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

doi:10.19678/j.issn.1000-3428.0064614

Abstract

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

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

CLC Number:

TP391

LUO Huafeng, SHEN Yifei, RUAN Lixiang, DU Qiwei, ZHENG Xiang, CHEN Zhiqi, ZHANG Sheng. Frame Offloading Scheduling Algorithm for Real-time Object Detection in Edge Environment[J]. Computer Engineering, 2023, 49(5): 295-301,309.

罗华峰, 沈奕菲, 阮黎翔, 杜奇伟, 郑翔, 陈智麒, 张胜. 边缘环境下面向实时目标检测的帧卸载调度算法[J]. 计算机工程, 2023, 49(5): 295-301,309.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0064614

http://www.ecice06.com/EN/Y2023/V49/I5/295

Figures/Tables 7

References

[1] Statista.Forecast number of mobile devices worldwide from 2020 to 2025[EB/OL].[2022-04-02].https://www.statista.com/statistics/245501/multiple-mobile-device-ownership-worldwide.
[2] LIU L Y,LI H Y,GRUTESER M.Edge assisted real-time object detection for mobile augmented reality[C]//Proceedings of the 25th Annual International Conference on Mobile Computing and Networking.New York,USA:ACM Press,2019:1-16.
[3] ZHANG H,ANANTHANARAYANAN G,BODIK P,et al.Live video analytics at scale with approximation and delay-tolerance[C]//Proceedings of the 14th Symposium on Networked Systems Design and Implementation.New York,USA:ACM Press,2017:377-392.
[4] RAN X K,CHEN H,ZHU X D,et al.DeepDecision:a mobile deep learning framework for edge video analytics[C]//Proceedings of IEEE Conference on Computer Communications.Washington D.C.,USA:IEEE Press,2018:1421-1429.
[5] ZHANG W,HE Z,LIU L,et al.Elf:accelerate high-resolution mobile deep vision with content-aware parallel offloading[C]//Proceedings of the 27th Annual International Conference on Mobile Computing and Networking.New York,USA:ACM Press,2021:201-214.
[6] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:779-788.
[7] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[8] XU L,JIA J Y,MATSUSHITA Y.Motion detail preserving optical flow estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(9):1744-1757.
[9] HOWARD A G,ZHU M,CHEN B,et al.MobileNets:efficient convolutional neural networks for mobile vision applications[EB/OL].[2022-04-02].https://arxiv.org/abs/1704.04861.
[10] LI Y,LI J,LIN W,et al.Tiny-DSOD:lightweight object detection for resource-restricted usages[EB/OL].[2022-04-02].https://arxiv.org/abs/1807.11013.
[11] HU C,BAO W,WANG D,et al.Dynamic adaptive DNN surgery for inference acceleration on the edge[C]//Proceedings of IEEE INFOCOM 2019-IEEE Conference on Computer Communications.Washington D.C.,USA:IEEE Press,2019:1423-1431.
[12] JEONG H J,LEE H J,SHIN C H,et al.IONN:incremental offloading of neural network computations from mobile devices to edge servers[C]//Proceedings of the ACM Symposium on Cloud Computing.New York,USA:ACM Press,2018:401-411.
[13] STAHL R,ZHAO Z R,MUELLER-GRITSCHNEDER D,et al.Fully distributed deep learning inference on resource-constrained edge devices[EB/OL].[2022-04-02].https://link.springer.com/chapter/10.1007/978-3-030-27562-4_6.
[14] HE J,QURESHI M A,QIU L L,et al.Rubiks:practical 360-degree streaming for smartphones[C]//Proceedings of the 16th Annual International Conference on Mobile Systems,Applications,and Services.New York,USA:ACM Press,2018:482-494.
[15] QIU H,AHMAD F,BAI F,et al.AVR:augmented vehicular reality[C]//Proceedings of the 16th Annual International Conference on Mobile Systems,Applications,and Services.New York,USA:ACM Press,2018:81-95.
[16] LI Y,REN F.Light-weight retinanet for object detection[EB/OL].[2022-04-02].https://arxiv.org/abs/1905.10011.
[17] WONG A,FAMUORI M,SHAFIEE M J,et al.YOLO nano:a highly compact you only look once convolutional neural network for object detection[EB/OL].[2022-04-02].https://arxiv.org/abs/1910.01271.
[18] HE W C,GUO S Y,GUO S,et al.Joint DNN partition deployment and resource allocation for delay-sensitive deep learning inference in IoT[J].IEEE Internet of Things Journal,2020,7(10):9241-9254.
[19] JIANG J C,ANANTHANARAYANAN G,BODIK P,et al.Chameleon:scalable adaptation of video analytics[C]//Proceedings of 2018 Conference of the ACM Special Interest Group on Data Communication.New York,USA:ACM Press,2018:253-266.
[20] LIU L Y,ZHONG R G,ZHANG W Y,et al.Cutting the cord:designing a high-quality untethered VR system with low latency remote rendering[C]//Proceedings of the 16th Annual International Conference on Mobile Systems,Applications,and Services.New York,USA:ACM Press,2018:68-80.
[21] CHENG Y,LI D,GUO Z Y,et al.DLBooster:boosting end-to-end deep learning workflows with offloading data preprocessing pipelines[C]//Proceedings of the 48th International Conference on Parallel Processing.New York,USA:ACM Press,2019:1-11.
[22] HUANG L,BI S Z,ZHANG Y J A.Deep reinforcement learning for online computation offloading in wireless powered mobile-edge computing networks[J].IEEE Transactions on Mobile Computing,2020,19(11):2581-2593.
[23] WANG C,ZHANG S,CHEN Y,et al.Joint configuration adaptation and bandwidth allocation for edge-based real-time video analytics[C]//Proceedings of IEEE Conference on Computer Communications.New York,USA:ACM Press,2020:257-266.
[24] CHEN N,QUAN S Y,ZHANG S,et al.Cuttlefish:neural configuration adaptation for video analysis in live augmented reality[J].IEEE Transactions on Parallel and Distributed Systems,2021,32(4):830-841.
[25] SUN Y,ZHU H S,ZHUANG F Z,et al.Exploring the urban region-of-interest through the analysis of online map search queries[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.New York,USA:ACM Press,2018:2269-2278.
[26] CHAI Z,LI S,HE Q,et al.FPGA-based ROI encoding for HEVC video bitrate reduction[J].Journal of Circuits,Systems and Computers,2020,29(11):82-93.
[27] ILG E,MAYER N,SAIKIA T,et al.Flownet 2.0:evolution of optical flow estimation with deep networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2462-2470.
[28] Xiph.org.Derf's test media collection[EB/OL].[2021-12-02].https://media.xiph.org/video/derf/.
[29] MOUSAVIAN A,ANGUELOV D,FLYNN J,et al.3D bounding box estimation using deep learning and geometry[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:5632-5640.

Please choose a citation manager

Content to export