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.
引用本文: 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, XIA Hai-ying. Single image defogging algorithm based on attention mechanism[J]. Microelectronics & Computer, 2021, 38(4): 52-56.
Citation: DU Fan, JIANG Pin-qun, SONG Shu-xiang, XIA Hai-ying. Single image defogging algorithm based on attention mechanism[J]. Microelectronics & Computer, 2021, 38(4): 52-56.

基于注意力机制的单幅图像去雾算法

Single image defogging algorithm based on attention mechanism

  • 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

     

/

返回文章
返回