计算机科学

计算机科学 ›› 2021, Vol. 48 ›› Issue (4): 180-186.doi: 10.11896/jsjkx.201200116

• 计算机图形学&多媒体 • 上一篇    下一篇

多分辨率下资源感知的图像目标自适应缩放检测

张开强1, 蒋从锋1, 程小兰1, 贾刚勇1, 张纪林2, 万健3   

  1. 1 杭州电子科技大学计算机学院 杭州310018
    2 杭州电子科技大学网络空间安全学院 杭州310018
    3 浙江科技学院信息与电子工程学院 杭州310023
  • 收稿日期:2020-06-24 修回日期:2021-03-01 出版日期:2021-04-15 发布日期:2021-04-09
  • 通讯作者: 蒋从锋(cjiang@hdu.edu.cn)
  • 基金资助:
    国家自然科学基金面上项目(61972118,61972358),浙江省重点研发计划项目(2019C01059)

Resource-aware Based Adaptive-scaling Image Target Detection Under Multi-resolution Scenario

ZHANG Kai-qiang1, JIANG Cong-feng1, CHENG Xiao-lan1, JIA Gang-yong1, ZHANG Ji-lin2, WAN Jian3   

  1. 1 School of Computer Science and Technology,Hangzhou Dianzi University,Hangzhou 310018,China
    2 School of Cyber Science and Engineering,Hangzhou Dianzi University,Hangzhou 310018,China
    3 School of Information and Electronic Engineering,Zhejiang University of Science and Technology,Hangzhou 310023,China
  • Received:2020-06-24 Revised:2021-03-01 Online:2021-04-15 Published:2021-04-09
  • About author:ZHANG Kai-qiang,born in 1997,postgraduate,is a student member of China Computer Federation.His main research interests include edge computing and system optimization.(zkqcs@hdu.edu.cn)
    JIANG Cong-feng,born in 1980,Ph.D,professor,is a member of China Computer Federation.His main research interests include edge computing,system optimization,performance evaluation and distributed system benchmarking.
  • Supported by:
    General Program of National Natural Science Foundation of China(61972118,61972358) and Zhejiang Key Research and Development Project of China(2019C01059).

PDF (PC)

709

摘要： 边缘视频处理可以降低云平台视频处理系统的视频传输时延、视频处理开销和存储成本,但是视频参数(分辨率、帧率等)的多样性容易导致边缘视频处理的效果不尽人意。通常,在图像预处理阶段会先对图像进行缩放变换再进行后续处理,以保障图像处理的最佳效果,但是在视频监控等具有不确定性的场景中对所有分辨率的图像直接成倍缩小容易降低目标检测率。基于以上问题,把图像水平像素点和垂直像素点的缩放倍数记作图像缩放因子,对于不同分辨率的视频数据,分析了图像缩放因子对视频数据处理效果的影响,提出了图像缩放因子动态设置方案。该方案以系统性能指标(服务器端系统功耗和内存使用率)为视频处理性能指标(人脸检测率)的约束条件,获取该分辨率下人脸检测率最优时对应的图像缩放因子。实验结果表明,对于不同分辨率的视频数据,图像缩放因子动态设置方案可以在保证视频处理性能的基础上,减少系统功耗和内存使用率,提高视频处理效率。

关键词: 边缘计算, 人脸检测, 视频参数, 视频处理, 图像缩放

Abstract: Edge video processing can reduce the video transmission delay,video processing overhead and storage cost in the video processing system of cloud platform,but the diversity of video parameters (resolution,frame rate,etc.) will lead to unsatisfactory effect of edge video processing.Usually,in the stage of image pre-processing,image scaling and transformation will be applied to ensure the best effect of image processing.However,in uncertain scenes such as video monitoring,the target detection rate can be reduced largely by directly scaling down the resolution of all the images.According to the problems mentioned above,this paper chooses the scaling ratio of the horizontal and vertical pixels as image scaling factor.For the video data with different resolutions,it analyzes the influence of the image scaling factor on the performance of video data processing and puts forward the dynamically-setting scheme of image scaling factor.In this scheme,the system performance index (system power consumption and memory utilization of the server-side) is taken as the constraint condition of video processing performance index (face detection rate),to get the image scaling factor corresponding to the optimal face detection rate with this resolution.Experimental results show that for video data with different resolutions,the dynamic setting scheme of image scaling factor can reduce system power consumption and memory utilization,improve video processing efficiency and capability while guaranteeing video processing performance.

