基于注意力机制的单幅图像去雾算法

杜帆; 蒋品群; 宋树祥; 夏海英

Chinese

您当前的位置：

首页 >

文章列表页 >

基于注意力机制的单幅图像去雾算法

更新时间：2026-09-04

- 基于注意力机制的单幅图像去雾算法
- Single image defogging algorithm based on attention mechanism
- 微电子学与计算机 2021年38卷第4期页码：52-56
- 作者机构：
  
  广西师范大学机构电子工程学院,广西,桂林,541004
- 作者简介：
- 基金信息：
  
  广西科技重大专项项目桂科AA18118009国家自然科学基金项目 61762014桂林市科学研究与技术开发计划项目 20170113-4
- DOI：
  中图分类号：
- 纸质出版：2021
- 稿件说明：
移动端阅览
杜帆, 蒋品群, 宋树祥, 夏海英. 基于注意力机制的单幅图像去雾算法[J]. 微电子学与计算机, 2021, 38(4): 52-56.

DU Fan, JIANG Pin-qun, SONG Shu-xiang, et al. Single image defogging algorithm based on attention mechanism[J]. 2021, 38(4): 52-56.
杜帆, 蒋品群, 宋树祥, 夏海英. 基于注意力机制的单幅图像去雾算法[J]. 微电子学与计算机, 2021, 38(4): 52-56. DOI：

DU Fan, JIANG Pin-qun, SONG Shu-xiang, et al. Single image defogging algorithm based on attention mechanism[J]. 2021, 38(4): 52-56. DOI：

摘要

针对现有去雾算法去雾效果不理想的问题，提出了一种基于注意力机制的单幅图像去雾算法.通过引入注意力机制构建通道注意和像素注意，并将两者结合实现特征注意模块；再通过多尺度卷积、局部残差学习和特征注意搭建基本模块；最后结合全局残差学习实现端到端的去雾处理.实验结果表明，该算法在峰值信噪比(PSNR)、结构相似度(SSIM)、特征相似度(FSIM)三种图像评价指标上均高于对比算法，取得了良好的去雾效果，有效地解决了去雾效果不理想的问题.

Abstract

Aiming at the problem that the existing defogging algorithm is not ideal for defogging

a single image defogging algorithm based on attention mechanism is proposed. Channel attention and pixel attention are constructed by introducing attention mechanism

and the feature attention module is realized by combining the two. Then the basic module is built through multi-scale convolution

local residual learning

and feature attention. At last

the end-to-end defogging is realized by global residual learning. The experimental results show that the algorithm is superior to the comparison algorithm in three image evaluation indexes of peak signal-to-noise ratio(PSNR)

structural similarity(SSIM) and feature similarity(FSIM)

and it achieves a good defogging effect and effectively solves the problems of undesirable defogging effect

关键词

Keywords

references

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 (ICCV). Venice: IEEE, 2017: 4770-4778. DOI: 10.1109/ICCV.2017.511.

HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on PatternAnalysis andMachine Intelligence, 2011, 33(12): 2341-2353. DOI:10.1109/TPAMI.2010.168.

LI B Y, REN W Q, FU D P, et al. Benchmarking single-image dehazing and beyond[J]. IEEE Transactions on Image Processing, 2019, 28(1): 492-505. DOI: 10.1109/TIP.2018.2867951.

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. DOI: 10.1109/TIP.2016.2598681.

LIU X H, MA Y R, SHI Z H, et al. GridDehazeNet: attention-based multi-scale network for image dehazing[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul: IEEE, 2019: 7314-7323. DOI: 10.1109/ICCV.2019.00741.

BERMAN D, TREIBITZ T, AVIDAN S. Non-local imagedehazing[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 1674-1682. DOI: 10.1109/CVPR.2016.185.

CHEN D D, HE M M, FAN Q N, et al. Gated context aggregation network for image dehazing and deraining[C]//Proceedings of the2019IEEE Winter Conference on Applications of Computer Vision (WACV). Waikoloa Village: IEEE, 2019: 1375-1383. DOI: 10.1109/WACV.2019.00151.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于2D-3D双模态Transformer人体姿态估计

基于区块链的AI生成内容溯源框架设计研究

基于MSS-YOLO-MPHands融合架构的装配手部动作识别研究

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

低功耗设计的双链电源关断策略的实现与验证