一种改进的轻量型网络图像去雾方法
作者:
作者单位:

昆明理工大学信息工程与自动化学院

中图分类号:

TP391


An Improved Lightweight Network for Image Dehazing
Author:
Affiliation:

School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [27]
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对卷积神经网络进行图像去雾时存在模型复杂度高、参数量大的问题,提出一种轻量型卷积神经网络LDNet(Lightweight image Dehazing Network,LDNet)。首先,改进了大气散射模型的表达公式,直接剔除雾噪声,减小估计中间变量的累计误差。其次,设计了融入注意力机制的倒残差模块RNAM(Reverse residual Network module with Attention Mechanism,RNAM),该模块能够多尺度提取图像特征,关注图像中重要的语义信息,同时解决网络参数量大、复杂度高的问题。最后,使用L1平滑损失函数和MS-SSIM损失函数作为联合损失函数,使恢复的无雾图像与真实无雾图像之间的距离尽可能最小化。实验结果表明,所提出的算法在RESIDE合成数据集上结构相似性(SSIM)和峰值性噪比(PSNR)均优于其它对比算法,无论在合成图像还是真实场景都能取得良好的去雾效果,且该方法具有参数少、运算快的特点。

    Abstract:

    In order to solve the problems of high model complexity and large parameters in image dehazing using convolutional neural network, a light image dehazing network (LDNet) is proposed. Firstly, the expression formula of atmospheric scattering model is improved to eliminate fog noise directly and reduce the cumulative error of intermediate variable estimation. Secondly, a reverse residual network module with attention mechanism (RNAM) is designed, which can extract image features at multiple scales, pay attention to the important semantic information in the image, and solve the problems of large network parameters and high complexity. Finally, L1 smoothing loss function and MS-SSIM loss function are used as joint loss functions to minimize the distance between the restored image and the real image. The experimental results show that the proposed algorithm is superior to other contrast algorithms in terms of SSIM and PSNR on the composite data set of reside, and can achieve good dehazing effect in both synthetic images and real scenes, and the method has the characteristics of less parameters and fast operation.

    参考文献
    [1] Kim T K, Paik J K, Kang B S. Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering. IEEE Transactions on Consumer Electronics, 1998, 44(1): 82?87
    [2] Stark J A. Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Transactions on Image Processing, 2000, 9(5): 889?896
    [3] Seow M J, Asari V K. Ratio rule and homomorphic filter for enhancement of digital colour image. Neurocomputing,2006, 69(7?9): 954?958
    [4] S. G. Narasimhan and S. K. Nayar, “Contrast restoration of weather degraded images,” IEEE Trans. Pattern Anal. Mach..Learn., vol. 25, no. 6, pp. 713–724, Jun. 2003.
    [5] S. K. Nayar and S. G. Narasimhan, “Vision in bad weather,” in Proc. IEEE Conf. Comput.Vis., vol. 2. Sep. 1999, pp. 820–827.
    [6] K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” IEEE Trans. Pattern Anal. Mach.Intell.,vol. 33, no. 12, pp. 2341–2353, Dec. 2011.
    [7] K. Tang, J. Yang, and J. Wang, “Investigating haze-relevant features in a learning framework for image dehazing,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2014, pp. 2995–3002.
    [8] B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao. Dehazenet: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 25(11):5187–5198, 2016.
    [9] H. Zhang and V. M. Patel. Densely connected pyramid dehazing network. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
    [10] Luo Y, Xu Y, Ji H. Removing rain from a single image via discriminative sparse coding[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 3397-3405.
    [11] Kupyn O, Budzan V, Mykhailych M, et al. Deblurgan: Blind motion deblurring using conditional adversarial networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 8183-8192.
    [12] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
    [13] HowardSASG,SZhuSM,SChenSB,SetSal.SMobilenets:SEfficientSconvolutionalSneuralSnetworksSforSmobileSvisionSapplications[J].SarXivSpreprintSarXiv:1704.04861,S2017.
    [14] Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 2818-2826.
    [15] Ma N, Zhang X, Zheng H T, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 116-131.
    [16] Iandola F N, Han S, Moskewicz M W, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size[J]. arXiv preprint arXiv:1602.07360, 2016.
    [17] Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.
    [18] Woo S, Park J, Lee J Y, et al. Cbam: Convolutional block attention module[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 3-19.
    [19] Zhao M, Zhong S, Fu X, et al. Deep residual networks with adaptively parametric rectifier linear units for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2020, DOI: 10.1109/TIE.2020.2972458.
    [20] Z. Wang, E. P. Simoncelli and A. C. Bovik, "Multiscale structural similarity for image quality assessment,"SThe Thrity-Seventh Asilomar Conference on Signals, Systems Computers, 2003, Pacific Grove, CA, USA, 2003, pp. 1398-1402 Vol.2, doi: 10.1109/ACSSC.2003.1292216.
    [21] Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014.
    [22] [23] W. Ren, D. Fu, D. Tao, D. Feng, W. Zeng, and Z. Wang. Reside: A benchmark for single image dehazing. arXiv preprint arXiv:1712.04143, 2017
    [23] B. Li, X. Peng, Z. Wang, J. Xu, and D. Feng. Aod-net: All-in-one dehazing network. In Proceedings of the IEEE International Conference on Computer Vision, volume 1, page 7, 2017.
    [24] Chen D, He M, Fan Q, et al. Gated context aggregation network for image dehazing and deraining[C]//2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2019: 1375-1383.
    [25] Dong H, Pan J, Xiang L, et al. Multi-scale boosted dehazing network with dense feature fusion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 2157-2167.
    [26] Wang Y, Li J, Lu Y, et al. Image quality evaluation based on image weighted separating block peak signal to noise ratio[C]//Proceedings of International Conference on Neural Networks and Signal Processing. Nanjing, Dec 14-17, 2003. New York: IEEE, 2003:994-997.
    [27] 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, 2004:600-612.
    相似文献
    引证文献
    引证文献 [0] 您输入的地址无效!
    没有找到您想要的资源,您输入的路径无效!

    网友评论
    网友评论
    分享到微博
    发 布
引用本文
分享
文章指标
  • 点击次数:644
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2021-04-02
  • 最后修改日期:2021-06-18
  • 录用日期:2021-06-21
文章二维码