arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2008.03628cs.CVstat.AP
收藏

用于多目标跟踪的无外观三部匹配算法

Appearance-free Tripartite Matching for Multiple Object Tracking

The Chinese University of Hong Kong(香港中文大学);Hong Kong Baptist University(香港浸会大学)

Lijun Wang, Yanting Zhu, Jue Shi, Xiaodan Fan

摘要:

多对象跟踪(MOT)检测给定输入视频的多个对象的轨迹。它在各种研究和工业领域变得越来越重要,例如生物医学研究中的细胞跟踪和视频监控中的人体跟踪。现有的匹配算法大多依赖于目标外观的唯一性,而占主导地位的二分匹配算法忽略了速度平滑性。虽然有几种方法结合了速度平滑跟踪,但它们要么不能追求全局平滑速度,要么往往陷入局部最优。我们专注于一般的MOT问题,而不管外观,并提出了一个外观无关的三方匹配,以避免不规则的速度问题的二分匹配。三方匹配被制定为最大化的可能性的状态向量构成的位置和速度的对象,这导致在一个链依赖的结构。我们求助于动态规划算法来找到这样的最大似然估计。为了克服动态规划的搜索空间巨大,当许多目标被跟踪时,引起的高计算成本,我们分解的消失的目标的数量的空间,并提出了一种减少空间的方法,通过截断分解。大量的仿真实验表明了该方法的优越性和有效性,并与细胞跟踪挑战赛的顶级方法进行了比较,也证明了我们的能力。我们还将我们的方法应用于跟踪癌症研究中肿瘤细胞周围自然杀伤细胞的运动。\footnote {源代码可在\url{https://github.com/szcf-weiya/TriMatchMOT}上获得

英文摘要:

Multiple Object Tracking (MOT) detects the trajectories of multiple objects given an input video. It has become more and more important for various research and industry areas, such as cell tracking for biomedical research and human tracking in video surveillance. Most existing algorithms depend on the uniqueness of the object's appearance, and the dominating bipartite matching scheme ignores the speed smoothness. Although several methods have incorporated the velocity smoothness for tracking, they either fail to pursue global smooth velocity or are often trapped in local optimums. We focus on the general MOT problem regardless of the appearance and propose an appearance-free tripartite matching to avoid the irregular velocity problem of the bipartite matching. The tripartite matching is formulated as maximizing the likelihood of the state vectors constituted of the position and velocity of objects, which results in a chain-dependent structure. We resort to the dynamic programming algorithm to find such a maximum likelihood estimate. To overcome the high computational cost induced by the vast search space of dynamic programming when many objects are to be tracked, we decompose the space by the number of disappearing objects and propose a reduced-space approach by truncating the decomposition. Extensive simulations have shown the superiority and efficiency of our proposed method, and the comparisons with top methods on Cell Tracking Challenge also demonstrate our competence. We also applied our method to track the motion of natural killer cells around tumor cells in a cancer study.\footnote{The source code is available on \url{https://github.com/szcf-weiya/TriMatchMOT}

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