电子学报2017，Vol.45Issue(10)：2337-2342,6.DOI:10.3969/j.issn.0372-2112.2017.10.004
基于多阶段学习的相关滤波目标跟踪
Correlation Filtering Target Tracking Based on Online Multi-lifespan Learning
摘要
Abstract
Due to the target appearance changes and occlusion during tracking,the KCF algorithm using a single iterative update filter will accumulate much more noise information in the process of learning,which leads to the loss of the target.To solve this problem,we propose a correlation filtering target tracking algorithm based on multi-lifespan learning.We establish complementary relationship among global stage filter model,consistency stage filter model and initial stage filter model to parallel track the target.The experimental results achieved on the 51 video databases on benchmark show that our algorithm is superior to most existing methods in both overall accuracy and overall success rate with the scores of 77.6％ and 68.9％,respectively.关键词
目标跟踪/多阶段学习/滤波器更新/一致性Key words
target tracking/multi-lifespan learning/filter update/consistency分类
信息技术与安全科学引用本文复制引用
孙航,李晶,杜博,肖雅夫,胡云玲..基于多阶段学习的相关滤波目标跟踪[J].电子学报,2017,45(10):2337-2342,6.基金项目
国家自然科学基金(No.61471274) （No.61471274）
