1.西安建筑科技大学 理学院,陕西 西安 710055
[ "陈清江(1966-),男,河南信阳人,博士,教授,硕士生导师,2006年于西安交通大学获博士学位,主要从事小波分析,图像处理与信号处理方面的研究。E-mail:qjchen66xytu@126.com" ]
[ "顾 媛(1998-),女,陕西汉中人,硕士研究生,主要从事图像处理方面的研究。E-mail:2544020739@qq.com" ]
扫 描 看 全 文
陈清江, 顾媛. 多通道融合注意力网络的低照度图像增强[J]. 光学精密工程, 2023,31(14):2111-2122.
CHEN Qingjiang, GU Yuan. Low-light image enhancement algorithm based on multi-channel fusion attention network[J]. Optics and Precision Engineering, 2023,31(14):2111-2122.
陈清江, 顾媛. 多通道融合注意力网络的低照度图像增强[J]. 光学精密工程, 2023,31(14):2111-2122. DOI: 10.37188/OPE.20233114.2111.
CHEN Qingjiang, GU Yuan. Low-light image enhancement algorithm based on multi-channel fusion attention network[J]. Optics and Precision Engineering, 2023,31(14):2111-2122. DOI: 10.37188/OPE.20233114.2111.
针对低照度图像亮度低、对比度低、颜色失真以及现有增强算法大多没有区别处理不同的通道,不利于提取多层次特征的问题,提出多通道融合注意力网络的低照度图像增强算法。首先,通过将八度卷积(Octave Convolution, OctConv)引入通道拆分后的残差结构中提出多层级特征提取模块;其次,利用注意力机制与交叉残差结构提出跨尺度特征注意模块;再次,通过大小与通道数不同的模块堆叠的方式获取多层次信息;最后,在通道维度上进行特征融合,并通过重建模块获得输出。实验结果表明,与RISSNet算法相比,在真实图像上的峰值信噪比与结构相似度分别由27.001 6 dB和0.889 2提升到27.978 1 dB和0.925 5。所提算法在峰值信噪比、结构相似度、均方误差、视觉信息保真度4种客观评价指标上均获得了最好的结果。该算法能够有效地提高低照度图像的亮度及对比度,且图像纹理细节及色彩保持较好。
Low-light images have low brightness, low contrast, and color distortion, and most existing enhancement algorithms do not deal with different channels differently, which is not conducive to the extraction of multi-level features. Therefore, this study proposes a low-light image enhancement algorithm based on a multi-channel fusion attention network. Firstly, we introduced octave convolution (OctConv) into the residual structure after channel splitting and propose a multi-level feature extraction module. Secondly, we proposed a cross-scale feature attention module using an attention mechanism and cross-residual structure. Thirdly, we obtained multi-level information by stacking modules with different sizes and channels. Finally, we performed feature fusion in the channel dimension and obtained the final output through the reconstruction module. The experimental results showed that compared with the RISSNet algorithm, the peak signal-to-noise ratio and structural similarity of real images were improved from 27.001 6 dB and 0.889 2 to 27.978 1 dB and 0.925 5, respectively. The proposed algorithm achieved the best results in four objective evaluation indicators: peak signal-to-noise ratio, structural similarity, mean squared error, and visual information fidelity. The algorithm can effectively improve the brightness and contrast of low-light images with well-maintained image textures and colors.
