基于DBAFFNet的低照度图像增强

doi:10.3969/j.issn.0255-8297.2023.03.009

应用科学学报 ›› 2023, Vol. 41 ›› Issue (3): 476-487.doi: 10.3969/j.issn.0255-8297.2023.03.009

基于DBAFFNet的低照度图像增强

罗凡, 熊邦书, 余磊, 汪婉灵

南昌航空大学图像处理与模式识别江西省重点实验室, 江西南昌 330063

收稿日期:2022-07-19 出版日期:2023-05-30 发布日期:2023-06-16
通信作者: 熊邦书,教授,研究方向为模式识别、智能信号处理和图形处理。E-mail:xiongbs@126.com E-mail:xiongbs@126.com
基金资助:
国家自然科学基金(No. 61866027)；江西省重点研发计划基金(No. 20212BBE53017)；江西省自然科学基金(No. 20202BAB202016)资助

Low-Light Image Enhancement Based on DBAFFNet

LUO Fan, XIONG Bangshu, YU Lei, WANG Wanling

Key Laboratory of Image Processing and Pattern Recognition of Jiangxi Province, Nanchang Hangkong University, Nanchang 330063, Jiangxi, China

Received:2022-07-19 Online:2023-05-30 Published:2023-06-16

摘要/Abstract

摘要： 针对当前低照度图像增强后存在色偏、细节损失和噪声放大的问题，提出了基于双分支自适应特征融合网络的低照度图像增强方法。首先，设计自适应特征融合模块，在深层特征中融合更多细节和颜色信息；其次，构建通道及空间注意力模块，使网络着重于图像细节和颜色的恢复；最后，根据 Retinex 理论设计 Poisson-Retinex 损失函数，抑制图像的噪声，从而提高图像的增强效果。在多个数据集上的主观和客观对比结果表明，所提方法不仅能恢复增强图像的颜色和细节，而且能更好地抑制噪声，从而获得良好的增强效果。

关键词: 低照度图像增强, 自适应特征融合模块, 注意力模块, Retinex

Abstract: To solve the problems of color cast, detail loss and noise amplification after lowlight image enhancement, an improved low-light image enhancement method is proposed based on dual-branch adaptive feature fusion network (DBAFFNet). Firstly, the adaptive feature fusion (AFF) module is designed to fuse more details and color information into deep features. Secondly, the channel and spatial attention (CASA) module is established to focus on the restoration of image details and color. Finally, a Poisson-Retinex loss function based on Retinex theory is designed to suppress noise of the image, thereby improving the enhancement effect of images. The results of subjective and objective comparisons on multiple datasets demonstrate that the proposed method not only restores the color and details of the enhanced image, but also suppress the noise better, and achievea good enhancement effect.

Key words: low-light image enhancement, adaptive feature fusion module, attention module, Retinex

中图分类号:

TP391

罗凡, 熊邦书, 余磊, 汪婉灵. 基于DBAFFNet的低照度图像增强[J]. 应用科学学报, 2023, 41(3): 476-487.

LUO Fan, XIONG Bangshu, YU Lei, WANG Wanling. Low-Light Image Enhancement Based on DBAFFNet[J]. Journal of Applied Sciences, 2023, 41(3): 476-487.

参考文献

[1] 欧巧凤, 肖佳兵, 谢群群, 等. 基于深度学习的车检图像多目标检测与识别[J]. 应用科学学报, 2021, 39(6): 939-951. Ou Q F, Xiao J B, Xie Q Q, et al. Multi-target detection and recognition for vehicle inspection images based on deep learning [J]. Journal of Electronics & Information Technology, 2021, 39(6): 939-951. (in Chinese)
[2] 张晓龙, 王庆伟, 李尚滨. 基于强化学习的多模态场景人体危险行为识别方法[J]. 应用科学学报, 2021, 39(4): 605-614. Zhang X L, Wang Q W, Li S B. Recognition method of human dangerous behavior in multimodal scenes using reinforcement learning [J]. Journal of Electronics & Information Technology, 2021, 39(4): 605-614. (in Chinese)
[3] Abdullah-Al-Wadud M, Kabir M H, Dewan M A A, et al. A dynamic histogram equalization for image contrast enhancement [J]. IEEE Transactions on Consumer Electronics, 2007, 53(2): 593-600.
[4] Liu S X, Long W, He L, et al. Retinex-based fast algorithm for low-light image enhancement [J]. Entropy, 2021, 23(6): 746-746.
[5] Fu X, Zeng D, Huang Y, et al. A variational framework for single low light image enhancement using bright channel prior [C]//Proceedings of 2013 IEEE Global Conference on Signal and Information Processing, 2013: 1085-1088.
[6] Park S, Yu S, Moon B, et al. Low-light image enhancement using variational optimizationbased Retinex model [J]. IEEE Transactions on Consumer Electronics, 2017, 63(2): 178-184.
[7] Ren X T, Yang W H, Cheng W H, et al. LR3M: robust low-light enhancement via low-rank regularized Retinex model [J]. IEEE Transactions on Image Processing, 2020, 29: 5862-5876.
[8] Lore K G, Akintayo A, Sarkar S. LLNet: a deep autoencoder approach to natural low-light image enhancement [J]. Pattern Recognition, 2017, 61: 650-662.
[9] 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.
[10] Zhang Y H, Zhang J W, Guo X J. Kindling the darkness: a practical low-light image enhancer [C]//The 27th ACM International Conference on Multimedia, 2019: 1632-1640.
[11] Lu K, Zhang L H. TBEFN: a two-branch exposure-fusion network for low-light image enhancement [J]. IEEE Transactions on Multimedia, 2020, 23: 4093-4105.
[12] Wang L W, Liu Z S, Siu W C, et al. Lightening network for low-light image enhancement [J]. IEEE Transactions on Image Processing, 2020, 29: 7984-7996.
[13] 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 2020), 2020: 1777-1786.
[14] Kong X Y, Liu L, Qian Y S. Low-light image enhancement via Poisson noise aware Retinex model [J]. IEEE Signal Processing Letters, 2021, 28: 1540-1544.
[15] Ng M K, Wang W. A total variation model for Retinex [J]. SIAM Journal on Imaging Sciences, 2011, 4(1): 345-365.
[16] Wei C, Wang W J, Yang W H, et al. Deep Retinex decomposition for low-light enhancement [C]//British Machine Vision Conference (BMVC 2018), 2018: 1-10.
[17] Mittal A, Soundararajan R, Bovik A C. Making a “completely blind” image quality analyzer [J]. IEEE Signal Processing Letters, 2013, 20(3): 209-212.
[18] Wang S H, Zheng J, Hu H M, et al. Naturalness preserved enhancement algorithm for nonuniform illumination images [J]. IEEE Transactions on Image Processing, 2013, 22(9): 3538- 3548.
[19] Gu K, Tao D C, Qiao J F, et al. Learning a no-reference quality assessment model of enhanced images with big data [J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 29(4): 1301-1313.
[20] Lee C, Kim C S. Contrast enhancement based on layered difference representation [C]//201219th IEEE International Conference on Image Processing, 2012: 965-968.
[21] Loh Y P, Chan C S. Getting to know low-light images with the exclusively dark dataset [J]. Computer Vision and Image Understanding, 2019, 178: 30-42.
[22] Fu X Y, Zeng D L, Huang Y, et al. A fusion-based enhancing method for weakly illuminated images [J]. Signal Processing, 2016, 129: 82-96.
[23] Guo X J, Li Y, Ling H B. LIME: low-light image enhancement via illumination map estimation [J]. IEEE Transactions on Image Processing, 2017, 26(2): 982-993.
[24] Zhao Z J, Xiong B S, Wang L, et al. RetinexDIP: a unified deep framework for low-light image enhancement [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 32(3): 1076-1088.
[25] Liang D, Li L, Wei M Q, et al. Semantically contrastive learning for low-light image enhancement [C]//Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2022), 2022: 1555-1563.

基于DBAFFNet的低照度图像增强

Low-Light Image Enhancement Based on DBAFFNet

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	张涵, 秦昆, 毕奇, 张晔, 许凯. 注意力引导的三维卷积网络用于遥感场景变化检测[J]. 应用科学学报, 2021, 39(2): 272-280.
[2]	付仲良童春芽邵世维. 采用FFTW的Retinex及其在扫描地形图匀光中的应用[J]. 应用科学学报, 2010, 28(3): 297-300.