arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.12990cs.MAcs.RO
收藏

有限视场传感器下的分布式多目标跟踪

Distributed Multi-object Tracking under Limited Field of View Sensors

School of Computer Science, The University of Adelaide(阿德莱德大学计算机学院);Monash University(莫纳什大学);Curtin University(科廷大学)

Hoa Van Nguyen, Hamid Rezatofighi, Ba-Ngu Vo, Damith C. Ranasinghe

摘要:

我们认为具有挑战性的问题,跟踪多个对象使用分布式网络的传感器。针对节点视场、计算能力和通信资源有限的实际情况,提出了一种新的分布式多目标跟踪算法。为了实现这一点,我们首先正式的标签一致性的概念,确定一个充分条件,以实现它,并开发一种新的\textit{label consensus approach},减少标签不一致所造成的对象的移动从一个节点的有限的FoV到另一个。其次,我们开发了一种分布式多目标融合算法,融合局部多目标状态估计,而不是局部多目标密度。该算法:i)需要比多目标密度融合方法显著更少的处理时间; ii)通过考虑在几次扫描而不是单次扫描上的最优子模式分配(OSPA)跟踪误差来实现更好的跟踪精度; iii)与局部多目标跟踪技术无关,并且仅需要每个节点提供一组估计的轨迹。因此,没有必要假设节点保持多对象密度,并且因此融合结果不修改局部多对象密度。数值实验表明,我们提出的解决方案的实时计算效率和准确性相比,国家的最先进的解决方案在具有挑战性的情况下。我们还在https://github.com/AdelaideAuto-IDLab/Distributed-limitedFoV-MOT上发布了融合方法的源代码,以促进DMOT算法的发展。

英文摘要:

We consider the challenging problem of tracking multiple objects using a distributed network of sensors. In the practical setting of nodes with limited field of views (FoVs), computing power and communication resources, we develop a novel distributed multi-object tracking algorithm. To accomplish this, we first formalise the concept of label consistency, determine a sufficient condition to achieve it and develop a novel \textit{label consensus approach} that reduces label inconsistency caused by objects' movements from one node's limited FoV to another. Second, we develop a distributed multi-object fusion algorithm that fuses local multi-object state estimates instead of local multi-object densities. This algorithm: i) requires significantly less processing time than multi-object density fusion methods; ii) achieves better tracking accuracy by considering Optimal Sub-Pattern Assignment (OSPA) tracking errors over several scans rather than a single scan; iii) is agnostic to local multi-object tracking techniques, and only requires each node to provide a set of estimated tracks. Thus, it is not necessary to assume that the nodes maintain multi-object densities, and hence the fusion outcomes do not modify local multi-object densities. Numerical experiments demonstrate our proposed solution's real-time computational efficiency and accuracy compared to state-of-the-art solutions in challenging scenarios. We also release source code at https://github.com/AdelaideAuto-IDLab/Distributed-limitedFoV-MOT for our fusion method to foster developments in DMOT algorithms.

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。

↑