期刊文献+

基于遥控侦察仪的目标检测 被引量:1

Target detection based on remote control reconnaissance instrument
下载PDF
导出
摘要 针对原有的遥控侦察仪只能够采集和显示视频,而未对视频做相应处理的问题,设计了一个基于遥控侦察仪的目标检测方案,赋予遥控侦察仪检测目标的功能。当侦察区域内出现运动目标,遥控侦察仪的显示界面发出警报提示,实现遥控侦察仪的智能化。采用单高斯模型进行背景建模,但检测到的目标图像存在空缺部分。利用三帧差分法得到的差分图像和更新单高斯模型的学习速率来弥补图像的空缺部分,使得检测到的目标图像较为完整。依据帧数来实现学习速率的更新。多次实验表明,遥控侦察仪目标检测性能稳定,满足了遥控侦察仪的功能需求。 Aiming at the problem that the original remote control reconnaissance instrument can only capture and display video without corresponding processing of the video,a target detection scheme based on the remote control reconnaissance instrument is designed to give the remote control reconnaissance instrument the ability to detect the target.When a moving target appears in the reconnaissance area,the display interface of the remote control reconnaissance device issues an alarm prompt to realize the intelligence of the remote control reconnaissance device.This paper uses Single Gaussian Method to build the background model,but there are gaps in the detected target image.The differential image by threeframe differential method is obtainedand the learning rate of Single Gaussian Method is updated to make up for the missing part of the image.This method makes the detected target image more complete.According to the number of frames,the learning rate of Single Gaussian Method is updated.After several experimental tests,the results show that the performance of the image processing system for detecting targets is stable,which meets the functional requirements of remote control reconnaissance instrument.
作者 胡志伟 朱蕴璞 Hu Zhiwei;Zhu Yunpu(School of Mechanical Engineering,Nanjing University of Science and Technology,Nanjing 210000,China)
出处 《国外电子测量技术》 2020年第5期76-80,共5页 Foreign Electronic Measurement Technology
关键词 遥控侦察仪 目标检测 智能化 单高斯模型 remote control reconnaissance instrument target detection intelligence single gaussian method
  • 相关文献

参考文献11

二级参考文献104

  • 1张源峰.无线视频监控传输技术的研究[J].安防科技,2010(2):3-7. 被引量:3
  • 2代科学,李国辉,涂丹,袁见.监控视频运动目标检测减背景技术的研究现状和展望[J].中国图象图形学报,2006,11(7):919-927. 被引量:169
  • 3万缨,韩毅,卢汉清.运动目标检测算法的探讨[J].计算机仿真,2006,23(10):221-226. 被引量:121
  • 4Peng Suo, Wang Yanjiang. An improved adaptive background modeling algorithm based on Gaussian mixture model [ C ] // Proceedings of ICSP2008. Beijing: IEEE Press,2008 : 1426-1439.
  • 5Power P W, Schoonees J A. Understanding background mixture models for foregrounds segmentation [ C ]//Proceedings of Image and Vision Computing, New Zealand : Auckland ,2002:267-271.
  • 6Harville M, Gordon G, Woodfill J. Foreground segmentation using adaptive mixture models in color and depth [C ]//Proceedings of IEEE Workshop on Detection and Recognition of Events in Video. Vancouver, BC, Canada: USA : IEEE Press, 2001 : 3 - 11.
  • 7Zhong J ,Sclaroff S. Segmenting foreground objects from a dynamic textured background via a robust Kalman filter [ C ] // Proceedings of International Conference on Computer Vision. Nice, France : IEEE Press,2003:44-50.
  • 8Jabri S, Duric Z, Wechsler H. Detection and location people in video images using adaptive fusion of color and edge information [ C ] //Proceedings of International Conference on Pattern Recognition. Barcdona, Spain : IEEE Press ,2000,627-630.
  • 9Ercan Ozyildiz, Nils Krahnstover, Rajeev Shanna. Adaptive texture and color segmentation for tracking moving objects [ J ]. Pattern Recognition ,2002,35 (10) :2013-2029.
  • 10Li Liyuan, Leung K H Maylor. Integrating intensity and texture differences for robust change detection [ J ]. IEEE Trans. Image Processing,2002,11 (2) : 105 - 112.

共引文献131

同被引文献10

引证文献1

二级引证文献2

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