基于边缘计算的视频监控框架
|
摘要
为降低云平台视频监控系统视频传输时延、视频分析处理开销和存储成本,提出一种基于边缘计算的视频监控框架。根据边缘节点地理位置靠近视频源的特点,将监控视频流的分析预处理工作迁移到边缘节点完成;设计边缘节点帧过滤算法,通过对视频流的目标识别,筛选出有效视频帧进行上传;在此基础上,设计边缘节点任务调度算法,提高视频流实时性和资源利用率。实验结果表明,该框架能够有效降低视频传输开销和视频分析处理开销。
To reduce transmission delay,video processing costs and video storage space of the cloud platform video surveillance system,a video surveillance framework based on edge computing was proposed.Based on the characteristics of the ECN's location near the source of surveillance,the analysis and preprocessing of the monitored video stream was offloaded to the ECN.The Frame-Selection algorithm was designed to select the effective video frames for uploading through the object detection of the video stream.On this basis,the ECN controller scheduling algorithm was designed to improve the timeliness and resource utilization of video streaming.Experimental results show that the proposed framework can significantly reduce unnecessary video traffic and the consumption of computing resources.
To reduce transmission delay,video processing costs and video storage space of the cloud platform video surveillance system,a video surveillance framework based on edge computing was proposed.Based on the characteristics of the ECN's location near the source of surveillance,the analysis and preprocessing of the monitored video stream was offloaded to the ECN.The Frame-Selection algorithm was designed to select the effective video frames for uploading through the object detection of the video stream.On this basis,the ECN controller scheduling algorithm was designed to improve the timeliness and resource utilization of video streaming.Experimental results show that the proposed framework can significantly reduce unnecessary video traffic and the consumption of computing resources.
引文
[1]Kangin D,Angelov P,Markarian G.Intelligent video surveillance[D].Lancaster:Lancaster University,2016.
[2]Chen X,Jiao L,Li W,et al.Efficient multi-user computation offloading for mobile-edge cloud computing[J].IEEE/ACM Transactions on Networking,2016,24(5):2795-2808.
[3]Mach P,Becvar Z. Mobile edge computing:A survey on architecture and computation offloading[J].IEEE Communications Surveys&Tutorials,2017(99):1.
[4]Wang Y,Sheng M,Wang X,et al.Mobile-edge computing:Partial computation offloading using dynamic voltage scaling[J].IEEE Transactions on Communications,2016,64(10):4268-4282.
[5]Anjum A,Abdullah T,Tariq M,et al.Video stream analysis in clouds:An object detection and classification framework for high performance video analytics[J].IEEE Transactions on Cloud Computing,2016(99):1.
[6]Gupta T,Singh RP,Phanishayee A,et al.Bolt:Data management for connected homes[C]//Usenix Conference on Networked Systems Design and Implementation.Washington:USENIX Association,2014:243-256.
[7]Kim H,Lee S,Kim Y,et al. Weighted joint-based human behavior recognition algorithm using only depth information for low-cost intelligent video-surveillance system[J].Expert Systems with Applications an International Journal,2016,45(C):131-141.
[8]Lin X,Wang Y,Xie Q,et al.Task scheduling with dynamic voltage and frequency scaling for energy minimization in the mobile cloud computing environment[J].IEEE Transactions on Services Computing,2015,8(2):175-186.
[9]Variani E, Mcdermott E, Heigold G.A Gaussian mixture model layer jointly optimized with discriminative features within a deep neural network architecture[C]//IEEE International Conference on Acoustics,Speech and Signal Processing.South Brisbane:IEEE,2015:4270-4274.
[10]Krizhevsky A,Sutskever I,Hinton GE.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(2):2012.
[11]Dong C,Chen CL, He K,et al.Image super-resolution using deep convolutional networks[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2016,38(2):295.
[12]Melendez S,McGarry MP.Computation offloading decisions for reducing completion time[C]//Consumer Communications&Networking Conference.Las Vegas:IEEE,2017:160-164.
[13]Bian N,Wang X,Mao L.Performance evaluation model for network simulation in heterogeneous computing environment[J].Journal of Frontiers of Computer Science&Technology,2015,145(4):425-426.
[14]Khamse-Ashari J,Kesidis G,Lambadaris I,et al.Max-min fair scheduling of variable-length packet-flows to multiple servers by deficit round-robin[C]//Conference on Information Science and Systems.Princeton:IEEE,2016:390-395.
