视频目标跟踪典型算法比较与分析  

Comparison and Analysis of State-of-the-art Visual Object Tracking Algorithms

作　　者：王苹[1] 张磊[1] 吴泽民[1] 徐任晖[1] 赵晓通[1] 徐明月[1] 

机构地区：[1]解放军理工大学通信工程学院,江苏南京210007

出　　处：《电视技术》2015年第23期79-84,共6页Video Engineering

基　　金：国家自然科学基金项目(61201217)

摘　　要：视频目标跟踪由于场景和目标的外观变化等问题的存在,仍旧是计算机视觉领域研究的热点和挑战。阐述了视频目标跟踪技术的研究背景;介绍了视频目标跟踪系统组成原理、研究现状;重点分析了几种近来较为前沿的跟踪算法并进行分析比较;还对跟踪算法的评价指标以及典型的标准库进行介绍;最后归纳总结了视频目标跟踪的发展前景以及面临的问题挑战,为下一步研究奠定基础。Visual object tracking is still a challenge and significant research area in computer vision, due to the appearance changes of the scene and target. This paper presents the background, the composition and principle of the tracking system, including research status of visual object tracking. In this paper, several recent state-of-the-art object tracking algorithms are emphatically analyzed and compared. Besides, evaluation parameters and testing datasets are also given in this paper. At last, there is an overview of the challenges and prospect of visual object tracking which sets the base of further research.

关 键 词：视频目标跟踪 外观模型 特征提取 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]