两阶段特征迁移图像去雾算法

doi:10.3778/j.issn.1002-8331.2309-0455

摘要/Abstract

摘要： 针对常见去雾算法处理后图像容易产生伪影、颜色失真以及对非均匀雾气影响下图像的去雾效果不理想等问题，提出了两阶段特征迁移图像去雾算法，基于编解码器结构实现图像去雾。第一阶段将清晰图像送入特征学习网络，通过混合注意力机制学习清晰图像空间结构信息与色彩规律。第二阶段利用特征迁移损失，将特征学习网络中学习到的清晰图像特征知识迁移至特征细化图像去雾网络中，并通过多尺度特征提取模块与全局特征细化块对图像上下文信息进行有效提取与融合。最后将两阶段输出进行特征融合，恢复清晰无雾图像。实验结果表明，该算法在RESIDE数据集以及真实非均匀雾天图像中具备较好的去雾效果，且处理后图像色彩合理，更加符合人类视觉感知。

关键词: 图像去雾, 卷积神经网络, 特征迁移, 特征学习, 混合注意力机制, 全局特征细化

Abstract: To solve the problems such as artifacts, color distortion and unsatisfactory dehazing effect on images under the influence of non-uniform fog after image processing by common dehazing algorithms, a two-stage feature transfer image dehazing algorithm is proposed, which is implemented based on the encoder-decoder structure. In the first stage, the clear image is sent to the feature learning network, and the spatial structure information and color rules of the clear image are learned through the hybrid attention mechanism. In the second stage, the feature transfer loss is used to transfer the clear image feature knowledge learned in the feature learning network to the feature refinement image dehazing network. At the same time, the image context information is effectively extracted and fused through the multi-scale feature extraction module and the global feature refinement block. Finally, the output of the two stages is fused to restore a clear and dehazing image. The experimental results show that the algorithm has a good dehazing effect in the RESIDE dataset and real non-uniform foggy images, and the color of the processed image is reasonable and more in line with human visual perception.

Key words: image dehazing, convolutional neural network, feature transfer, feature learning, hybrid attention mechanism, global feature refinement

袁姮, 颜廷昊, 张晟翀. 两阶段特征迁移图像去雾算法[J]. 计算机工程与应用, 2025, 61(4): 241-252.

YUAN Heng, YAN Tinghao, ZHANG Shengchong. Two-Stage Feature Transfer Image Dehazing Algorithm[J]. Computer Engineering and Applications, 2025, 61(4): 241-252.

参考文献

[1] LAND E H. The retinex theory of color vision[J]. Scientific America, 1977, 237(6): 108-128.
[2] LAND E H. The retinex[J]. American Scientist, 1964, 52(2): 247-264.
[3] SEOW M J, ASARI V K. Ratio rule and homomorphic filter for enhancement of digital colour image[J]. Neurocomputing, 2006, 69(7/8/9): 954-958.
[4] STARK J A. Adaptive image contrast enhancement using generalizations of histogram equalization[J]. IEEE Transactions on Image Processing, 2000, 9(5): 889-896.
[5] MALLAT S G. A theory for multiresolution signal decomposition: the wavelet representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674-693.
[6] KAPLAN N H. Real-world image dehazing with improved joint enhancement and exposure fusion[J]. Journal of Visual Communication and Image Representation, 2023, 90: 103720.
[7] HE K, SUN J, TANG X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.
[8] NARASIMHAN S G, NAYAR S K. Vision and the atmosphere[J]. International Journal of Computer Vision, 2002, 48(3): 233-254.
[9] NARASIMHAN S G, NAYAR S K. Contrast restoration of weather degraded images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(6): 713-724.
[10] TANG K, YANG J, WANG J. Investigating haze-relevant features in a learning framework for image dehazing[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 2995-3002.
[11] 金天虎, 陶砚蕴, 李佐勇. 基于超像素图像分割的暗通道先验去雾改进算法[J]. 电子学报, 2023, 51(1): 146-159.
JIN T H, TAO Y Y, LI Z Y. An improved dark channel prior dehazing algorithm based on superpixel image segmentation[J]. Acta Electronica Sinica, 2023, 51(1): 146-159.
[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] LI B Y, PENG X L, WANG Z Y, et al. AOD-Net: all-in-one dehazing network[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 4780-4788.
[14] QIN?X, WANG?Z?L, BAI Y?C, et al. FFA-net: feature fusion attention network for single image dehazing[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 11908-11915.
[15] ZHENG Z, REN W, CAO X, et al. Ultra-high-definition image dehazing via multi-guided bilateral learning[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 16180-16189.
[16] FENG T, WANG C S, CHEN X W, et al. URNet: a U-Net based residual network for image dehazing[J]. Applied Soft Computing, 2021, 102: 106884.
[17] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
[18] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778.
[19] JIA T Y, LI J F, ZHUO L, et al. Effective meta-attention dehazing networks for vision-based outdoor industrial systems[J]. IEEE Transactions on Industrial Informatics, 2022, 18(3): 1511-1520.
[20] REN W Q, MA L, ZHANG J W, et al. Gated fusion network for single image dehazing[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 3253-3261.
[21] QU Y Y, CHEN Y Z, HUANG J Y, et al. Enhanced Pix2pix dehazing network[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 8152-8160.
[22] 但志平, 方帅领, 孙航, 等. 基于双判别器异构CycleGAN框架下多阶通道注意力校准的室外图像去雾[J]. 电子学报, 2023, 51(9): 2558-2571.
DAN Z P, FANG S L, SUN H, et al. Outdoor image dehazing based on multi-order channel attention calibration using a dual-discriminator heterogeneous CycleGAN framework[J]. Acta Electronica Sinica, 2023, 51(9): 2558-2571.
[23] ZHENG Y, SU J, ZHANG S, et al. Dehaze-AGGAN: unpaired remote sensing image dehazing using enhanced attention-guide generative adversarial networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5630413.
[24] YANG Y, WANG C, LIU R, et al. Self-augmented unpaired image dehazing via density and depth decomposition[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 2027-2036.
[25] WANG P, CHEN P F, YUAN Y, et al. Understanding convolution for semantic segmentation[C]//Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2018: 1451-1460.
[26] LI B Y, REN W Q, FU D P, et al. Benchmarking single image dehazing and beyond[J]. IEEE Transactions on Image Processing, 2018, 28(1): 492-505.
[27] SILBERMAN N, HOIEM D, KOHLI P, et al. Indoor segmentation and support inference from RGBD images[C]//Proceedings of the 12th European Conference on Computer Vision. Berlin, Heidelberg: Springer, 2012: 746-760.