适于机载环境对地目标跟踪的粒子滤波设计  

Particle filter design for tracking ground targets in airborne environment

作　　者：宋策[1,2] 张葆[1] 尹传历[1] 

机构地区：[1]中国科学院长春光学精密机械与物理研究所中国科学院航空光学成像与测量重点实验室,吉林长春130033 [2]中国科学院大学,北京100039

出　　处：《光学精密工程》2014年第4期1037-1047,共11页Optics and Precision Engineering

基　　金：国家863高技术研究发展计划资助项目(No.2008AA121803)

摘　　要：为提高机载环境对地面强机动性目标跟踪的鲁棒性,本文以粒子滤波为跟踪框架,研究了它的动态模型与观测模型。针对机载环境的特点与跟踪目标的强机动性,提出了基于Kristan双步动态模型结构的加速度双步动态模型(TSA)。根据Yilmaz等人提出的非对称核函数思想,针对实际工程中目标变化特点与实时性要求,提出利用Snake算法提取目标轮廓,以轮廓信息构造非对称核函数的方法。最后,依据上述方法提出了TSA-AK粒子滤波跟踪算法。利用提出的算法对机载环境对地目标跟踪的视频进行了测试,结果表明,本文算法可实现对大幅度变速运动目标的稳定跟踪,正确跟踪率为98%;对大小为25pixel×30pixel的目标的处理帧率为26frame/s。To improve the robustness while tracking a ground target with strong mobility in the cabin environment,a particle filter was taken as tracking framework,and its dynamic model and observation model were investigated.According to the two-stage dynamic model proposed by Kristan et al,a two-stage acceleration （TSA） dynamic model was proposed for the characteristics of cabin environment and the strong mobility of the tracking target.According to the idea of asymmetric kernel function proposed by Yilmaz et al.,a method was proposed by using Snake algorithm to extract the object contour and to construct an asymmetric kernel function based on contour information to solve the realtime moving target problem.Finally,the TSA-AK particle filter tracking algorithm was proposed based on above methods.The proposed algorithm was tested on the video tracking ground target in cabin environment.The results show that the proposed algorithm can stably track target moving in a wide range of velocity.The targeting accuracy is 98％,and the computing frame rate is 26 frame/s when the object scale is 25 pixel× 30 pixel.

关 键 词：目标跟踪 粒子滤波 动态模型 核函数 SNAKE算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] V556[自动化与计算机技术—计算机科学与技术]