摘要
结合粒子滤波技术,提出一种基于加权颜色直方图的彩色物体跟踪算法.将目标颜色直方图作为目标的颜色模型,同时考虑其大小及像素点的位置对颜色分布的影响,将颜色直方图进行加权处理,使模型对区域特征描述更加合理.利用巴特查理亚距离描述粒子与目标颜色模型的相似性,作为粒子更新权值的有力依据.目标颜色模型的合理建立使得算法的粒子需求量少,计算复杂度降低,利于实现实时跟踪.试验结果验证了该算法的有效性和实用性.
A method of tracking colored object in noisy environment is discussed. In order to implement an effective and robust tracking task, a novel approach of weighted color histogram based particle filter algorithm is presented, which not only integrates color histogram into particle filtering, but also takes into account the target＇s shape as a necessary factor in target model. Furthermore, Bhattacharyya distance is employed to estimate the similarity between the target model and each hypotheses of the particle filter, which makes the measurement matching and samples＇ weight updating more reasonable. The implementation of this method exhibits robust results for different situation such as partial occlusion, rotation and shape distortion. Experiment results show the validity and practicability of the method.
出处
《控制与决策》
EI
CSCD
北大核心
2006年第8期868-872,878,共6页
Control and Decision
基金
辽宁省高等学校学科拔尖人才资金项目(2003-54)
大连理工大学青年教师培养基金项目