Key words: Edge computing, Face detection, Image scaling, Video parameters, Video processing

中图分类号: 

  • TP391
[1]ZHOU B,DASTJERDI A V,CALHEIROS R N,et al.mCloud:A context-aware offloading framework forheterogeneous mobile cloud [J].IEEE Transactions on Services Computing,2017,10(5):797-810.
[2]LIU W,HUANG Y C,DU W,et al.Resource-Constrained Serial Task Offload Strategy in Mobile Edge Computing [J].Journal of Software,2020,31(6):1889-1908.
[3]MA H R,CHEN X,ZHOU Z,et al.Dynamic Task Offloading for Mobile Edge Computing with Green Energy [J].Journal of Computer Research and Development,2020,31(6):1889-1908.
[4]LIU Y,XU C,ZHAN Y,et al.Incentive mechanism for computation offloading using edge computing:a Stackelberg game approach [J].Computer Networks,2017,129:399-409.
[5]ME E,TODD T D,ZHAO D,et al.Energy awareoffloading for competing users on a shared communication channel [J].IEEE Transactions on Mobile Computing,2017,16(1):87-96.
[6]CHEN X.Decentralized computation offloading game for mobile cloud computing [J].IEEE Transactions on Parallel andDistri-buted Systems,2015,26(4):974-983.
[7]CHEN X,JIAO L,LI W,et al.Efficient multi-user computation offloading for mobile-edge cloud computing [J].IEEE/ACM Transactions on Networking,2016(5):2795-2808.
[8]JIA M,CAO J,YANG L.Heuristic offloading of concurrenttasks for computation-intensive applications in mobile cloud computing [C]//Proceedings of the IEEE Conference on Computer Communications Workshops.2014:352-357.
[9]YU B W,PU L J,XIE Y L,et al.Joint Task Offloading and Base Station Association in Mobile Edge Computing [J].Journal of Computer Research and Development,2018,55(3):537-550.
[10]BILAL K,ERBAD A.Edge computing for interactive media and video streaming[C]//Proceedings of the Second International Conference on Fog and Mobile Edge Computing (FMEC).2017:68-73.
[11]LONG C,CAO Y,JIANG T,et al.Edge computing framework for cooperative video processing in multimedia IoT systems [J].IEEE Transactions on Multimedia,2018,20(5):1126-1139.
[12]BAILAS C,MARSDEN M,ZHANG D,et al.Performance of video processing at the edge for crowd-monitoring applications [C]//Proceedings of the 4th World Forum on Internet of Things (WF-IoT).2018:482-487.
[13]TRAN T X,PANDEY P,HAJISAMI A,et al.Collaborative multi-bitrate video caching and processing in mobile-edge computing networks[C]//Proceedings of the 13thAnnual Confe-rence on Wireless On-demand Network Systems and Services (WONS).2017:165-172.
[14]JIANG W,CHEN G,YANG F,et al.Self-adaptive Image Sca-ling Algorithm Based on Sobel Operator [J].Computer Engineering,2010,36(7):214-216.
[15]WANG D,ZHAO H W,DAI Y,et al.A face detection acceleration algorithm based on regression [J].JournalofChongqingUniversityofPostandTelecommunications(NaturalScienceEdition),2019,31(4):550-555.
[16]SHI W S,SUN H,CHEN Y M.Prospect of new video surveillance system based on edge computing [J].China Academic Journal Electronic Publishing House,2018,35(12):60-63.
[17]GE C,BAI G W,SHEN H,et al.Edge computing-based video surveillance framework [J].Computer Engineering and Design,2019,40(1):32-39.
[18]MANGIANTE S,KLAS G,NAVON A,et al.VR is on theedge:How to deliver 360 videos in mobile networks[C]//Proceedings of the Workshop on Virtual Reality and Augmented Reality Network.2017:30-35.
[19]HU P,NING H,QIU T,et al.Fog computing based face identification and resolution scheme in Internet of Things [J].IEEE Transactions on Industrial Informatics,2017,13(4):1910-1920.
[20]ZHANG Q,ZHANG Q,SHI W,et al.Distributed collaborative execution on the edges and its application to AMBER alerts [J].IEEE Internet of Things Journal,2018,5(5):3580-3593.
