基于生成对抗网络的多特征融合去雾技术  

Multiple-feature fusion based generative adversarial network for image dehazing

作　　者：司亚中 张旭龙 杨帆[2] 王健宗 程宁 肖京 SI Yazhong;ZHANG Xulong;YANG Fan;WANG Jianzong;CHENG Ning;XIAO Jing(Ping An Technology(Shenzhen)Co.,Ltd.,Shenzhen 518063,China;Hebei University of Technology,Tianjin 300401,China)

机构地区：[1]平安科技(深圳)有限公司,广东深圳518063 [2]河北工业大学,天津300401

出　　处：《大数据》2024年第4期77-88,共12页Big Data Research

基　　金：广东省重点领域研发计划“新一代人工智能”重大专项(No.2021B0101400003)。

摘　　要：为提高图像清晰度,解决传统图像在去雾过程中存在的特征提取困难、去雾不彻底等问题,提出一种基于生成对抗网络的多特征融合端到端去雾网络。该网络由生成器和判别器组成,生成器采用编解码结构,通过多特征提取融合(MFEF)块提取多种感受野下的高维表征信息。判别器使用一系列卷积计算对生成图像和清晰图像进行特征差异分析,引导生成器输出更加真实的去雾图像。实验结果表明,该算法在有效消除雾霾干扰的同时,能够最大限度地保留图像的原始色调。与现有方法相比,该算法在峰值信噪比、结构相似性客观评价指标上分别提升了2.588 dB、2.66%。To enhance image clarity and address the difficulties in feature extraction and incomplete haze removal in traditional image dehazing processes,a multi-feature fusion based generative adversarial dehazing network is proposed.The network adopts a generative adversarial approach and consists of a generator and a discriminator.The generator utilizes an encoder-decoder structure,and extracts haze-related feature maps from multiple receptive fields by a multi-feature extraction fusion(MFEF)block.The discriminator uses a series of convolutional calculations to analyze the feature differences between the generated images and the clear images,guiding the generator to output move realistic dehazing images.The experimental images show that the proposed method can effectively eliminate haze interference while preserving the original color tone of the image to the greatest extent possible.The experimental results demonstrate that the dehazed images produced by our algorithm have improved peak signal-to-noise ratio and structural similarity with an average of 2.588 dB and 2.66%respectively,compared with existing methods.

关 键 词：图像处理 图像去雾 深度学习 生成对抗 多特征融合 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]