首页 | 本学科首页   官方微博 | 高级检索  
     

基于顺序形态滤波的运动点目标检测
引用本文:叶斌,彭嘉雄.基于顺序形态滤波的运动点目标检测[J].红外与激光工程,2001,30(1):25-29.
作者姓名:叶斌  彭嘉雄
作者单位:图像信息处理与智能控制教育部重点实验室华中科技大学图像识别与人工智能研究所,湖北 武汉 430074
基金项目:国防科技预研基金资助项目 !(编号 :98J2 .4 .6 .JW0 50 4 )
摘    要:为解决低信噪比快速运动点目标的检测问题,文中提出了一种基于顺序形态波波的点目标检测算法。首先采用百分位p=1的中面序形态滤波提取目标的广义内边缘,找出少量候选运动目标点,然后利用图像流模型建立 建立目标的运动约束议程,根据目标像素在图像序列中运动的连续性和轨迹的一致性 原则,在多帧连续图像中检测出真实的目标运动轨迹。实验结果证明,该方法能够快速、可靠检测信噪比小于3的运动点目标。

关 键 词:顺序形态波  运动点目标检测  图象处理
文章编号:1007-2276(2001)01-0025-05
修稿时间:2000年4月5日

Moving point target detection based on order morphology filtering
YE Bin,PENG Jia-xiong.Moving point target detection based on order morphology filtering[J].Infrared and Laser Engineering,2001,30(1):25-29.
Authors:YE Bin  PENG Jia-xiong
Abstract:To resolve the moving point target detection problem under the condition of low SNR , a new point target detection algorithm based on generalized edge extracted by order morphology filtering is presented. Two steps of point target detection are adopted. First, background suppression and generalized inner\|edge of targets extraction are performed by order morphology filtering whose percentile is selected to pick out a small quantity of possible moving point targets. Then the motion constraint equation of the targets is set up according to the image flow model. By use of the model, the true target motion trajectory is detected in multi\|frame successive image. The experiment results show that the method can effectively and reliably detect the moving point target with SNR less than 3.
Keywords:Point target  Backgroud suppression  Order morphology filtering  Image flow
本文献已被 CNKI 维普 万方数据 等数据库收录!
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