English

应用科学学报 ›› 2013, Vol. 31 ›› Issue (6): 607-6.doi: 10.3969/j.issn.0255-8297.2013.06.009

• 信号与信息处理 • 上一篇    下一篇

多尺度自卷积方差显著性SAR图像目标检测

王国力， 周伟， 丛瑜， 关键   

  • 收稿日期:2012-06-14 修回日期:2012-10-17 出版日期:2013-11-29 发布日期:2012-10-17
  • 作者简介:王国力，博士生，研究方向：SAR 图像目标检测、不变特征描述、图像配准，E-mail：wanggl@sdu.edu.cn；关键，教授，博导，研究方向：雷达目标自动检测、侦察图像处理和信息融合，E-mail：guanjian96@tsinghua.org.cn
  • 基金资助:

    国家自然科学基金(No.61179017, No.61201445)；“泰山学者”建设工程专项经费资助

SAR Image Target Detection Based on Multi-scale Auto-convolution Variance Saliency

WANG Guo-li, ZHOU Wei, CONG Yu, GUAN Jian   

  1. Department of Electronic and Information Engineering, Naval Aeronautical and Astronautical University,
    Yantai 264001, Shandong Province, China
  • Received:2012-06-14 Revised:2012-10-17 Online:2013-11-29 Published:2012-10-17

PDF

1578

被引次数

2

摘要： 针对SAR图像中显著性目标检测问题，提出一种基于多尺度自卷积方差显著性的自适应检测算法. 该算法在对SAR图像多尺度自卷积运算基础上，通过计算MSAV得到方差显著图. 设计了一种自适应阈值检测器，完成SAR图像中显著性目标的检测. 实验结果表明，在复杂背景环境下，所提算法能有效检测出与人类视觉较为一致的显著性目标.

关键词: 合成孔径雷达图像, 目标检测, 多尺度自卷积, 方差显著性

Abstract:  To detect salient objects in SAR image, an adaptive detection method is proposed based on multi-scale auto-convolution variance (MSAV) saliency. With multi-scale auto-convolution operation in SAR image and by calculating MSAV, a variance saliency map is obtained. An auto-threshold-selecting detector is
constructed and salient object detection from the SAR image is achieved. Experimental results show that, by applying the proposed algorithm to a complex scene, salient objects consistent with human visual sense can be effectively detected.

Key words: target detection, multi-scale auto-convolution, variance saliency, synthetic aperture radar (SAR) image

中图分类号: