ZHANG Jinlong， YANG Yan
（School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China）
Abstract： Convolutional neural network is developing rapidly in image processing. Most image dehazing algorithms only focus on dehazing but neglect the overall quality of dehazing image, which leads to problems such as loss of information blurred texture, etc. To solve these problems, we propose a dehazing and enhancement convolutional neural network. Hazy image and clear image are obtained by encoding and decoding. Enhancement network is used to restore the texture and details of dehazing image. Experiments show that the proposed method has excellent results in subjective evaluation and quality indexes. Haze can be removed more thoroughly, and images with clearer details and texture can be obtained.
Key words： image dehazing; hazy features extraction; texture restoration; enhancement network; adaptive residual; channel attention
References
［1］HE K M, SUN J, TANG X O, et al. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2011, 33(12): 2341-2353.
［2］XU Y, GUO X, WANG H, et al. Single image haze removal using light and dark channel prior//IEEE International Conference on Communications, Jul. 27-29, 2016, Chengdu, China. New York: IEEE, 2016: 1-6.
［3］YANG Y, WANG Z W. Haze removal: push DCP at the edge. IEEE Signal Processing Letters, 2020, 27: 1405-1409.
［4］MENG G, WANG Y, DUAN J, et al. Efficient image dehazing with boundary constraint and contextual regularization//IEEE International Conference on Computer Vision, Dec. 1-8, 2013, Sydney, Austrilia. New York: IEEE, 2014: 617-624.
［5］SUN W, WANG H, SUN C, et al. Fast single image haze removal via local atmospheric light veil estimation. Computers & Electrical Engineering, 2015, 46: 371-383.
［6］MEI W, LI X. Singleimage dehazing using dark channel fusion and haze density weight//IEEE International Conference on Electronics Information and Emergency Communication, Jul. 12-14, 2019, Beijing, China. New York: IEEE, 2019: 579-585.
［7］BI G L, REN J, FU T, et al. Image dehazing based on accurate estimation of transmission in the atmospheric scattering model. IEEE Photonics Journal,.2017, 9(4): 1-18.
［8］JACKSON J, KUN S, AGYEKUM K O, et al. A fast single-image dehazing algorithm based on dark channel prior and Rayleigh scattering. IEEE Access, 2020, 8: 73330-73339.
［9］CAI B L, XU X, JIA K, et al. Dehaze-Net: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 2016, 25(11): 5187-5198.
［10］REN W Q, LIU S, ZHANG H, et al. Single image dehazing via multi-scale convolutional neural networks with holistic edges//The 14th Conference on Computer Vision, Oct. 8-10, 2016, Amsterdan, Netherlands. Amsterdan: Springer, 2016: 154-169.
［11］REN W Q, MA L, ZHANG J W, et al. Gated fusion network for single image dehazing//IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 18-23, Salt Lake City, USA. New York: IEEE, 2018, 3253-3261.
［12］LI B Y, PENG X, WANG Z, et al. AOD-Net: All-in-one dehazing network//IEEE International Conference on Computer Vision, Oct. 22-29, 2017, Venice, Italy. New York: IEEE, 2017: 4780-4788.
［13］QIAN W, ZHOU C, ZHANG D, et al. CIASM-Net: A novel convolutional neural network for dehazing image//IEEE 5th International Conference on Computer and Communication Systems, May 15-177, 2020, Shanghai, China. New York: IEEE, 2020: 329-333.
［14］ZHU Q, MAI J, SHAO L, et al. A fast single image haze removal algorithm using color attenuation prior. IEEE Transactions on Image Processing, 2015, 24(11): 3522-3533.
［15］LIU R, FAN X, HOU M, et al. Learning aggregated transmission propagation networks for haze removal and beyond. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(10): 2973-2986.
［16］LI C, GUO C, GUO J,et al. PDR-Net: Perception-inspired single image dehazing network with refinement. IEEE Transactions on Multimedia, 2020, 22(3): 704-716.
［17］ZHANG J, TAO D. FAMED-Net: Afast and accurate multi-scale end-to-end dehazing network. IEEE Transactions on Image Processing, 2020, 29(1): 72-84.
［18］WANG A, WANG W, LIu J, et al. AIP-Net: Image-to-image single image dehazing with atmospheric illumination prior. IEEE Transactions on Image Processing, 2019, 28(1): 381-393.
［19］LI R, PAN J, HE M, et al. Task-oriented network for image dehazing//IEEE Transactions on Image Processing, 2020, 29: 6523-6534.
［20］YANG H, FU Y. Wavelet u-net and the chromatic adaptation transform for single image dehazing//IEEE International Conference on Image Processing, Sept. 22-25, 2019, Taipei, China. New York: IEEE, 2019: 2736-2740.
［21］JU Q, LI C, SANG Q, et al. Single sea surface image dehazing using multi-scale cascaded convolutional neural network//International Symposium in Sensing and Instrumentation in IoT Era, Setp. 6-7, 2018, Shanghai, China. New York: IEEE, 2018: 1-5.
［22］QIN X, WANG Z, BAI Y, et al. FFA-Net:Feature fusion attention network for single image dehazing. Association for the Advance of Artificial Intelligence, 2020: 11908-11915.
［23］HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition//IEEE Conference on Computer Vision & Pattern Recognition, Jun. 27-30, 2016, Las Vegas. USA. New York: IEEE, 2016: 770-778.
［24］SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition. (2014-09-14)［2020-04-19］. https://doi.org/10.48550/arXiv.1409.1556.
［25］MIN X K, ZHAI G T, GU K, et al. Quality evaluation of image dehazing methods using synthetic hazy images. IEEE Transactions on Multimedia, 2019, 21(9): 2319-2333.
基于雾层特征提取与增强网络的端到端去雾算法
张金龙， 杨燕
（兰州交通大学 电子与信息工程学院， 甘肃 兰州 730070）
摘要:卷积神经网络在图像处理中发展迅速。 大多数图像去雾算法仅专注于去雾， 忽略了去雾图像的整体质量， 进而导致诸如信息丢失和纹理模糊等问题。 为此， 提出了一种去雾和增强卷积神经网络。 通过编码和解码获得雾层图像和一阶段去雾图像， 增强网络用于恢复去雾图像的纹理和细节。 实验表明， 该方法在主观评价和质量指标上均具有优异的效果， 获得了去雾程度更加彻底、 细节和纹理更加清晰的去雾图像， 有效地解决了信息丢失和纹理模糊的问题。
关键词:图像去雾； 雾层提取； 纹理恢复； 增强网络； 自适应残差； 通道注意力
引用格式：ZHANG Jinlong， YANG Yan． Single image dehazing based on hazy features extraction and enhancement network． Journal of Measurement Science and Instrumentation， 2023， 14（1）： 45-54. DOI： 10．3969／j．issn．1674-8042．2023．01．006
[full text view]