[15]Bellard F,Niedermayer M.FFmpeg[EB/OL].[2017-06-23].http://ffmpeg.org.
[16]Winlin. SimpleRTSPserver[EB/OL].[2017-07-31].https://github.com/ossrs/srs.
[17]Ri Wei Chen.FaceTools[EB/OL].[2017-08-02].http://github.com/RiweiChen/FaceTools.
[18]Jia Y,Shelhamer E,Donahue J,et al.Caffe:Convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia.Orlando:ACM,2014:675-678.
[19]Ouyang W,Loy CC,Tang X,et al.DeepID-Net:Deformable deep convolutional neural networks for object detection[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2016(99):2403-2412.
[20]Schroff F,Kalenichenko D,Philbin J.FaceNet:A unified embedding for face recognition and clustering[C]//IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE Computer Society,2015:815-823.
[2]Chen X,Jiao L,Li W,et al.Efficient multi-user computation offloading for mobile-edge cloud computing[J].IEEE/ACM Transactions on Networking,2016,24(5):2795-2808.
[3]Mach P,Becvar Z. Mobile edge computing:A survey on architecture and computation offloading[J].IEEE Communications Surveys&Tutorials,2017(99):1.
[4]Wang Y,Sheng M,Wang X,et al.Mobile-edge computing:Partial computation offloading using dynamic voltage scaling[J].IEEE Transactions on Communications,2016,64(10):4268-4282.
[5]Anjum A,Abdullah T,Tariq M,et al.Video stream analysis in clouds:An object detection and classification framework for high performance video analytics[J].IEEE Transactions on Cloud Computing,2016(99):1.
[6]Gupta T,Singh RP,Phanishayee A,et al.Bolt:Data management for connected homes[C]//Usenix Conference on Networked Systems Design and Implementation.Washington:USENIX Association,2014:243-256.
[7]Kim H,Lee S,Kim Y,et al. Weighted joint-based human behavior recognition algorithm using only depth information for low-cost intelligent video-surveillance system[J].Expert Systems with Applications an International Journal,2016,45(C):131-141.
[8]Lin X,Wang Y,Xie Q,et al.Task scheduling with dynamic voltage and frequency scaling for energy minimization in the mobile cloud computing environment[J].IEEE Transactions on Services Computing,2015,8(2):175-186.
[9]Variani E, Mcdermott E, Heigold G.A Gaussian mixture model layer jointly optimized with discriminative features within a deep neural network architecture[C]//IEEE International Conference on Acoustics,Speech and Signal Processing.South Brisbane:IEEE,2015:4270-4274.
[10]Krizhevsky A,Sutskever I,Hinton GE.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(2):2012.
[11]Dong C,Chen CL, He K,et al.Image super-resolution using deep convolutional networks[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2016,38(2):295.
[12]Melendez S,McGarry MP.Computation offloading decisions for reducing completion time[C]//Consumer Communications&Networking Conference.Las Vegas:IEEE,2017:160-164.
[13]Bian N,Wang X,Mao L.Performance evaluation model for network simulation in heterogeneous computing environment[J].Journal of Frontiers of Computer Science&Technology,2015,145(4):425-426.
[14]Khamse-Ashari J,Kesidis G,Lambadaris I,et al.Max-min fair scheduling of variable-length packet-flows to multiple servers by deficit round-robin[C]//Conference on Information Science and Systems.Princeton:IEEE,2016:390-395.
[15]Bellard F,Niedermayer M.FFmpeg[EB/OL].[2017-06-23].http://ffmpeg.org.
[16]Winlin. SimpleRTSPserver[EB/OL].[2017-07-31].https://github.com/ossrs/srs.
[17]Ri Wei Chen.FaceTools[EB/OL].[2017-08-02].http://github.com/RiweiChen/FaceTools.
[18]Jia Y,Shelhamer E,Donahue J,et al.Caffe:Convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia.Orlando:ACM,2014:675-678.
[19]Ouyang W,Loy CC,Tang X,et al.DeepID-Net:Deformable deep convolutional neural networks for object detection[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2016(99):2403-2412.
[20]Schroff F,Kalenichenko D,Philbin J.FaceNet:A unified embedding for face recognition and clustering[C]//IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE Computer Society,2015:815-823.