基于DESO运动预测的模板匹配算法  

A Template Matching Algorithm Based on Deso

作　　者：王晓卫[1,2] 马晓军[2] 周启煌[2] 

机构地区：[1]陆军航空兵学院机载设备系,北京101123 [2]装甲兵工程学院控制系,北京100072

出　　处：《激光与红外》2009年第1期105-109,共5页Laser & Infrared

基　　金：国家自然科学基金项目(No.60175010);背景预研项目(No.10401025)资助

摘　　要：针对战车目标自动跟踪火控系统对跟踪算法实时性、抗遮挡性要求高的特点,提出了一种基于DESO运动预测的模板匹配算法。该算法通过使用DESO对目标的运动轨迹进行预测,减少了目标的搜索范围,缩短了算法的运算时间。同时,遮挡判断和处理的增加使算法的鲁棒性得到了增强。实验结果表明与基于其他滤波算法的模板匹配算法相比,该算法具有不依赖于目标运动模型,预测精度高,实时性好,抗遮挡能力强的优点。In this paper, an improved template matching method based on DESO is studied deeply to meet the practical requirement in real-time and solve occlusion of Target Tracking Fire Control System. Because the proposed algorithm uses target＇s motion information that DESO filtered and predicted, it reduces target searching range, shortens matching computed time. At the same time, its robustness is improved due to occlusion judging and handling. Compared with the template algorithms based on other filters, experiment results illustrate the proposed algorithm has superior features, such as its independenees to model information, higher prediction precision, stronger anti-occlusion performance, and can meet the practical requirement in real-time.

关 键 词：目标跟踪 运动预测 模板匹配 微分扩张状态观测器 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]