A Novel Performance Evaluation Method for Visual Tracking Methods

摘要：

　　The evaluation for visual tracking is of utmost importance in computer vision.During the last two decades,several evaluation frameworks have been proposed and applied by a large amount of researchers,such as average central error,success rate,or Pascal score.It turns out that it is not easy to compare trackers fairly,precisely,and comprehensively with just only one evaluation index.Given the fact,a novel method for the evaluation of visual tracking algorithms is proposed in this paper,which combines both central error and Pascal score.Using this metric,an experimental validation was conducted finally and may serve as a reference for related research.

关键词： Visual tracking Evaluation Pascal score Central error

作者: Hui Teng Lianzhi Yu Huaping Liu Fuchun Sun Xiaojuan Liu

作者单位: Department of Computer Science and Technology,State Key Laboratory of Intelligent Technology and Sys School of Optical Electrical and Computer Engineering,University of Shanghai for Science and Technol Department of Computer Science and Technology,State Key Laboratory of Intelligent Technology and Sys

会议类型: 国际会议

会议名称: The 2015 Chinese Intelligent Automation Conference(2015中国智能自动化会议)

会议地点: 福州

会议语种:英文

页码: 313-324

在线出版日期: 2015-05-08（万方平台首次上网日期，不代表论文的发表时间）