期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于视觉显著性的毫米波隐匿物品检测算法

Millimeter wave hidden object detection algorithm based on visual saliency
下载PDF
导出
摘要 针对毫米波图像中隐匿物品与人体灰度差异小、形状多变的问题,提出了一种基于视觉显著性的隐匿物品检测算法。该算法在双边滤波后,结合OTSU和形态学运算完成预处理以获得人体区域,再根据频域显著性计算定位前景,经背景抑制后生成显著图完成检测。实验数据表明,所提算法与典型的主动式毫米波成像检测算法相比,检出率分别提高5.87%和9.08%,有更好的检测性能。 In order to solve the problem that the gray level difference between hidden objects and human body in millimeter wave image is small and the shape is changeable,a hidden object detection algorithm based on visual saliency is proposed.After bilateral filtering,combined with OTSU and morphological operation,the algorithm completes the pretreatment to obtain the human body region.And then the foreground is located based on the significance calculation in the frequency domain.After background suppression,the significance map is generated,so the detection is completed.Experimental results show that compared with the typical active millimeter wave imaging detection algorithm,the detection rate of the proposed algorithm increases by 5.87% and 9.08%,respectively,and the proposed algorithm has better detection performance.
作者 张珂绅 郭文风 王鹤澎 叶学义 Zhang Keshen;Guo Wenfeng;Wang Hepeng;Ye Xueyi(School of Communication Engineering,Hangzhou Dianzi University,Hangzhou 310018,China)
机构地区 杭州电子科技大学通信工程学院
出处 《电子技术应用》 2022年第11期99-103,109,共6页 Application of Electronic Technique
基金 国家自然科学基金(U19B2016,60802047)。
关键词 隐匿物品 视觉显著性 图像签名 阈值分割 hidden object visual salience image signature threshold segmentation
分类号 TN928 [电子电信—通信与信息系统] TP391.41 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献5

二级参考文献33

  • 1Oliver C,Quegan S 著.丁赤飚,陈杰,何国金,等译.合成孔径雷达图像理解[M] .北京:电子工业出版社,2009.
  • 2Kolinko V G, Lin S H,Shek A, et al. A passive millimeter-wave imaging system for concealed weapons and explosives de-tection[C] // Proc. of the De fense and Security, InternationalSociety for Optics and Photonics * 2005 : 85 - 92.
  • 3Kemp M C. Millimetre wave and terahertz technology for the de-tection of concealed threats: a review[C]/y Proc. of the Interna-tional Society for Optical Engineering, 2006 : 64020I>1-64020D-19.
  • 4Stanko S, Notel I), Huck J,et al. Millimeter wave imaging for con-cealed weapon detection and surveillance at up to 220 GHz[C] //tional Society for Optics and Plwtonics, 2008 : 69480 N-.1 -69480N-7.
  • 5Sato H. Sawaya K,Mizuno K, et al. Passive millimeter-waveimaging for security and safety applications[C] // Proc. of theSPIE Defense, Security, and Sensing , 2010: 76710V - 1 -76710V- 11.
  • 6Lee D S, Yeom S, Son J Y. et al. Image segmentation of con-cealed objects detected by passive millimeter wave imagingCC]//Proc. of the 3 4//2 IEEE International Can ference o.i Infrared ,Millimeter<,and Terahertz Waves , 2009:1 -2.
  • 7Lee H, Yeom S,Son J Y,et al. Image registration and fusion ofMMW and visual images for concealed object detection [C] //Proc. 0f the SPIE Defense , Security, cmd Sensing, 2010:76700H- 1 -76700H-7.
  • 8Yeom S, Lee D S,Son J Y. Multi-level segmentation of passivemillimeter wave images with Gaussian mixture modeling[C] //Proc. of I he SPIE Defense , Security^ and Setisijig , 2011 :80230D- 1 -80230D-6.
  • 9Lee D S, Yeom S, Son J Y, et al. Multi-channel millimeter waveimage registration and .segmentation for concealed object detec-tion[C] // Proc. of the SPIE Defense . Security t and SensingInternational Society for Optics and Photonics , 2010 : 76662U -1 - 76662U-6.
  • 10Lee D S, Yeom S, Son J Y, et al. Automatic image segmentation forconcealed object detection using the expectation-maximization algo-rithm[J]. Optics Express , 2010, 18(10): 10659 - 10667.

共引文献40

电子技术应用
2022年 第11期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部