运动目标的识别跟踪控制研究  

Detection and tracking control of moving targets

作　　者：王琳[1] 董兴法[1] 郎科伟[1] 

机构地区：[1]苏州科技学院电子与信息工程学院,江苏苏州215009

出　　处：《苏州科技学院学报（工程技术版）》2013年第3期72-75,80,共5页Journal of Suzhou University of Science and Technology （Engineering and Technology）

基　　金：江苏省自然科学基金(BK2011703)

摘　　要：针对空中运动目标的识别和跟踪,提出图像匹配算法和连通域算法相结合的方法。该方法主要用图像匹配算法获得目标的位置信息,当图像匹配算法失效时,则采用连通域算法重新捕获目标、获得图像模板。同时,为提高跟踪的实时性,采用最小二乘线性预测法来预测目标的运动轨迹。在实验室的目标跟踪系统平台上,该方法能够对运动目标进行稳定的识别和跟踪。In view of the detection and tracking control of the air moving target, a combination of the image matching algorithm and the connected domain algorithm is proposed. This method mainly uses the image matching algorithm to obtain the location information of the target. When the image matching algorithm fails, the connected domain algorithm is applied to re-capture the target and obtain an image template. Moreover, to improve the system performance, the least squares linear prediction algorithm is introduced to forecast the moving path of the target. On the target tracking system platform in the laboratory, the method can realize and track air moving targets stably.

关 键 词：图像匹配 连通域 目标跟踪 

分 类 号：TP23[自动化与计算机技术—检测技术与自动化装置]