计算机科学 ›› 2022, Vol. 49 ›› Issue (5): 50-57.doi: 10.11896/jsjkx.210400093
范新南1, 赵忠鑫2, 严炜1, 严锡君2, 史朋飞1
FAN Xin-nan1, ZHAO Zhong-xin2, YAN Wei1, YAN Xi-jun2, SHI Peng-fei1
摘要: 针对传统图像去雾算法容易受到先验知识制约以及颜色失真等问题,提出了一种结合注意力机制的多尺度特征融合图像去雾算法。该算法首先通过下采样操作得到多个尺度的特征图,然后在不同尺度的特征图之间采用跳跃连接的方式将编码器部分的特征图与解码器部分的特征图连接起来以进行特征融合。同时,在网络中加入一个由通道注意力子模块和像素注意力子模块组成的特征注意力模块来控制不同通道与像素的重要性,这种特征注意力模块让网络更加关注细节信息和重要特征,因此能取得更好的去雾效果。为了验证所提算法的有效性,首先在RESIDE数据集上将所提算法与5种流行的去雾算法进行定性与定量对比实验。实验结果表明,所提算法能比较完全地除雾,而且对图像色彩的保持度较好;同时,在两个评价指标峰值信噪比(Peak Signal to Noise Ratio,PSNR)和结构相似性(Structure Similarity,SSIM)上的平均值分别为28.83 dB和0.957 5,相较于对比算法中性能位居第二的模型分别提高了2.23 dB和0.017 2。然后在MSD数据集以及真实图像上将所提算法与5种对比算法进行了定性对比实验。实验结果进一步证明了所提算法的去雾性能以及色彩保持度良好。
中图分类号:
[1]GAO Z Z,WEI W B,PAN Z K,et al.Image dehazing combining dark channel prior and Hessian regular term[J].Journal of Graphics,2020,41(1):73-80. [2]CHEN Y,GUO H G,AI Y P.Single image dehazing method based on multi-scale convolution neural network[J].Acta Optica Sinica,2019,39(10):1-10. [3]LENG J W,LI P.Single image defogging algorithm based onhigh-order markov random fields[J].Journal of Graphics,2017,38(5):745-753. [4]LI B Y,REN W Q,FU D P,et al.Benchmarking single-image dehazing and beyond[J].IEEE Transactions on Image Proces-sing,2018,28(1):492-505. [5]XIAO M X,LU C H,WEI H C,et al.Study on monitoring technology of straw burning based on UAV aerial image dehazing enhancement algorithm[J].Journal of Electronic Measurement and Instrumentation,2017:31(4):543-548. [6]ZHANG H,PATEL V M.Densely connected pyramid dehazing network[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE Press,2018:3194-3203. [7]CHU G S,SONG Y L,LI X C,et al.Near infrared dehazed imaging system based on SCMOS sensor[J].Chinese Journal of Scientific Instrument,2014,35(6):138-141. [8]WU J W,YU Z C,LI Z Y,et al.A two-stage image dehazing network based on deep learning[J].Computer Applications and Software,2020,37(4):197-202. [9]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. [10]MENG G F,WANG Y,DUAN J Y,et al.Efficient image deha-zing with boundary constraint and contextual regularization[C]//2013 IEEE International Conference on Computer Vision.Sydney:IEEE Press,2013:617-624. [11]ZHU Q S,MAI J M,SHAO L.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):3522-3533. [12]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. [13]REN W Q,LIU S,ZHANG H,et al.Single image dehazing via multi-scale convolutional neural networks[C]//2016 European Conference on Computer Vision.Amsterdam:Springer Press,2016:154-169. [14]LI B Y,PENG X L,WANG Z Y,et al.Aod-net:all-in-one dehazing network[C]//2017 IEEE International Conference on Computer Vision.Venice:IEEE Press,2017:4780-4788. [15]REN W Q,MA L,ZHANG J W,et al.Gated fusion network for single image dehazing[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE Press,2018:3253-3261. [16]CHEN D D,HE M M,FAN Q N,et al.Gated context aggregation network for image dehazing and deraining[C]//2019 IEEE Winter Conference on Applications of Computer Vision.Waikoloa Village:IEEE Press,2019:1375-1383. [17]CHOI H,LIM H,YU S,et al.Haze removal of multispectral remote sensing imagery using atmospheric scattering model-based haze thickness map[C]//2020 IEEE International Conference on Consumer Electronics-Asia.Seoul:IEEE Press,2020:1-2. [18]TANG K T,YANG J C,WANG J.Investigating haze-relevant features in a learning framework for image dehazing[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE Press,2014:2995-3002. [19]HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE Press,2016:770-778. [20]CHEN L,ZHANG H W,XIAO J,et al.Sca-cnn:Spatial andchannel-wise attention in convolutional networks for image captioning[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE Press,2017:6298-6306. [21]SILBERMAN N,HOIEM D,KOHLI P,et al.Indoor segmentation and support inference from rgbd images[C]//12th Euro-pean Conference on Computer Vision.Florence:Springer Press,2012:746-760. [22]HE T,ZHANG Z,ZHANG H,et al.Bag of tricks for image classification with convolutional neural networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE Press,2019:558-567. |
[1] | 周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085 |
[2] | 戴禹, 许林峰. 基于文本行匹配的跨图文本阅读方法 Cross-image Text Reading Method Based on Text Line Matching 计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032 |
[3] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
[4] | 熊丽琴, 曹雷, 赖俊, 陈希亮. 基于值分解的多智能体深度强化学习综述 Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization 计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112 |
[5] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
[6] | 汪鸣, 彭舰, 黄飞虎. 基于多时间尺度时空图网络的交通流量预测模型 Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction 计算机科学, 2022, 49(8): 40-48. https://doi.org/10.11896/jsjkx.220100188 |
[7] | 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153 |
[8] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
[9] | 闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042 |
[10] | 姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046 |
[11] | 张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036 |
[12] | 曾志贤, 曹建军, 翁年凤, 蒋国权, 徐滨. 基于注意力机制的细粒度语义关联视频-文本跨模态实体分辨 Fine-grained Semantic Association Video-Text Cross-modal Entity Resolution Based on Attention Mechanism 计算机科学, 2022, 49(7): 106-112. https://doi.org/10.11896/jsjkx.210500224 |
[13] | 徐鸣珂, 张帆. Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法 Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition 计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085 |
[14] | 孟月波, 穆思蓉, 刘光辉, 徐胜军, 韩九强. 基于向量注意力机制GoogLeNet-GMP的行人重识别方法 Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism 计算机科学, 2022, 49(7): 142-147. https://doi.org/10.11896/jsjkx.210600198 |
[15] | 金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190 |
|