图像增强低照度注意力机制多通道八度卷积
image enhancementlow lightattention mechanismmulti-channelOctConv
ELIZA JACOB J, SARITHA S. Video Enhancement and Low-Resolution Facial Image Reconstruction for Crime Investigation[M]. Intelligent Data Communication Technologies and Internet of Things. Singapore: Springer Singapore, 2021: 773-788. doi: 10.1007/978-981-15-9509-7_63http://dx.doi.org/10.1007/978-981-15-9509-7_63
MA Y H, LIU J, LIU Y H, et al. Structure and illumination constrained GAN for medical image enhancement[J]. IEEE Transactions on Medical Imaging, 2021, 40(12): 3955-3967. doi: 10.1109/tmi.2021.3101937http://dx.doi.org/10.1109/tmi.2021.3101937
朱均安, 陈涛, 曹景太. 基于显著性区域加权的相关滤波目标跟踪[J]. 光学 精密工程, 2021, 29(2):363-373. doi: 10.37188/OPE.20212902.0363http://dx.doi.org/10.37188/OPE.20212902.0363
ZHU J A, CHEN T, CAO J T., CHEN T, CAO J T. Salient region weighted correlation filter for object tracking[J]. Opt. Precision Eng., 2021, 29(2):363-373.(in Chinese). doi: 10.37188/OPE.20212902.0363http://dx.doi.org/10.37188/OPE.20212902.0363
杨艳春, 裴佩佩, 党建武, 等. 基于交替梯度滤波器和改进PCNN的红外与可见光图像融合[J]. 光学 精密工程, 2022, 30(9):1123-1138. doi: 10.37188/OPE.20223009.1123http://dx.doi.org/10.37188/OPE.20223009.1123
YANG Y C, PEI P P, DANG J W, et al. Infrared and visible image fusion based on alternating gradient filter and improved PCNN[J]. Opt. Precision Eng., 2022, 30(9):1123-1138.(in Chinese). doi: 10.37188/OPE.20223009.1123http://dx.doi.org/10.37188/OPE.20223009.1123
HUMMEL R. Image enhancement by histogram transformation[J]. Computer Graphics and Image Processing, 1977, 6(2): 184-195. doi: 10.1016/s0146-664x(77)80011-7http://dx.doi.org/10.1016/s0146-664x(77)80011-7
PIZER SM, AMBURN EP, AUSTIN JD, et al. Adaptive histogram equalization and its variations[J]. Computer Vision, Graphics, and Image Processing, 1987, 39(3): 355-368. doi: 10.1016/s0734-189x(87)80186-xhttp://dx.doi.org/10.1016/s0734-189x(87)80186-x
REZA A M. Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement[J]. Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 2004, 38(1): 35-44. doi: 10.1023/b:vlsi.0000028532.53893.82http://dx.doi.org/10.1023/b:vlsi.0000028532.53893.82
LAND E H. The retinex theory of color vision[J]. Scientific American, 1977, 237(6): 108-128. doi: 10.1038/scientificamerican1277-108http://dx.doi.org/10.1038/scientificamerican1277-108
JOBSON D J, RAHMAN Z, WOODELL G A. Properties and performance of a center/surround retinex[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 1997, 6(3): 451-462. doi: 10.1109/83.557356http://dx.doi.org/10.1109/83.557356
JOBSON D J, RAHMAN Z, WOODELL G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 1997, 6(7): 965-976. doi: 10.1109/83.597272http://dx.doi.org/10.1109/83.597272
WEI C, WANG W, YANG W, et al. Deep Retinex Decomposition for Low-Light Enhancement[EB/OL]. 2018: arXiv: 1808.04560. https://arxiv.org/abs/1808.04560https://arxiv.org/abs/1808.04560
ZHANG Y H, ZHANG J W, GUO X J. Kindling the Darkness: a Practical Low-Light Image Enhancer[C]. Proceedings of the 27th ACM International Conference on Multimedia. 2125,2019, Nice, France. New York: ACM, 2019: 1632-1640. doi: 10.1145/3343031.3350926http://dx.doi.org/10.1145/3343031.3350926
GUO C L, LI C Y, GUO J C, et al. Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement[C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).13-19, 2020, Seattle, WA, USA. IEEE, 2020: 1777-1786. doi: 10.1109/cvpr42600.2020.00185http://dx.doi.org/10.1109/cvpr42600.2020.00185
JIANG Y F, GONG X Y, LIU D, et al. EnlightenGAN: deep light enhancement without paired supervision[J]. IEEE Transactions on Image Processing, 2021, 30: 2340-2349. doi: 10.1109/tip.2021.3051462http://dx.doi.org/10.1109/tip.2021.3051462
LV F F, LU F, WU J H, et al. MBLLEN: Low-Light Image/Video Enhancement Using CNNs[C]. BMVC. 2018, 220(1): 4.
