基于多尺度密集特征融合的生成式对抗除雾网络

doi:10.12068/j.issn.1005-3026.2022.11.010

东北大学学报（自然科学版） ›› 2022, Vol. 43 ›› Issue (11): 1591-1598.DOI: 10.12068/j.issn.1005-3026.2022.11.010

基于多尺度密集特征融合的生成式对抗除雾网络

连静^1,2，陈实¹，丁堃³，李琳辉^1,2

(1. 大连理工大学汽车工程学院，辽宁大连116024； 2. 大连理工大学工业装备结构分析国家重点实验室，辽宁大连116024； 3. 大连海洋大学应用技术学院，辽宁大连116000)

发布日期:2022-12-06
通讯作者: 连静
作者简介:连静(1980-)，女，吉林公主岭人，大连理工大学副教授，博士生导师.
基金资助:
国家自然科学基金资助项目(61976039，52172382)；中央高校基本科研业务费专项资金资助项目(DUT22JC09)；大连市科技创新基金资助项目(2021JJ12GX015).

Generative Adversarial Network Based on Multi-scale Dense Feature Fusion for Image Dehazing

LIAN Jing^1,2， CHEN Shi¹， DING Kun³， LI Lin-hui^1,2

1. School of Automotive Engineering， Dalian University of Technology， Dalian 116024， China; 2. State Key Laboratory of Structural Analysis for Industrial Equipment， Dalian University of Technology， Dalian 116024， China; 3. Applied Technology College， Dalian Ocean University， Dalian 116000， China.

Published:2022-12-06
Contact: LI Lin-hui
About author:-
Supported by:
-

摘要/Abstract

摘要： 在真实雾天场景下，针对除雾网络无法去除远处雾气、天空区域容易出现噪声的问题，提出了一种基于多尺度密集特征融合的生成式对抗除雾网络，并采用制作的合成雾天数据集进行对抗训练.首先，对除雾网络进行设计，构建了网络模型；其次，从合成晴朗天气图像中利用深度标签生成逼真的雾天数据集，以适用于真实雾天除雾领域；最后，在真实雾天数据集上测试，选取近几年具有代表性的6种基于深度学习的除雾网络进行主观视觉效果，并借助除雾领域常用的无参考图像质量评价指标进行客观分析.研究结果表明:提出的除雾网络在真实场景下的除雾效果较其他网络有显著提升，主观视觉效果明显优于对比的除雾网络，在无参评价指标上综合表现优于其他除雾网络.

关键词: 图像处理；图像除雾；生成式对抗网络；多尺度密集特征融合；对抗训练

Abstract: In view of the poor dehazed effect of the existing dehazing networks in real hazy image and the obvious noise in the sky area of the image， a generative adversarial network based on multi-scale dense feature fusion for image dehazing is proposed. The dehazing network uses the produced synthetic foggy data set for adversarial training. Firstly， the dehazing network is designed and the network model is constructed; secondly， a realistic foggy data set is directly generated from the synthetic sunny weather image using deep tags to be suitable for the dehazed field; finally， the network is tested on the real foggy day data set and selects six representative deep learning dehazing networks in recent years for comparison， and non-reference image quality evaluation indicators are used for objective analysis. The research results show that the effect of the proposed dehazing network in real scenes is significantly improved compared to the other networks. The subjective visual effect is significantly better， and the comprehensive performance is better than the other networks in non-reference image quality evaluation indicators.

Key words: image processing; image dehazing; generative adversarial network; multi-scale dense feature fusion; adversarial training

中图分类号:

TP391.4

连静，陈实，丁堃，李琳辉. 基于多尺度密集特征融合的生成式对抗除雾网络[J]. 东北大学学报（自然科学版）, 2022, 43(11): 1591-1598.

LIAN Jing， CHEN Shi， DING Kun， LI Lin-hui. Generative Adversarial Network Based on Multi-scale Dense Feature Fusion for Image Dehazing[J]. Journal of Northeastern University(Natural Science), 2022, 43(11): 1591-1598.

