基于频率与注意力机制的图像去雾算法  

Image Dehazing Algorithm Based on Frequency and Attention Mechanism

作　　者：王军[1,2] 孟儒君 程勇 WANG Jun;MENG Ru-Jun;CHENG Yong(School of Software,Nanjing University of Information Science&Technology,Nanjing 210044,China;Science and Technology Industries Division,Nanjing University of Information Science&Technology,Nanjing 210044,China)

机构地区：[1]南京信息工程大学软件学院,南京210044 [2]南京信息工程大学科技产业处,南京210044

出　　处：《计算机系统应用》2025年第1期161-170,共10页Computer Systems & Applications

基　　金：国家自然科学基金(41975183)。

摘　　要：由于大气雾和气溶胶的存在,图像能见度显著下降且色彩失真,给高级图像识别带来极大困难.现有的图像去雾算法常存在过度增强、细节丢失和去雾不充分等问题.针对过度增强和去雾不充分的问题,本文提出了一种基于频率和注意力机制的图像去雾算法(frequency and attention mechanism of the image dehazing network,FANet).该算法采用编码器-解码器结构,通过构建双分支频率提取模块获取全局和局部的高低频信息.构建频率融合模块调整高低频信息的权重占比,并在下采样过程中引入附加通道-像素模块和通道-像素注意力模块,以优化去雾效果.实验结果显示,FANet在SOTS-indoor数据集上的PSNR和SSIM分别为40.07 dB和0.9958,在SOTS-outdoor数据集上分别为39.77 dB和0.9958.同时,该算法也在HSTS和Haze4k测试集上取得了不错的结果,与其他去雾算法相比有效缓解了颜色失真和去雾不彻底等问题.Atmospheric fog and aerosols can significantly reduce visibility and distort colors in images,bringing great difficulties to advanced image recognition.Existing image dehazing algorithms often face problems such as excessive enhancement,loss of details,and insufficient dehazing.To avoid excessive enhancement and insufficient dehazing,this study proposes an image dehazing algorithm based on frequency and attention mechanisms.The algorithm adopts an encoder-decoder structure and constructs a dual-branch frequency extraction module to obtain both global and local high and low-frequency information.A frequency fusion module is then constructed to adjust the weight proportions of the high and low-frequency information.To optimize the dehazing effect,the algorithm introduces an additional channelpixel module and a channel-pixel attention module during down sampling.Experimental results show that FANet achieves a PSNR of 40.07 dB and an SSIM of 0.9958 on the SOTS-indoor dataset,and a PSNR of 39.77 dB and an SSIM of 0.9958 on the SOTS-outdoor dataset.The proposed algorithm also achieves good results on the HSTS and Haze4k test sets.It effectively alleviates color distortion and incomplete dehazing compared with other dehazing algorithms.

关 键 词：图像去雾 双分支频率提取模块 注意力机制 特征融合 编码器-解码器结构 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]