自适应模板更新的粒子滤波实时跟踪算法  

Real-time object tracking algorithm based on particle filter and adaptive template update

作　　者：赖作镁[1] 陈怀新[1] 吴必富[1] 

机构地区：[1]中国电子科技集团公司第十研究所,四川成都610036

出　　处：《系统工程与电子技术》2009年第4期768-772,共5页Systems Engineering and Electronics

摘　　要：提出一种自适应模板更新的粒子滤波实时跟踪算法。在粒子滤波的跟踪框架下,目标模板的自适应观测模型采用含有三个分量的混合高斯模型来建模并用增量EM算法在线更新,很好地解决了模板更新问题。实验结果表明:该跟踪算法在光照变化条件下的红外目标、外观姿态快速变化、局部遮挡等情况下的目标跟踪实验均能长时间稳定地跟踪目标,且无需普通粒子滤波算法的重采样策略,计算简单,易于硬件并行实现。A real-time object track algorithm based on particle filter and adaptive template update is proposed. On the framework of particle filter, a mixture Gaussian model is introduced to be an effective target description, which is composed of three components and online updated to solve the template update problem by using an incremental EM algorithm. Experiment results show that the algorithm can track infrared targets under variational illumination, especially for fast varying appearance and pose and local occlusion, furthermore, it is simple enough to be a real-time object tracking algorithm without particle resample.

关 键 词：目标跟踪 粒子滤波 自适应模板更新 混合高斯模型 增量EM算法 

分 类 号：TH74[机械工程—光学工程]