Abstract

Keywords

۱٫ Introduction

۲٫ System model

۳٫ Our approach

۳٫۱٫ Basic idea

۳٫۲٫ Trajectory modeling

۳٫۳٫ Trajectory parameter estimation

۳٫۴٫ Object location prediction

۴٫ Performance evaluation

۵٫ Extension

۶٫ Related works

۷٫ Conclusion

References

Abstract

Mobile object tracking, which has broad applications, utilizes a large number of Internet of Things (IoT) devices to identify, record, and share the trajectory information of physical objects. Nonetheless, IoT devices are energy constrained and not feasible for deploying advanced tracking techniques due to significant computing requirements. To address these issues, in this paper, we develop an edge computing-based multivariate time series (EC-MTS) framework to accurately track mobile objects and exploit edge computing to offload its intensive computation tasks. Specifically, EC-MTS leverages statistical technique (i.e., vector auto regression (VAR)) to conduct arbitrary historical object trajectory data revisit and fit a best-effort trajectory model for accurate mobile object location prediction. Our framework offers the benefit of offloading computation intensive tasks from IoT devices by using edge computing infrastructure. We have validated the efficacy of EC-MTS and our experimental results demonstrate that EC-MTS framework could significantly improve mobile object tracking efficacy in terms of trajectory goodness-of-fit and location prediction accuracy of mobile objects. In addition, we extend our proposed EC-MTS framework to conduct multiple objects tracking in IoT systems.

۱٫ Introduction

With the advance of Internet of Things (IoT) and big data sharing and analytics, massive number of IoT devices (sensors, actuators, etc.) are deployed to enable the monitoring and control of things under minor or no human intervention [1], [2], [3], [4], [5], [6], [7]. Mobile object tracking, a typical IoT application, along with other smart-world applications, such as smart grid, smart transportation, smart health, and smart manufacturing, are involving more and more IoT devices so that automatic monitoring and tracking on physical objects, including moving targets, vehicles, assets, etc., can be supported [8], [9], [10], [11], [12].

Nonetheless, it is a common practice that IoT devices are energy and computing constrained, and they are not competent to consistently handle complex mobile object tracking tasks, which are computationally intensive and consume lots of energy resources. Thus, computation offloading in IoT systems is a critical issue for accurate and efficient mobile object tracking. Our proposed scheme in this paper, designated Edge Computing-based Multivariate Time Series (EC-MTS) framework, endeavors to apply complex tracking technique to improve mobile object tracking performance in IoT systems and employs edge computing to offload computation intensive tasks that energy constrained IoT devices cannot handle. With an intent to understand how to track mobile objects in IoT systems and design corresponding solutions, a number of research efforts have been conducted [13], [14], [15], [16], [17], [18], [19]. The existing efforts demonstrate that the advance of mobile object tracking could support a diverse array of smart-world IoT applications (e.g., video surveillance, robot navigation, etc.) in dynamic environments.