作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2023, Vol. 49 ›› Issue (5): 295-301,309. doi: 10.19678/j.issn.1000-3428.0064614

• 开发研究与工程应用 • 上一篇    下一篇

边缘环境下面向实时目标检测的帧卸载调度算法

罗华峰1, 沈奕菲1, 阮黎翔1, 杜奇伟2, 郑翔3, 陈智麒4, 张胜4   

  1. 1. 国网浙江省电力有限公司电力科学研究院, 杭州 310014;
    2. 国网浙江省电力有限公司, 杭州 310007;
    3. 国网浙江省电力有限公司衢州供电公司, 浙江 衢州 324000;
    4. 南京大学 计算机软件新技术国家重点实验室, 南京 210023
  • 收稿日期:2022-05-05 修回日期:2022-06-21 发布日期:2022-08-31
  • 作者简介:罗华峰(1989-),男,高级工程师、硕士,主研方向为目标检测;沈奕菲,工程师;阮黎翔、杜奇伟、郑翔,高级工程师;陈智麒,硕士;张胜(通信作者),副教授、博士生导师。
  • 基金资助:
    国网浙江电力有限公司科技项目(5211DS200087)。

Frame Offloading Scheduling Algorithm for Real-time Object Detection in Edge Environment

LUO Huafeng1, SHEN Yifei1, RUAN Lixiang1, DU Qiwei2, ZHENG Xiang3, CHEN Zhiqi4, ZHANG Sheng4   

  1. 1. State Grid Zhejiang Electric Power Co., Ltd. Electric Power Science Research Institute, Hangzhou 310014, China;
    2. State Grid Zhejiang Electric Power Co., Ltd., Hangzhou 310007, China;
    3. State Grid Zhejiang Electric Power Co., Ltd. Quzhou Power Supply Company, Quzhou 324000, Zhejiang, China;
    4. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China
  • Received:2022-05-05 Revised:2022-06-21 Published:2022-08-31

摘要: 边缘环境下的目标检测应用大多依赖于边缘设备。目前,MobileNet等轻量级检测模型在满足实时性要求的前提下难以达到准确度要求,Faster RCNN等重量级模型的检测准确度较高,但数据传输耗时大,难以保证检测实时性。提出一种边缘辅助的目标检测框架及自适应帧卸载(OEOD)算法,在线将视频帧卸载到边缘服务器,以执行高准确度、高时延的目标检测,或在本地执行低准确度、低时延的目标检测,从而在满足给定检测准确度要求的前提下缩短视频帧的平均处理时延。为实现OEOD算法,提出一种基于内容相似性的特征向量度量方式,以预测当前帧的检测时延和准确度,并以贪心的方式决定当前帧的检测策略。实验结果表明,与MobileNet算法相比,OEOD算法在保证准确度的前提下将检测时延降低了29%,且在不同的数据集上均表现良好。

关键词: 边缘计算, 目标检测, 计算卸载, 在线调度, 时延优化

Abstract: The application of object detection in edge environment mostly depends on the edge device. At present,lightweight detection models,such as MobileNet,have difficulty simultaneously meeting real-time and accuracy requirements. Heavyweight models,such as Faster RCNN,have high detection accuracy but data transmission is time-consuming,making it difficult to ensure real-time detection. An edge assisted object detection framework and adaptive frame offloading algorithm called OEOD is proposed,which,given an accuracy requirement,adaptively chooses to offload a video frame to an edge server for high-accuracy high-delay object detection or locally run low-accuracy low-delay object detection,which optimizes the average per-frame detection delay. To implement OEOD algorithm,we also propose a feature vector measurement method based on content similarity to predict the detection delay and accuracy of the current frame and determine the detection strategy of the current frame in a greedy manner. Experimental results show that OEOD algorithm can reduce the per-frame delay by 29% compared with MobileNet given a fixed accuracy requirement,and performs well on different datasets.

Key words: edge computing, object detection, computation offloading, online scheduling, delay optimization

中图分类号: