基于Camshift和Particle Filter的小目标跟踪算法  

Weak aerial target tracking algorithm based on Camshift and Particle Filter

作　　者：李忠海[1] 王莉[1] 崔建国[1] 

机构地区：[1]沈阳航空工业学院自动化学院,沈阳110136

出　　处：《计算机工程与应用》2011年第9期192-195,199,共5页Computer Engineering and Applications

基　　金：航空科学基金项目(No.2008ZD54011);辽宁省教育厅科研基金项目(No.2008544);沈阳航空工业学院博士启动基金项目(No.05BY15)~~

摘　　要：Particle Filter算法有较好的跟踪鲁棒性,但实时性差;Camshift算法计算速度快,但它属于半自动跟踪,所以都无法有效避免复杂背景的干扰。为了解决上述问题,提出了基于Camshift和Particle Filter的融合算法。该算法首先利用Particle Filter来自动搜索小目标的初始位置,接着采用Camshift跟踪小目标,然后通过度量因子自适应切换Camshift和Particle Filter来跟踪短时丢失的目标。利用复杂背景下的飞行小目标图像序列,与序贯相似性检测算法(SSDA)、Camshift和Particle Filter做对比实验。结果表明算法不仅能实现小目标的全自动跟踪,而且还降低了跟踪效果受目标形变和部分遮挡的影响,对小目标跟踪具有较高的鲁棒性和实时性。Particle Filter algorithm has played good performance in tracking robustness,but is poor in real-time;Camshift algorithm has the fast speed of calculation,but it is semi-automatic,so they are both unable to avoid the disturbance effectively in complex background.In order to solve above problem,an integrated algorithm is proposed based on Camshift and Particle Filter. This algorithm uses Particle Filter to search the initial position of the Weak Aerial Targe（tWAT）,then uses Camshift to track WAT and switches Camshift and Particle Filter to track the missing WAT by measurement parameter adaptively.Contrast experiment is conducted in the SSDA,Camshift and Particle Filter by the image sequence of WAT which is under the complex background.The result of experiment indicates that this algorithm can not only realize the wholly automatic tracking,but also decrease the influence of deformation and partial occlusion in WAT.This algorithm has the strong robustness and real-time property.

关 键 词：飞行小目标 融合算法 序贯相似性检测算法(SSDA) CAMSHIFT PARTICLE Filter 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]