首页|基于多尺度残差和注意力机制的图像去雾算法

基于多尺度残差和注意力机制的图像去雾算法

扫码查看
原文链接
  • 万方数据
  • 维普
雾的存在严重降低了图像的质量,阻碍了后续对图像的进一步处理.针对已有去雾算法特征提取不充分等问题,提出了一种端到端的基于多尺度空洞残差块和多尺度注意力机制的图像去雾算法.首先,通过三个小尺度的卷积核进行卷积运算提取雾图的浅层特征,可以在得到较大感受野的同时降低参数量.然后,将其输入多个由多尺度残差空洞卷积特征提取模块和多尺度注意力机制模块串联组成的网络模块,多尺度空洞卷积残差特征提取模块可以提取不同感受野的雾图特征并进行不同维度的特征融合,有效解决特征尺度单一问题;多尺度注意力机制模块可合理分配不同特征的权重,并抑制无关的冗余信息.最后,把雾图中的雾特征筛减便得到去雾图的特征图,再通过卷积操作恢复出无雾图像.通过在SOTS测试集上测试,得到了比其他几种经典方法更好的视觉效果,且在PSNR和SSIM上的表现也优于其他几种经典方法.
Image dehazing algorithm based on multi-scale residual and attention mechanism
The presence of fog severely reduces the image quality and hinders further image processing as well as the corresponding feature information extraction.An end-to-end image defogging algorithm based on a multi-scale hole residual block and multi-scale attention mechanism is proposed to address the prob-lems of inadequate feature extraction of existing defogging algorithms.First,the shallow features of the fog map were extracted by three small-scale convolution kernels,which can obtain a large receptive field and reduce the number of parameters.Then,it was input into a plurality of network modules composed of a multi-scale residual hole convolution feature extraction module and multi-scale attention mechanism mod-ule in series,in which the multi-scale hole convolution residual feature extraction module could extract the fog map features of different receptive fields and fuse the features of different dimensions to effectively solve the problem of single feature scale,while the multi-scale attention mechanism module reasonably al-located the weights of different features and suppressed irrelevant redundant information.Finally,the fog features in the fog map were filtered to obtain the feature map of the defogging map,followed by restoring the fog-free image using convolution operation.By testing on the sots test set,better visual effects are ob-tained compared with other classical methods,and the performance on PSNR and SSIM is also better than other classical methods.

image defoggingresidual hole convolutionattention mechanismfeature extractiondeep learning

陈辉、牛丽丽、付辉、张天佑、席磊

展开 >

兰州理工大学电气工程与信息工程学院,甘肃兰州 730050

甘肃省科学院 自动化研究所,甘肃兰州 730000

图像去雾 残差空洞卷积 注意力机制 特征提取 深度学习

国家自然科学基金国家自然科学基金国家自然科学基金国家自然科学基金甘肃省教育厅产业支撑计划甘肃省科学院重大专项甘肃省军民融合发展专项(2023)甘肃省重点人才项目(2024)

621630236236603162363023618731162021CYZC-022023ZDZX-03

2024

兰州理工大学学报
兰州理工大学

兰州理工大学学报

CSTPCD北大核心
影响因子：0.57
ISSN：1673-5196
年,卷(期)：2024.50(2)
  • 3