参考文献

[1]Sakaridis C，Dai D，Gool L V.Semantic foggy scene understanding with synthetic data［J］.International Journal of Computer Vision，2018，126(9):973-992.
[2]Dai D，Sakaridis C，Hecker S，et al.Curriculum model adaptation with synthetic and real data for semantic foggy scene understanding［J］.International Journal of Computer Vision，2020，128(5):1182-1204.
[3]Tan R T.Visibility in bad weather from a single image［C］//IEEE Conference on Computer Vision and Pattern Recognition.Anchorage，2008:1-8.
[4]He K，Sun J，Tang X.Single image haze removal using dark channel prior［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2010，33(12):2341-2353.
[5]Fattal R.Single image dehazing［J］.ACM Transactions on Graphics，2008，27(3):1-9.
[6]Berman D，Avidan S.Non-local image dehazing［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas，2016:1674-1682.
[7]Zhang Y，Gao K，Wang J，et al.Single-image dehazing using extreme reflectance channel prior［J］.IEEE Access，2021，9:87826-87838.
[8]Cai B，Xu X，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.
[9]Sakaridis C，Dai D，Van Gool L.Semantic foggy scene understanding with synthetic data［J］.International Journal of Computer Vision，2018，126(9):973-992.
[10]Zhang H，Patel V M.Densely connected pyramid dehazing network［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City，2018:3194-3203.
[11]Ren W，Si L，Hua Z，et al.Single image dehazing via multi-scale convolutional neural networks［C］// European Conference on Computer Vision.Cham:Springer，2016:154-169.
[12]Li B，Peng X，Wang Z，et al.Aod-net:all-in-one dehazing network［C］// Proceedings of the IEEE International Conference on Computer Vision.Venice，2017:4770-4778.
[13]Wang N，Cui Z，Su Y，et al.RGNAM:recurrent grid network with an attention mechanism for single-image dehazing［J］.Journal of Electronic Imaging，2021，30(3):033026.
[14]Qin X，Wang Z，Bai Y，et al.FFA-Net:feature fusion attention network for single image dehazing［C］// Proceedings of the AAAI Conference on Artificial Intelligence.New York，2020:11908-11915.
[15]Chen W T，Fang H Y，Ding J J，et al.PMHLD:patch map-based hybrid learning DehazeNet for single image haze removal［J］.IEEE Transactions on Image Processing，2020，29:6773-6788.
[16]Liu X，Ma Y，Shi Z，et al.Grid dehazenet:attention-based multi-scale network for image dehazing［C］// Proceedings of the IEEE/CVF International Conference on Computer Vision.Seoul，2019:7314-7323.
[17]Engin D，Genc A，Ekenel H K.Cycle-dehaze:enhanced cycleGAN for single image dehazing［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.Salt Lake City，2018:825-833.
[18]Dong Y，Liu Y，Zhang H，et al.FD-GAN:generative adversarial networks with fusion-discriminator for single image dehazing［C］// Proceedings of the AAAI Conference on Artificial Intelligence.New York，2020:10729-10736.
[19]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).Waikoloa，2019:1375-1383.
[20]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.Seattle，2020:2157-2167.
[21]Li B Y，Ren W Q，Fu D P，et al.Benchmarking single-image dehazing and beyond［J］.IEEE Transactions on Image Processing，2019，28(1):492-505.
[22]Dai S，Han M，Wu Y，et al.Bilateral back-projection for single image super resolution［C］// 2007 IEEE International Conference on Multimedia and Expo.Beijing，2007:1039-1042.
[23]Wrenninge M，Unger J.Synscapes:a photorealistic synthetic dataset for street scene parsing［EB/OL］［2018-12-01］.arXiv preprint arXiv:1810.08705.
[24]Hahner M，Dai D，Sakaridis C，et al.Semantic understanding of foggy scenes with purely synthetic data［C］// 2019 IEEE Intelligent Transportation Systems Conference(ITSC).Auckland，2019:3675-3681.
[25]Liu L，Liu B，Huang H，et al.No-reference image quality assessment based on spatial and spectral entropies［J］.Signal Processing:Image Communication，2014，29(8):856-863.
[26]Mittal A，Soundararajan R，Bovik A C.Making a “completely blind” image quality analyzer［J］.IEEE Signal Processing Letters，2012，20(3):209-212.
[27]Mittal A，Moorthy A K，Bovik A C.No-reference image quality assessment in the spatial domain［J］.IEEE Transactions on Image Processing，2012，21(12):4695-4708.
[28]Moorthy A K，Bovik A C.A two-step framework for constructing blind image quality indices［J］.IEEE Signal Processing Letters，2010，17(5):513-516.

