On Particle Filter and Mean Shift Tracking Algorithm Based on Multi-feature Fusion

摘要：

　　To solve the problem that a single feature lead to tracking failure easily in a complex environment,an efficient particle filter and Mean Shift tracking algorithm based on multi-feature fusion was proposed.Under the framework of particle filter,it the closer to the real posterior distribution by embedding Mean Shift algorithm and using color and structural as the observation model to represent the object,and the weights of particles were calculated by this integration,in order to avoid the single color features easy to track the failure problem.The experiments show that the proposed method has a better robustness when using the same particles and the average weight of the particle is improved and the resample times reduced significantly,even using the less particles can achieve tracking stability.

关键词： object tracking mean shift multi-feature particle filter color feature structural feature

作者: QIAO Nan YU Jin-xia

作者单位: College of Computer Science and Technology,Henan Polytechnic University,Jiaozuo,Henan,454003,China

会议类型: 国际会议

会议名称: The 33th Chinese Control Conference第33届中国控制会议

会议地点: 南京

会议语种:英文

页码: 4712-4715

在线出版日期: 2014-07-28（万方平台首次上网日期，不代表论文的发表时间）