首页 | 本学科首页   官方微博 | 高级检索  
     

基于分区动态规划和航迹关联的弱小目标检测
引用本文:陈尚锋,肖山竹,卢焕章.基于分区动态规划和航迹关联的弱小目标检测[J].红外与激光工程,2007,36(5):738-741.
作者姓名:陈尚锋  肖山竹  卢焕章
作者单位:国防科学技术大学,ATR国防重点实验室,湖南,长沙,410073
基金项目:国家高技术研究发展计划(863计划)
摘    要:序列图像中低信噪比运动弱小目标的实时检测算法,是精确制导系统中的关键算法之一。提出一种图像序列弱小目标实时检测新算法,采用分方向区间的动态规划算法和二值图像航迹关联检测。通过在动态规划能量累加过程中引入方向限制,减小了噪声轨迹能量积累和目标轨迹能量扩散,提高了算法的目标检测能力。对算法的检测性能进行了仿真实验,结果表明该算法能有效检测深空背景下信噪比大于1.8、运动方向任意、速度不大于1像素/帧的多个运动弱小目标。

关 键 词:弱小目标检测  动态规划  航迹关联
文章编号:1007-2276(2007)05-0738-04
收稿时间:2007/2/5
修稿时间:2007-02-05

Dim targets detection based on multi-regions dynamic programming and track matching
CHEN Shang-feng,XIAO Shan-zhu,LU Huan-zhang.Dim targets detection based on multi-regions dynamic programming and track matching[J].Infrared and Laser Engineering,2007,36(5):738-741.
Authors:CHEN Shang-feng  XIAO Shan-zhu  LU Huan-zhang
Affiliation:ATR Key Lab, National University of Defense Technology, Changsha 410073, China
Abstract:The real-time detection algorithm of moving dim small targets in image sequences is one of the key algorithms in precise guidance system. A real-time target detection algorithm is proposed, which employs dynamic programming(DP) and track matching algorithm in multi target moving regions in image sequences. After performing DP separately in multi speed-direction regions, noise trajectory energy accumulation and target trajectory divarication decrease. As a result, target enhancements are achieved. Simulational experiments show that low SNR(>1.8) moving targets with arbitrary speed direction and maximum speed of 1 pix/frame can be detected with high probability.
Keywords:Dim targets detection  Dynamic programming  Track matching
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《红外与激光工程》浏览原始摘要信息
点击此处可从《红外与激光工程》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号