Analysis and Design of an Edge Computing Enabled Real-Time Object Detection Platform for Drone-as-a-Service Using Network Calculus
Analysis and Design of an Edge Computing Enabled Real-Time Object Detection Platform for Drone-as-a-Service Using Network Calculus
复制标题
DOI：
10.1109/icc45041.2023.10278785
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Boyang Zhou;Ryan Cheng;Unmesh Khanolkar;Liang Cheng
中科院分区：
文献类型：
--
作者：
Boyang Zhou;Ryan Cheng;Unmesh Khanolkar;Liang Cheng
许多无人机即服务（DaaS）应用（诸如监视、搜索和救援以及基础设施检查）可以采用实时对象检测来实现基于计算机视觉的自主功能。然而，运行对象检测算法，例如，无人机上的本地YOLO需要大量的计算能力，这在成本和能耗方面都很昂贵。相反，边缘计算有助于实现一个经济高效的平台，无人机可以压缩图像并将其传输到边缘服务器，以进行实时目标检测。尽管如此，应用支持边缘计算的实时对象检测（ECOD）的DaaS设计人员必须了解ECOD平台的网络设计和性能，以确保实时对象检测。在我们的研究中，我们提出了一种方法来分析延迟性能的ECOD平台利用网络演算。一个测试平台的实施，以评估这种方法的有效性。分析结果为ECOD平台的设计提供了原则性的指导。本文提供的示例说明了如何在DaaS中的流量配置文件，网络容量和延迟要求方面将指南应用于ECOD平台设计。
Numerous Drone-as-a-Service (DaaS) applications, such as surveillance, search and rescue, and infrastructure inspection, may employ realtime object detection to achieve computer vision-based autonomous functions. However, running object detection algorithms, e.g., YOLO, locally on a drone requires extensive computational power, which is expensive in terms of cost and energy consumption. Conversely, edge computing facil-itates the implementation of an affordable and efficient platform where drones compress and transmit images to an edge server for realtime object detection. Nevertheless, DaaS designers applying Edge Computing Enabled Real-Time Object Detection (ECOD) must be cognizant of the network design and performance of the ECOD platform to ensure object detection in realtime. In our research, we propose an approach to analyzing the delay performance of an ECOD platform utilizing network calculus. A testbed was implemented to evaluate the effectiveness of this approach. The analysis result provides principled guidance for the ECOD platform design lacking in previous studies. Examples are provided in this paper to illustrate how to apply the guidance to the ECOD platform design in terms of traffic profile, network capacity, and delay requirements in DaaS.