基于梯度可感知通道注意力模块的 红外小目标检测前去噪网络
DOI:
作者:
作者单位:

国防科技大学

作者简介:

通讯作者:

中图分类号:

基金项目:

国家科技攻关计划,国家自然科学基金项目(面上项目,重点项目,重大项目)


Gradient-aware channel attention network for infrared small target image denoising before detection
Author:
Affiliation:

National University of Defense and Technology

Fund Project:

The National Key Technologies R&D Program of China,

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    红外图像去噪在军事及民用领域应用广泛。现有基于深度学习的图像去噪方法主要为可见光图像设计,此类方法容易过度平滑图像细节,从而导致弱小目标丢失,为后续的检测任务带来困难。为了在去除噪声的同时保留好红外图像中的目标信息,本文提出了一种基于梯度可感知通道注意力模块的红外弱小目标检测前去噪网络。该网络首先采用编码器-解码器结构来去除图像中的加性噪声,然后通过梯度可感知通道注意力模块对图像高频区域进行自适应增强,有效保持红外弱小目标的响应强度。此外,本文公开了领域第一个包含3981张含噪声的红外图像数据集。实验结果表明,该网络能够在有效去除加性噪声的同时避免过度平滑,很好地保留了红外图像中的目标信息,最终实现了在含噪声环境下的高鲁棒性红外弱小目标检测。本文的数据集和代码即将开源在https://github.com/yihang455/GCAN

    Abstract:

    Infrared small target denoising is widely used in military and civilian fields. Existing deep learning-based methods are specially designed for optical images, which easily overall smooths the informative image details and thus loses the response of small target. To both denoise and maintain informative image details, this paper proposed a gradient-aware channel attention network (GCAN) for infrared small target image denoising before detection. Specifically, we first use a encoder-decoder network to remove the additive noise of the infrared images. Then, a gradient-aware channel attention module is designed to adaptively enhance the informative high-gradient image channel. The informative target region with high-gradient can be maintained in this way. After that, we develop a large dataset with 3981 noisy infrared images. Experimental results show that our proposed GCAN can both effectively remove the additive noise and maintain the informative target region. Additional experiments of infrared small targets detection further verify the effectiveness of our method. Our dataset and source-code will be available at https://github.com/yihang455/GCAN soon.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2023-06-29
  • 最后修改日期:2023-08-08
  • 录用日期:2023-10-19
  • 在线发布日期:
  • 出版日期: