An experimental comparison of online object-tracking algorithms
An experimental comparison of online object-tracking algorithms
复制标题
DOI：
10.1117/12.895965
复制
发表时间：
2011-09
期刊：
影响因子：
--
通讯作者：
Qing Wang;Feng Chen;Wenli Xu;Ming-Hsuan Yang
中科院分区：
文献类型：
--
作者：
Qing Wang;Feng Chen;Wenli Xu;Ming-Hsuan Yang
本文回顾和评价了几种最先进的在线目标跟踪算法。尽管经过几十年的努力，由于诸如照明、姿态、尺度、变形、运动模糊、噪声和遮挡等因素，对象跟踪仍然是一个具有挑战性的问题。考虑到外观变化，最近的跟踪算法集中在强大的对象表示和有效的状态预测。在本文中，我们分析了每种跟踪方法的组成部分，并确定了它们在应对特定挑战时的关键作用，从而阐明了如何为不同情况选择和设计算法。我们比较了最先进的在线跟踪方法，包括IVT，1 VRT，2 FragT，3 BoostT，4 SemiT，5 BeSemiT，6 L1T，7 MILT，8 VTD9和TLD 10算法在许多具有挑战性的序列，并评估他们与不同的性能指标。定性和定量的比较结果表明了这些算法的优缺点。
This paper reviews and evaluates several state-of-the-art online object tracking algorithms. Notwithstanding decades of efforts, object tracking remains a challenging problem due to factors such as illumination, pose, scale, deformation, motion blur, noise, and occlusion. To account for appearance change, most recent tracking algorithms focus on robust object representations and effective state prediction. In this paper, we analyze the components of each tracking method and identify their key roles in dealing with specific challenges, thereby shedding light on how to choose and design algorithms for different situations. We compare state-of-the-art online tracking methods including the IVT,1 VRT,2 FragT,3 BoostT,4 SemiT,5 BeSemiT,6 L1T,7 MILT,8 VTD9 and TLD10 algorithms on numerous challenging sequences, and evaluate them with different performance metrics. The qualitative and quantitative comparative results demonstrate the strength and weakness of these algorithms.