摘要
针对单特征目标跟踪算法的鲁棒性较差以及不能充分利用最新的量测信息等问题,提出了一种基于多特征融合的改进UPF(Unscented Particle Filter)跟踪算法.基于比例最小偏度单形采样策略的UKF(Unscented Kalman Filter)算法和IKF(Iterated Kalman Filter)算法对粒子滤波算法进行改进,并在改进的算法框架下,采用不确定性度量方法融合目标的颜色和纹理特征,对目标进行跟踪.仿真实验表明,改进算法提高了跟踪精度,对复杂背景下的目标进行跟踪有较好的效果,并能有效跟踪被遮挡的目标.
To solve the robustness problem and poor use of the latest measurement information in object tracking with single feature, this paper proposed an improved UPF tracking algorithm based on multi-fea- ture fusion. First, the algorithm was improved by using the UPF algorithm with the scaled minimal skew simplex sampling strategy and the IKF algorithm. Then, the uncertain measurement method was adopted to fuse the color and texture features of the object and track the object with the framework of the improved algorithm. The simulation results show that the proposed algorithm improves the tracking accuracy, has a better effect on tracking the object under complex scenes accurately and tracks the occluded object effectively.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2014年第10期1473-1478,共6页
Journal of Shanghai Jiaotong University
基金
国家自然科学基金(61263031)
甘肃省自然科学基金(1310RJZA034)资助项目
关键词
目标跟踪
比例最小偏度单形采样
UPF算法
IKF算法
多特征融合
不确定性度量
object tracking
scaled minimal skew simplex sampling
unscented particle filter （UPF）algorithm
iterated Kalman filter（IKF） algorithm~ multiple features fusion
uncertainty measurement
