The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
Bookmark and Share
Flexible Feature Optimization Based Robust Object Tracking
Author(s): 
Pages: 332-338
Year: Issue:  2
Journal: Pattern Recognition and Artificial Intelligence

Keyword:  目标跟踪 陡峭因子 特征融合 粒子滤波;
Abstract: 针对单一特征空间不足以对动态时变环境中跟踪目标进行准确表达的缺点,提出一种基于柔性加权特征的Particle Filter目标跟踪算法.首先引入"陡峭因子"这一概念对不同特征的跟踪鉴别性能进行客观评估,然后参照当前不同特征的可跟踪性能以加权组合的方式自适应生成当前最优特征,最后将生成的最优特征嵌入到Particle Filter跟踪构架中完成目标跟踪任务.该算法具备较高的柔性可对任意采用直方图表达的特征进行自适应融合.不同的视频序列实验表明该算法可动态地对异类特征进行有效融合,对复杂场景下的目标进行稳健跟踪.
Related Articles
No related articles found