潘晓英, 魏苗, 王昊, 等. 多尺度融合残差编解码器的低照度图像增强方法[J]. 计算机辅助设计与图形学学报, 2022, 34(1): 104-112. doi: 10.3724/sp.j.1089.2022.18833http://dx.doi.org/10.3724/sp.j.1089.2022.18833
PAN X Y, WEI M, WANG H, et al. A multi-scale fusion residual encoder-decoder approach for low illumination image enhancement[J]. Journal of Computer-Aided Design & Computer Graphics, 2022, 34(1): 104-112.(in Chinese). doi: 10.3724/sp.j.1089.2022.18833http://dx.doi.org/10.3724/sp.j.1089.2022.18833
ZHAO J B, CHEN H Y, ZENG S Y, et al. RISSNet: Retain low-light image details and improve the structural similarity net[J]. IET Image Processing, 2022, 16(7): 1793-1806. doi: 10.1049/ipr2.12446http://dx.doi.org/10.1049/ipr2.12446
CHEN Y P, FAN H Q, XU B, et al. Drop an octave: reducing spatial redundancy in convolutional neural networks with octave convolution[C]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV).272,2019, Seoul, Korea (South). IEEE, 2020: 3434-3443. doi: 10.1109/iccv.2019.00353http://dx.doi.org/10.1109/iccv.2019.00353
HU J, SHEN L, SUN G. Squeeze-and-Excitation Networks[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.18-23, 2018, Salt Lake City, UT, USA. IEEE, 2018: 7132-7141. doi: 10.1109/cvpr.2018.00745http://dx.doi.org/10.1109/cvpr.2018.00745
WANG Q L, WU B G, ZHU P F, et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks[C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).13-19, 2020, Seattle, WA, USA. IEEE, 2020: 11531-11539. doi: 10.1109/cvpr42600.2020.01155http://dx.doi.org/10.1109/cvpr42600.2020.01155
WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional Block Attention Module[M]. Computer Vision - ECCV 2018. Cham: Springer International Publishing, 2018: 3-19. doi: 10.1007/978-3-030-01234-2_1http://dx.doi.org/10.1007/978-3-030-01234-2_1
GAO S H, CHENG M M, ZHAO K, et al. Res2Net: a new multi-scale backbone architecture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 652-662. doi: 10.1007/978-3-030-01234-2_1http://dx.doi.org/10.1007/978-3-030-01234-2_1
SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Largescale Image Recognition[C]. Proc of the 3rd International Conference on Learning Representations. La Jolla, CA: ICLR Press, 2015: 1-14.
MANNOS J, SAKRISON D. The effects of a visual fidelity criterion of the encoding of images[J]. IEEE Transactions on Information Theory, 1974, 20(4): 525-536. doi: 10.1109/tit.1974.1055250http://dx.doi.org/10.1109/tit.1974.1055250
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: a Publication of the IEEE Signal Processing Society, 2004, 13(4): 600-612. doi: 10.1109/tip.2003.819861http://dx.doi.org/10.1109/tip.2003.819861
SHEIKH H R, BOVIK A C. Image information and visual quality[J]. IEEE Transactions on Image Processing, 2006, 15(2): 430-444. doi: 10.1109/tip.2005.859378http://dx.doi.org/10.1109/tip.2005.859378
CHEN X Y, WANG S A. Superpixel segmentation based on delaunay triangulation[C]. 2016 23rd International Conference on Mechatronics and Machine Vision in Practice (M2VIP).28-30, 2016, Nanjing, China. IEEE, 2017: 1-6. doi: 10.1109/m2vip.2016.7827311http://dx.doi.org/10.1109/m2vip.2016.7827311
CHEN C, CHEN Q F, XU J, et al. Learning to see in the dark[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.18-23, 2018, Salt Lake City, UT, USA. IEEE, 2018: 3291-3300. doi: 10.1109/cvpr.2018.00347http://dx.doi.org/10.1109/cvpr.2018.00347
0
浏览量
35
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构