基于生成对抗网络的图像自增强去雾算法  

Image Self-enhancement De-hazing Algorithm Combined with Generative Adversarial Network

作　　者：刘万军[1] 程裕茜 曲海成[1] Liu Wanjun;Cheng Yuqian;Qu Haicheng(College of Software,Liaoning Technical University,Huludao 125105,China)

机构地区：[1]辽宁工程技术大学软件学院,辽宁葫芦岛125105

出　　处：《系统仿真学报》2024年第5期1093-1106,共14页Journal of System Simulation

基　　金：国家自然科学基金面上项目(42271409);辽宁工程技术大学学科创新团队资助项目(LNTU20TD-23)。

摘　　要：针对现有去雾模型使用合成有雾图像数据集训练后容易出现过拟合的问题,提出了一种融合生成对抗网络的图像自增强去雾算法。在结合两个生成对抗网络的同时估计图像的深度信息。第一个GAN利用清晰图像学习图像加雾过程,将其生成的有雾图像作为第二个GAN的输入,指导第二个GAN如何正确去雾。为了减少图像处理前后的差异,利用一致性损失函数来优化两个网络。在图像加雾部分添加场景深度估计模块,并对散射因子进行随机采样,实现图像自增强功能,更加真实地模拟现实世界中不同浓度的雾气。该算法无需使用合成有雾图像数据集的成对信息,进一步避免过拟合问题。实验结果表明:所提算法能够取得较好的去雾效果,在主观视觉质量和客观评价指标上均有良好表现,优于同类算法。To solve the problem that existing dehazing models are prone to over fitting after training with synthetic hazy image data sets,an image self-enhancement dehazing algorithm is proposed in combination with generative adversarial network.The depth information of an image is estimated while combining two Generative Adversarial Networks.The first GAN uses a clear image to learn the process of image hazing,and then adopts the hazed image generated by it as the input of the second GAN to guide the second GAN to correct dehazing.In order to reduce the difference before and after image processing,the consistency loss function is applied to optimize two network parts.In addition,the scene depth estimation module is added to the image hazing part,and the scattering factor is randomly sampled to achieve the image self enhancement function,which can more realistically simulate fog of different concentrations in real world.The algorithm does not need to use the paired information of synthetic hazy image dataset to further avoid over fitting.Experimental results show that the proposed algorithm can achieve better dehazing effect,which has good performance in subjective visual quality and objective evaluation indicators,superior to similar algorithms.

关 键 词：图像处理 机器视觉 生成对抗网络 光学模型 图像去雾 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]