| 基于多特征融合的目标跟踪算法 |
| |
| 引用本文： | 曹洁,李伟.基于多特征融合的目标跟踪算法[J].兰州理工大学学报,2011,37(2):80-84. |
| |
| 作者姓名： | 曹洁 李伟 |
| |
| 作者单位： | 1. 兰州理工大学,计算机与通信学院,甘肃,兰州,730050
2. 兰州理工大学,计算机与通信学院,甘肃,兰州,730050;中国人民解放军91666部队,浙江,舟山,316000 |
| |
| 基金项目： | 甘肃省自然科学基金(1010RJZA046); 甘肃省教育厅研究生导师基金(0914ZTB003) |
| |
| 摘 要： | 针对单一特征的目标跟踪算法鲁棒性较差的情况,利用目标的多种观测信息通过D-S证据理论进行融合跟踪.在粒子滤波的总体框架下,嵌入Mean-Shift算法产生更加逼近真实后验分布的粒子,同时采用颜色和运动边缘特征作为观测模型,有效地避免了单一颜色特征在光照突变、姿态变化以及背景相似情况下的跟踪稳定性较差的问题.实验表明,该...
|
| 关 键 词： | 目标跟踪 多特征融合 粒子滤波 运动边缘 D-S证据理论 |
Object tracking algorithm based on multi-feature fusion |
| |
| CAO Jie,LI Wei.Object tracking algorithm based on multi-feature fusion[J].Journal of Lanzhou University of Technology,2011,37(2):80-84. |
| |
| Authors: | CAO Jie LI Wei |
| |
| Institution: | CAO Jie1,LI Wei1,2(1.College of Computer and Communication,Lanzhou Univ.of Tech.,Lanzhou 730050,China,2.PLA Troops of 91666,Zhoushan 316000,China) |
| |
| Abstract: | Aimed at the situation that the object tracking with single feature results in a poor performance of robustness,a fusion tracking method was presented by using multiple observed information of the object and D-S evidence theory.Mean-Shift algorithm was embeded to produce particles with closer approximation to real posterior distribution in the framework of particle filtering.Meantime,by using the peripheral feature of color and motion as an observation model,the worse tracking stability with monochromic fea... |
| |
| Keywords: | object tracking multi-feature fusion particle filtering motion periphery D-S evidence theory |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
