改进的粒子滤波器目标跟踪方法  

Improved object tracking method for particle filter

作　　者：钱翔[1] 李新华[1] 刘波[1] 张辉[2] 

机构地区：[1]安徽大学计算智能与信号处理教育部重点实验室,安徽合肥230039 [2]安徽大学电子科学与技术学院,安徽合肥230039

出　　处：《计算机工程与设计》2011年第1期277-280,共4页Computer Engineering and Design

摘　　要：针对现有粒子滤波器目标跟踪算法采用单一颜色直方图特征在目标建模中的缺点和不足,提出了一种将目标颜色特征和不变矩特征融合建立目标模型的改进方法,粒子权重由环境决定的两种特征欧式距离加权生成。实验结果表明,该方法改进了单一颜色特征描述目标在跟踪过程中对抗一些干扰的不足,在不影响实时性的基础上提高了跟踪的准确性和鲁棒性。In order to restrain the deficiencies and shortcomings of the particle filter target tracking algorithm for using single color histogram property to establish a target model,an improved method to establish a target model for combining both properties of target color and moment invariant is presented,the weights of the particle are weighting generated by two environment determined Euclidean distance properties.The experiment proves that this method ameliorates the interference immunity of the single color property for tracking target. In addition,this method also improves the tracking accuracy and robustness while dose not affecting the real-time characteristics.

关 键 词：目标跟踪 粒子滤波 融合权 不变矩 颜色直方图 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]