高速视频的运动目标匹配识别算法  

Moving target matching recognition algorithm for high speed video

作　　者：唐瑞 侯宏录[1] 侯盼晴 Tang Rui;Hou Honglu;Hou Panqing(Xi'an Technological University,Xi'an 710021,China)

机构地区：[1]西安工业大学光电工程学院

出　　处：《国外电子测量技术》2018年第11期52-57,共6页Foreign Electronic Measurement Technology

基　　金：陕西省工业科技攻关基金(2016GY-051);陕西省教育厅重点实验室科研计划基金(15JS035)资助项目

摘　　要：针对运动目标的动态识别问题,提出了一种完整有效的建立数据模板库的目标匹配识别算法。为了识别高速视频中的飞碟,采用像素提取运动目标的特征值;通过控制变量的方法依次改变飞碟姿态,进行图像采集,建立模板数据库;采用相似度匹配原理进行目标识别,获得目标姿态信息。最后在MATLAB环境下对飞碟姿态识别进行算法验证,对3种不同情况下的获取的飞碟图像进行模板匹配,获得了飞碟实时姿态,通过电子经纬仪验证了仿真实验结果,验证了该算法的有效性和准确性。Aiming at the dynamic recognition problem of moving targets,a complete and effective target matching recognition algorithm based on data template library is proposed.In order to identify the flying saucer in high speed video,the feature value of the moving target is extracted with pixels,and the attitude of the flying saucer is changed by the method of controlling the variable,the image acquisition is carried out,the template database is set up,and the target recognition is obtained by using the similarity matching principle to obtain the information of the target attitude.Finally,The algorithm of flying saucer attitude recognition is validated in MATLAB environment.The template matching of the flying saucer images obtained in three different situations is matched,and the real time attitude of the flying saucer is obtained.The results of the simulation experiment are verified by the electronic theodolite,and the validity and accuracy of the algorithm are verified.

关 键 词：目标识别 特征提取 模板匹配 MATALB仿真 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]