基于深度学习的单幅图像去雾研究进展
Research Advances on Deep Learning Based Single Image Dehazing
查看参考文献72篇
文摘
|
户外视觉系统极易受到雾霾等恶劣天气影响,采集到的图像/视频质量严重下降,这不仅影响人眼的主观感受,也给后续的智能化分析带来严峻挑战.近年来,学者们将深度学习应用于图像去雾领域,取得了诸多的研究成果.但是雾霾图像场景复杂多变、降质因素众多,这对去雾算法的泛化能力提出了很高的要求.本文主要总结了近年来基于深度学习的单幅图像去雾技术研究进展.从先验知识和物理模型、映射关系建模、数据样本、知识迁移学习等角度出发,介绍了现有算法的研究思路、具体特点、优势与不足.尤其侧重于近两年来新出现的训练策略和网络结构,如元学习、小样本学习、域自适应、Transformer等.另外,本文在公共数据集上对比了各种代表性去雾算法的主客观性能、模型复杂度等,尤其是分析了去雾后的图像对于后续目标检测任务的影响,更全面地评价了现有算法性能的优劣,并探讨了未来可能的研究方向. |
其他语种文摘
|
Vision-based outdoor systems are highly susceptible to severe weather such as haze.The quality of the collected images in the hazy environments is seriously degraded,which affects subjective perception and brings challenges to the subsequent intelligent processing tasks.In recent years,deep learning has been applied to single image dehazing and achieved promising results.However,the hazy scenes are complex and unpredictable,which puts a high demand on the generalization ability of the dehazing methods.In this paper,we summarize the recent deep-learning-based single-image dehazing methods.The advantages and disadvantages of these methods are analyzed in terms of network mapping relationships,learning methods,training datasets,and knowledge transfer.In particular,we focus on new training strategies and network structures that have emerged in the last few years,such as meta-learning,few-shot learning,domain adaption,and Transformer.In addition,the subjective and objective performances of various representative dehazing methods are compared on several public datasets.Further,the impact of the dehazed images on the performance of subsequent object detection tasks is analyzed and evaluated comprehensively.We also provide the computational complexity and running time of these methods.Finally,the conclusions and future tendency of single-image dehazing are drawn. |
来源
|
电子学报
,2023,51(1):231-245 【核心库】
|
DOI
|
10.12263/DZXB.20220838
|
关键词
|
单幅图像去雾
;
深度学习
;
无监督学习
;
域泛化
|
地址
|
1.
北京工业大学信息学部, 北京, 100124
2.
北京工业大学, 计算智能与智能系统北京市重点实验室, 北京, 100124
|
语种
|
中文 |
文献类型
|
综述型 |
ISSN
|
0372-2112 |
学科
|
自动化技术、计算机技术 |
基金
|
国家自然科学基金
;
北京市教育委员会科学研究计划项目资助
;
北京市自然科学基金-丰台轨道交通前沿研究联合基金
;
北京市教育委员会科技计划一般项目
|
文献收藏号
|
CSCD:7419797
|
参考文献 共
72
共4页
|
1.
Li J F. Effective data-driven technology for efficient vision-based outdoor industrial systems.
IEEE Transactions on Industrial Informatics,2020,16(7):4344-4354
|
CSCD被引
1
次
|
|
|
|
2.
郭璠. 图像去雾技术研究综述与展望.
计算机应用,2010,30(9):2417-2421
|
CSCD被引
31
次
|
|
|
|
3.
沈琛. 夜间图像去雾研究综述与展望.
电子测量与仪器学报,2020,34(11):101-114
|
CSCD被引
2
次
|
|
|
|
4.
郑凤仙. 单幅图像去雾算法研究综述.
计算机工程与应用,2022,58(3):1-14
|
CSCD被引
9
次
|
|
|
|
5.
He K M. Single image haze removal using dark channel prior.
IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353
|
CSCD被引
509
次
|
|
|
|
6.
Zhu Q S. A fast single image haze removal algorithm using color attenuation prior.
IEEE Transactions on Image Processing,2015,24(11):3522-3533
|
CSCD被引
167
次
|
|
|
|
7.
Berman D. Non-local image dehazing.
2016 IEEE Conference on Computer Vision and Pattern Recognition,2016:1674-1682
|
CSCD被引
16
次
|
|
|
|
8.
Mccartney E J. Optics of the atmosphere: Scattering by molecules and particles.
Physics Today,1977,30(5):76-77
|
CSCD被引
23
次
|
|
|
|
9.
Nayar S K. Vision in bad weather.
Proceedings of the Seventh IEEE International Conference on Computer Vision,1999:820-827
|
CSCD被引
16
次
|
|
|
|
10.
Narasimhan S G. Removing weather effects from monochrome images.
Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2001:II
|
CSCD被引
1
次
|
|
|
|
11.
Ju M Y. IDE: Image dehazing and exposure using an enhanced atmospheric scattering model.
IEEE Transactions on Image Processing,2021,30:2180-2192
|
CSCD被引
11
次
|
|
|
|
12.
Ju M Y. IDRLP: Image dehazing using region line prior.
IEEE Transactions on Image Processing,2021,30:9043-9057
|
CSCD被引
3
次
|
|
|
|
13.
Chen W T. PMS-Net: Robust haze removal based on patch map for single images.
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition,2019:11673-11681
|
CSCD被引
2
次
|
|
|
|
14.
Cai B L. DehazeNet: An end-toend system for single image haze removal.
IEEE Transactions on Image Processing,2016,25(11):5187-5198
|
CSCD被引
197
次
|
|
|
|
15.
Li B Y. AOD-Net: All-inone dehazing network.
2017 IEEE International Conference on Computer Vision,2017:4780-4788
|
CSCD被引
14
次
|
|
|
|
16.
Zhang J. FAMED-net: A fast and accurate multi-scale end-to-end dehazing network.
IEEE Transactions on Image Processing,2020,29:72-84
|
CSCD被引
13
次
|
|
|
|
17.
Zhang H. Densely connected pyramid dehazing network.
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,2018:3194-3203
|
CSCD被引
20
次
|
|
|
|
18.
Li Y N. LAP-Net: Level-aware progressive network for image dehazing.
2019 IEEE/CVF International Conference on Computer Vision,2019:3275-3284
|
CSCD被引
2
次
|
|
|
|
19.
Liu Y. Learning deep priors for image dehazing.
2019 IEEE/CVF International Conference on Computer Vision,2019:2492-2500
|
CSCD被引
1
次
|
|
|
|
20.
Li R D. Task-oriented network for image dehazing.
IEEE Transactions on Image Processing,2020,29:6523-6534
|
CSCD被引
7
次
|
|
|
|
|