空域加权局部对比度的红外小目标检测算法
DOI:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:


An infrared small object detection algorithm based on spatial weighted local contrast
Author:
Affiliation:

Fund Project:

  • 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:

    针对传统局部对比度算法在强杂波背景下,容易引入虚警目标的不足,提出了一种空域加权局部对比度的红外小目标检测算法。首先,利用具有中心激励和侧向抑制性的二维高斯差分滤波器,抑制了原始图像大部分的背景杂波,以提高图像的信噪比;然后,利用目标均值与邻域的中值的比值进行局部对比度测量,再用目标各区域的灰度均值差加权局部对比度,生成目标显著图;最后,对显著图进行自适应阈值分割,检测出真实目标。实验结果表明,与其他几种检测方法对比,该算法不仅具有较高的信躁比增益和背景抑制因子,还具有较高的检测率和较低的虚警率,是一种有效的红外小目标检测方法。

    Abstract:

    In view of the shortcomings of traditional local contrast algorithm in the background of strong clutter,which is easy to introduce false alarm target,an infrared small target detection algorithm with spatial weighted local contrast is proposed.Firstly,the two-dimensional Gaussian difference filter with central excitation and lateral inhibition is used to suppress most of the background clutter of the original image,so as to improve the signal-to-noise ratio of the image;secondly,the ratio of the target mean value to the median value of the neighborhood is used to measure the local contrast,and then the gray mean difference of each region of the target is used to weight the local contrast to generate the target saliency map;finally,the image is displayed the real target is detected by adaptive threshold segmentation.Experimental results show that,compared with other detection methods,the algorithm not only has a high signal to noise ratio gain and background suppression factor,but also has a high detection rate and a low false alarm rate.It is an effective infrared small target detection method.

    参考文献
    相似文献
    引证文献
引用本文

段思韦,王忠华,叶铮.空域加权局部对比度的红外小目标检测算法[J].激光与红外,2020,50(10):1200~1206
DUAN Si-wei,WANG Zhong-hua,YE Zheng.An infrared small object detection algorithm based on spatial weighted local contrast[J].LASER & INFRARED,2020,50(10):1200~1206

复制
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:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2020-10-28
  • 出版日期: