运动弱目标检测的一种新方法  

Detection of Moving Weak Targets

作　　者：祁小平[1] 张启衡[1] 

机构地区：[1]中国科学院光电技术研究所,四川成都610209

出　　处：《半导体光电》2004年第6期463-464,492,共3页Semiconductor Optoelectronics

基　　金：国家"863"计划资助项目 ;中科院光电所前沿领域部署课题资助项目

摘　　要：　分析了噪声背景下弱目标区域的梯度分布特性,采用模糊技术来描述了弱目标边缘区域内灰度变化方向的一致性程度,把灰度变化方向的一致性程度作为各像素点隶属于边缘的模糊隶属度,进行目标初分割。然后利用帧间信息,根据目标的运动特征再分割,并根据现场采集到的数据进行仿真,证明了该方法的有效性。The distribution characteristics of weak target under the noise background are analyzed. A method to describe the grey-degree variance direction consistence among the pixels is proposed by using fuzzy technique, i.e., the grey-degree variance direction consistence among the pixels as fuzzy membership belonging to the edge is used to realize initially the image segmentation, then, according to the information among the frames and true moving target, the segmented image is again segmented to enhance the segmentation precision. The simulation results show that this method is efficient.

关 键 词：图像分割 隶属函数 梯度分析 目标检测 

分 类 号：TN247[电子电信—物理电子学]