73
    下载: 导出CSV
  • [1] Wonkyun K, Jong Y, Jechang J. Contrast enhancement using histogram equalization based on logarithmic mapping. Optical Engineering, 2012, 51(6), 067002: 1-11
    [2] Li H, Xie W H, Wang X G. GPU implementation of multi-scale retinex image enhancement algorithm. In: Proceedings of IEEE/ACS International Conference of Computer Systems and Applications, Agadir, Morocco: IEEE, 2016. 1-5
    [3] Stark J A. Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Transactions on Image Processing, 2000, 9(5): 889-896 doi: 10.1109/83.841534
    [4] He K, Sun J, Tang X. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(12): 2341-2353
    [5] Tarel J P, Hautière N. Fast visibility restoration from a single color or gray level image. In: Proceedings of IEEE International Conference on Computer Vision, Kyoto, Japan: IEEE, 2010. 2201−2208
    [6] 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 doi: 10.1109/TIP.2015.2446191
    [7] Berman D, Treibitz T, Avidan S. Non-local image dehazing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA: IEEE, 2016. 1674−1682
    [8] 张小刚, 唐美玲, 陈华, 汤红忠. 一种结合双区域滤波和图像融合的单幅图像去雾算法. 自动化学报, 2014, 40(8): 1733-1739

    ZHANG Xiao-Gang, TANG Mei-Ling, CHEN Hua, TANG Hong-Zhong. A dehazing method in single image based on double-area filter and image fusion. Acta Automatica Sinica, 2014, 40(8): 1733-1739
    [9] 汪云飞, 冯国强, 刘华伟, 赵搏欣. 基于超像素的均值-均方差暗通道单幅图像去雾方法. 自动化学报, 2018, 44(3): 481-489

    WANG Yun-Fei, FENG Guo-Qiang, LIU Hua-Wei, ZHAO Bo-Xin. Superpixel-based mean and mean square deviation dark channel for single image fog removal. Acta Automatica Sinica, 2018, 44(3): 481-489
    [10] Cai B L, Xu X M, Jia K, Qing C M, Tao D C. DehazeNet: an end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 2016, 25(11): 5187-5198 doi: 10.1109/TIP.2016.2598681
    [11] Cai B L, Xu X M, Jia K, Qing C M, Tao D C. DehazeNet: an end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 2016, 25(11): 5187-5198 doi: 10.1109/TIP.2016.2598681
    [12] 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 2016 European Conference on Computer Vision, Amsterdam, NETHERLANDS: Springer, 2016. 154−169
    [13] Zhang H, Patel V M. Densely connected pyramid dehazing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA: IEEE, 2018. 3194−3203
    [14] Li B Y, Peng X L, Wang Z Y, Xu J Z, Feng D. AOD-Net: all-in-one dehazing network. In: Proceedings of 2017 IEEE International Conference on Computer Vision, Venice, Italy: IEEE, 2017. 4780−4788
    [15] Chen D D, He M M, Fan Q N, Liao J, Zhang L H, Hou D D, et al. Gated context aggregation network for image dehazing and deraining. In: Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision, Hilton Waikoloa Village, Hawaii: IEEE, 2019. 1375−1383
    [16] Liu X H, Ma Y R, Shi Z H, Chen J. GridDehazeNet: attention-based multi-scale network for image dehazing. In: Proceedings of 2019 IEEE International Conference on Computer Vision. Seoul, Korea: IEEE, 2019. 7314−7323
    [17] Dong J X, Pan J S. Physics-based feature dehazing networks. In: Proceedings of 2020 Europeon Conference on Computer Vision, Glasgow, UK: Springer, 2020. 188−204
    [18] Yang H H, Yang C H H, Tsai Y C J. Y-net: multi-scale feature aggregation network with wavelet structure similarity loss function for single image dehazing. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, Spain: IEEE, 2020. 2628−2632
    [19] Deng Q L, Huang Z L, Lin C W. HardGAN: a haze-aware representation distillation GAN for single image dehazing. In: Proceedings of 2020 Europeon Conference on Computer Vision. Glasgow, UK: Springer, 2020. 722−738
    [20] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, 2015. 234–241
    [21] Johnson J, Alexandre A, Li F F. Perceptual losses for real-time style transfer and super-resolution. In: Proceedings of 2016 Europeon Conference on Computer Vision, Amsterdam, The Netherlands: Springer, 2016. 694−711
    [22] Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, et al. Imagenet large scale visual recognition challenge. In: Proceedings of International Journal of Computer Vision, Springer, 2015. 211–252
    [23] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of 2015 3rd International Conference on Learning Representations, San Diego, CA, USA: ICLR, 2015. 1−14
    [24] Li B Y, Ren W Q, Fu D P, Tao D C, Feng D, Zeng W J, et al. Benchmarking single image dehazing and beyond. IEEE Transactions on Image Processing, 2019. 28(1): 492-505 doi: 10.1109/TIP.2018.2867951
    [25] Ancuti C O, Ancuti C, Timofte R, Vleeschouwer C D. O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, UT, USA: IEEE, 2018. 754−762
    [26] Qu Y Y, Chen Y Z, Huang J Y, Xie Y. Enhanced pix2pix dehazing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019. 8160−8168
    [27] Dong H, Pan J S, Xiang L, Hu Z, Zhang X Y, Wang F, Yang M H. Multi-Scale boosted dehazing network with dense feature fusion. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2020. 2154−2164
    [28] Dhara S K, Roy M, Sen D, Biswas P K. Color cast dependent image dehazing via adaptive airlight refinement and non-linear color balancing. IEEE Transactions on Circuits and Systems for Video Technology, 2020: 1-5
    [29] Qin X, Wang Z L, Bai Y C, Xie X D, Jia H Z. FFA-Net: Feature fusion attention network for single image dehazing. In: Proceedings of the Association for the Advance of Artificial Intelligence. Hilton Midtown, New York: AAAI Press, 2020. 11908−11915
  • 加载中
计量
  • 文章访问数:  220
  • HTML全文浏览量:  89
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-03-31
  • 录用日期:  2021-09-17
  • 网络出版日期:  2021-11-05

目录

    /

    返回文章
    返回