基于多尺度密集特征融合的生成式对抗除雾网络

Generative Adversarial Network Based on Multi-scale Dense Feature Fusion for Image Dehazing

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	丁其川，王力，刘成. 融合长距离信道注意力与病理特征的肺结节分类[J]. 东北大学学报（自然科学版）, 2023, 44(4): 476-485.
[2]	杨丹，刘国如，任梦成，裴宏杨. 多尺度卷积核U-Net模型的视网膜血管分割方法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 7-14.
[3]	原培新，陈鼎夫. 双能X射线高动态范围安检图像压缩算法[J]. 东北大学学报（自然科学版）, 2021, 42(1): 96-101.
[4]	张田，田勇，王子，王昭东. 基于清晰度评价的自适应阈值图像分割法[J]. 东北大学学报:自然科学版, 2020, 41(9): 1231-1238.
[5]	徐久强，张金鹏，贾玉其，邵建新. 基于集成学习的束支传导阻滞识别方法[J]. 东北大学学报:自然科学版, 2020, 41(3): 321-326.
[6]	徐礼胜，宋代远，刘文彦，王瑜璠. 用不同外周动脉波形重建主动脉波形的对比研究[J]. 东北大学学报:自然科学版, 2020, 41(2): 188-192.
[7]	冯宝，李昌林，李智，刘壮盛. 基于活动轮廓模型和影像组学的乳腺癌LVI状态预测[J]. 东北大学学报:自然科学版, 2020, 41(2): 193-199.
[8]	石春鹤，吴成东. 基于加权稀疏非负矩阵分解的车脸识别算法[J]. 东北大学学报:自然科学版, 2019, 40(10): 1376-1381.
[9]	张云洲，郑瑞，暴吉宁，朱尚栋. 基于多个相关滤波器的行人跟踪尺度算法[J]. 东北大学学报:自然科学版, 2019, 40(9): 1228-1234.
[10]	陈红，于晓升，吴成东，孙鹏. 参数化水平集活动轮廓模型的快速图像分割算法[J]. 东北大学学报:自然科学版, 2019, 40(1): 6-10.
[11]	张良钰，边天元，徐礼胜. 冠脉狭窄对外周与中心动脉间传递函数的影响[J]. 东北大学学报:自然科学版, 2018, 39(12): 1702-1707.
[12]	赵海，李雄峰，朱宏博，王彬. 基于分形维数特征的肺结节形状建模[J]. 东北大学学报:自然科学版, 2018, 39(11): 1545-1551.
[13]	窦圣昶，赵海，朱宏博，王彬. 修正与融合的肺部分割算法[J]. 东北大学学报:自然科学版, 2018, 39(11): 1562-1566.
[14]	徐礼胜，张书琪，牛潇，徐阳. 基于全卷积网络的左心室射血分数自动检测[J]. 东北大学学报:自然科学版, 2018, 39(11): 1572-1576.
[15]	齐林，吕旭阳，杨本强，徐礼胜. 基于全卷积网络迁移学习的左心室内膜分割[J]. 东北大学学报:自然科学版, 2018, 39(11): 1577-1582.