论文标题
SmartDet：上下文感知边缘任务的动态控制移动对象检测
SmartDet: Context-Aware Dynamic Control of Edge Task Offloading for Mobile Object Detection
论文作者
论文摘要
移动设备越来越多地通过深层神经网络（DNN）依赖对象检测（OD）来执行关键任务。由于它们的高复杂性，这些DNN的执行需要过多的时间和能量。低复杂对象跟踪（OT）可以与OD一起使用，后者定期应用以生成“新鲜”参考以进行跟踪。但是，使用OD处理的框架会产生较大的延迟，这可能会使参考过时并降低跟踪质量。本文中，我们建议在此上下文中使用边缘计算，并在移动设备上（在移动设备上）和OD（在边缘服务器上的OD（在边缘服务器上）进行弹性弹性延迟。我们提出了Katch-Up，这是一种新颖的跟踪机制，可提高系统对过度OD延迟的弹性。但是，尽管Katch-Up显着提高了性能，但它也增加了移动设备的计算负载。因此，我们设计了SmartDet，这是一种基于深度强化学习（DRL）的低复杂控制器，该控制器学习控制资源利用率和OD性能之间的权衡。 SmartDet将与当前视频内容和当前网络条件相关的输入相关信息作为输入相关信息，以优化OD卸载的频率和类型，以及Katch-Up利用率。我们在由Jetson Nano组成的实际测试床上广泛评估SMARTDET，作为移动设备和GTX 980 Ti作为Edge Server，通过Wi-Fi链接连接。实验结果表明，SmartDet在跟踪性能 - 平均平均召回率（MAR）和资源使用情况之间取得了最佳平衡。关于完全katchususage和最大通道使用的基线，我们仍将MAR增加4％，而使用少50％的频道和与Katch-Up相关的30％功率资源。关于使用最少资源的固定策略，我们在1/3帧上使用Katch-Up时将MAR增加20％。
Mobile devices increasingly rely on object detection (OD) through deep neural networks (DNNs) to perform critical tasks. Due to their high complexity, the execution of these DNNs requires excessive time and energy. Low-complexity object tracking (OT) can be used with OD, where the latter is periodically applied to generate "fresh" references for tracking. However, the frames processed with OD incur large delays, which may make the reference outdated and degrade tracking quality. Herein, we propose to use edge computing in this context, and establish parallel OT (at the mobile device) and OD (at the edge server) processes that are resilient to large OD latency. We propose Katch-Up, a novel tracking mechanism that improves the system resilience to excessive OD delay. However, while Katch-Up significantly improves performance, it also increases the computing load of the mobile device. Hence, we design SmartDet, a low-complexity controller based on deep reinforcement learning (DRL) that learns controlling the trade-off between resource utilization and OD performance. SmartDet takes as input context-related information related to the current video content and the current network conditions to optimize frequency and type of OD offloading, as well as Katch-Up utilization. We extensively evaluate SmartDet on a real-world testbed composed of a JetSon Nano as mobile device and a GTX 980 Ti as edge server, connected through a Wi-Fi link. Experimental results show that SmartDet achieves an optimal balance between tracking performance - mean Average Recall (mAR) and resource usage. With respect to a baseline with full Katch-Upusage and maximum channel usage, we still increase mAR by 4% while using 50% less of the channel and 30% power resources associated with Katch-Up. With respect to a fixed strategy using minimal resources, we increase mAR by 20% while using Katch-Up on 1/3 of the frames.
