Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications
Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications
复制标题
DOI：
10.1109/tgcn.2020.3041666
复制
发表时间：
2020-11
影响因子：
4.8
通讯作者：
Haoxin Wang;Baekgyu Kim;Jiang Xie;Zhu Han
中科院分区：
文献类型：
--
作者：
Haoxin Wang;Baekgyu Kim;Jiang Xie;Zhu Han
将深度学习应用于对象检测提供了准确检测和分类现实世界中复杂对象的能力。然而，目前很少有移动应用程序使用深度学习，因为这种技术是计算密集型且耗能的。据我们所知，本文首次对移动增强现实 (AR) 客户端的能耗和执行基于卷积神经网络 (CNN) 的对象检测的检测延迟进行了详细的实验研究，无论是在智能手机本地还是在边缘服务器上远程执行。为了准确测量智能手机上的能耗并获得目标检测处理管道每个阶段消耗的能耗明细，我们提出了一种新的测量策略。我们详细的测量改进了移动 AR 客户端的能耗分析，并揭示了有关执行基于 CNN 的对象检测的能耗的几个有趣的观点。此外，根据我们的实验结果提出了一些见解和研究机会。我们实验研究的这些发现将指导基于 CNN 的目标检测的节能处理流程的设计。
Applying deep learning to object detection provides the capability to accurately detect and classify complex objects in the real world. However, currently, few mobile applications use deep learning because such technology is computation-intensive and energy-consuming. This article, to the best of our knowledge, presents the first detailed experimental study of a mobile augmented reality (AR) client’s energy consumption and the detection latency of executing Convolutional Neural Networks (CNN) based object detection, either locally on the smartphone or remotely on an edge server. In order to accurately measure the energy consumption on the smartphone and obtain the breakdown of energy consumed by each phase of the object detection processing pipeline, we propose a new measurement strategy. Our detailed measurements refine the energy analysis of mobile AR clients and reveal several interesting perspectives regarding the energy consumption of executing CNN-based object detection. Furthermore, several insights and research opportunities are proposed based on our experimental results. These findings from our experimental study will guide the design of energy-efficient processing pipeline of CNN-based object detection.