[21]ZHANG Z,ZHANG X Q,ZUO D C,et al.Research on Target Tracking Application Deployment Strategy for Edge Computing [J].Journal of Software,2020,31(9):2691-2708.
[22]SUN H,YU Y,SHA K,et al.mVideo:Edge Computing Based Mobile Video Processing Systems [J].IEEE Access,2019,8:11615-11623.
[23]LONG C C,CAO Y,JIANG T,et al.Edge Computing Framework for Cooperative Video Processing in Multimedia IoT Systems [J].IEEE Transactions on Multimedia,2017,20(5):1126-1139.
[1] 孙慧婷, 范艳芳, 马孟晓, 陈若愚, 蔡英.
VEC中基于动态定价的车辆协同计算卸载方案
Dynamic Pricing-based Vehicle Collaborative Computation Offloading Scheme in VEC
计算机科学, 2022, 49(9): 242-248. https://doi.org/10.11896/jsjkx.210700166
[2] 于滨, 李学华, 潘春雨, 李娜.
基于深度强化学习的边云协同资源分配算法
Edge-Cloud Collaborative Resource Allocation Algorithm Based on Deep Reinforcement Learning
计算机科学, 2022, 49(7): 248-253. https://doi.org/10.11896/jsjkx.210400219
[3] 李梦菲, 毛莺池, 屠子健, 王瑄, 徐淑芳.
基于深度确定性策略梯度的服务器可靠性任务卸载策略
Server-reliability Task Offloading Strategy Based on Deep Deterministic Policy Gradient
计算机科学, 2022, 49(7): 271-279. https://doi.org/10.11896/jsjkx.210600040
[4] 袁昊男, 王瑞锦, 郑博文, 吴邦彦.
基于Fabric的电子病历跨链可信共享系统设计与实现
Design and Implementation of Cross-chain Trusted EMR Sharing System Based on Fabric
计算机科学, 2022, 49(6A): 490-495. https://doi.org/10.11896/jsjkx.210500063
[5] 方韬, 杨旸, 陈佳馨.
D2D辅助移动边缘计算下的卸载策略优化
Optimization of Offloading Decisions in D2D-assisted MEC Networks
计算机科学, 2022, 49(6A): 601-605. https://doi.org/10.11896/jsjkx.210200114
[6] 刘漳辉, 郑鸿强, 张建山, 陈哲毅.
多无人机使能移动边缘计算系统中的计算卸载与部署优化
Computation Offloading and Deployment Optimization in Multi-UAV-Enabled Mobile Edge Computing Systems
计算机科学, 2022, 49(6A): 619-627. https://doi.org/10.11896/jsjkx.210600165
[7] 谢万城, 李斌, 代玥玥.
空中智能反射面辅助边缘计算中基于PPO的任务卸载方案
PPO Based Task Offloading Scheme in Aerial Reconfigurable Intelligent Surface-assisted Edge Computing
计算机科学, 2022, 49(6): 3-11. https://doi.org/10.11896/jsjkx.220100249
[8] 周天清, 岳亚莉.
超密集物联网络中多任务多步计算卸载算法研究
Multi-Task and Multi-Step Computation Offloading in Ultra-dense IoT Networks
计算机科学, 2022, 49(6): 12-18. https://doi.org/10.11896/jsjkx.211200147
[9] 彭冬阳, 王睿, 胡谷雨, 祖家琛, 王田丰.
视频缓存策略中QoE和能量效率的公平联合优化
Fair Joint Optimization of QoE and Energy Efficiency in Caching Strategy for Videos
计算机科学, 2022, 49(4): 312-320. https://doi.org/10.11896/jsjkx.210800027
[10] 张海波, 张益峰, 刘开健.
基于NOMA-MEC的车联网任务卸载、迁移与缓存策略
Task Offloading,Migration and Caching Strategy in Internet of Vehicles Based on NOMA-MEC
计算机科学, 2022, 49(2): 304-311. https://doi.org/10.11896/jsjkx.210100157
[11] 林潮伟, 林兵, 陈星.
边缘环境下基于模糊理论的科学工作流调度研究
Study on Scientific Workflow Scheduling Based on Fuzzy Theory Under Edge Environment
计算机科学, 2022, 49(2): 312-320. https://doi.org/10.11896/jsjkx.201000102
[12] 梁俊斌, 张海涵, 蒋婵, 王天舒.
移动边缘计算中基于深度强化学习的任务卸载研究进展
Research Progress of Task Offloading Based on Deep Reinforcement Learning in Mobile Edge Computing
计算机科学, 2021, 48(7): 316-323. https://doi.org/10.11896/jsjkx.200800095
[13] 景慧昀, 周川, 贺欣.
针对人脸检测对抗攻击风险的安全测评方法
Security Evaluation Method for Risk of Adversarial Attack on Face Detection
计算机科学, 2021, 48(7): 17-24. https://doi.org/10.11896/jsjkx.210300305
[14] 田洋, 毕秀丽, 肖斌, 李伟生, 马建峰.
基于离散切比雪夫变换的图像接缝裁剪篡改检测
Image Seam Carving Tampering Detection by Discrete Tchebichef Transform
计算机科学, 2021, 48(6A): 43-50. https://doi.org/10.11896/jsjkx.200800020
[15] 钱甜甜, 张帆.
基于分布式边缘计算的情绪识别系统
Emotion Recognition System Based on Distributed Edge Computing
计算机科学, 2021, 48(6A): 638-643. https://doi.org/10.11896/jsjkx.201000010
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发