Networked Cameras Are the New Big Data Clusters

The increasing complexity of deep learning and massive deployment of cameras at the edge have drastically increased the resource demand of edge data analytics. Compared to traditional Internet web applications, such resource demand (in computing, storage and networking) is not limited by millions of human users, but rather the continuous activities of billions of sensors. This paper presents the abstraction of camera cluster as an attempt to address this challenge in the context of video analytics. We envision a novel analytics stack that orchestrates the computing resource of massive networked cameras to enable efficient edge video analytics.

[1]  Xuanzhe Liu,et al.  DeepCache: Principled Cache for Mobile Deep Vision , 2017, MobiCom.

[2]  Tianshu Chu,et al.  Neural Networks Meet Physical Networks: Distributed Inference Between Edge Devices and the Cloud , 2018, HotNets.

[3]  Srikanth Kandula,et al.  Multi-resource packing for cluster schedulers , 2014, SIGCOMM.

[4]  Jianli Pan,et al.  Future Edge Cloud and Edge Computing for Internet of Things Applications , 2018, IEEE Internet of Things Journal.

[5]  Paramvir Bahl,et al.  GLIMPSE: Continuous, Real-Time Object Recognition on Mobile Devices , 2016, GetMobile Mob. Comput. Commun..

[6]  Paramvir Bahl,et al.  Focus: Querying Large Video Datasets with Low Latency and Low Cost , 2018, OSDI.

[7]  Lin Zhong,et al.  Starfish: Efficient Concurrency Support for Computer Vision Applications , 2015, MobiSys.

[8]  Paramvir Bahl,et al.  Real-Time Video Analytics: The Killer App for Edge Computing , 2017, Computer.

[9]  Arun Ravindran,et al.  An Edge Datastore Architecture For Latency-Critical Distributed Machine Vision Applications , 2018, HotEdge.

[10]  Bowen Zhang,et al.  Real-Time Action Recognition with Enhanced Motion Vector CNNs , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Zheng Zhang,et al.  MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems , 2015, ArXiv.

[12]  Seungyeop Han,et al.  Fast Video Classification via Adaptive Cascading of Deep Models , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Matei Zaharia,et al.  NoScope: Optimizing Deep CNN-Based Queries over Video Streams at Scale , 2017, Proc. VLDB Endow..

[14]  Edward A. Lee,et al.  AWStream: adaptive wide-area streaming analytics , 2018, SIGCOMM.

[15]  Xiaogang Wang,et al.  Intelligent multi-camera video surveillance: A review , 2013, Pattern Recognit. Lett..

[16]  Aakanksha Chowdhery,et al.  Reinventing Video Streaming for Distributed Vision Analytics , 2018, HotCloud.

[17]  Paramvir Bahl,et al.  VideoEdge: Processing Camera Streams using Hierarchical Clusters , 2018, 2018 IEEE/ACM Symposium on Edge Computing (SEC).

[18]  Leibo Liu,et al.  RANA: Towards Efficient Neural Acceleration with Refresh-Optimized Embedded DRAM , 2018, 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA).

[19]  Andreas Moshovos,et al.  Bit-Pragmatic Deep Neural Network Computing , 2016, 2017 50th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO).

[20]  Randy H. Katz,et al.  The Datacenter Needs an Operating System , 2011, HotCloud.

[21]  Rajesh Krishna Balan,et al.  DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications , 2017, MobiSys.

[22]  H. T. Kung,et al.  Distributed Deep Neural Networks Over the Cloud, the Edge and End Devices , 2017, 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS).

[23]  Ion Stoica,et al.  Chameleon: scalable adaptation of video analytics , 2018, SIGCOMM.

[24]  Aakanksha Chowdhery,et al.  The Design and Implementation of a Wireless Video Surveillance System , 2015, MobiCom.

[25]  Trevor N. Mudge,et al.  Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge , 2017, ASPLOS.

[26]  Felix Xiaozhu Lin,et al.  VStore: A Data Store for Analytics on Large Videos , 2018, EuroSys.

[27]  Khaled A. Harras,et al.  Femto Clouds: Leveraging Mobile Devices to Provide Cloud Service at the Edge , 2015, 2015 IEEE 8th International Conference on Cloud Computing.

[28]  Katherine Guo,et al.  Cachier: Edge-Caching for Recognition Applications , 2017, 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS).

[29]  Ronald G. Dreslinski,et al.  Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers , 2015, ASPLOS.

[30]  Katia Obraczka,et al.  Wireless Smart Camera Networks for the Surveillance of Public Spaces , 2014, Computer.

[31]  Benjamin Hindman,et al.  Dominant Resource Fairness: Fair Allocation of Multiple Resource Types , 2011, NSDI.

[32]  Christian Damsgaard Jensen,et al.  Video Surveillance: Privacy Issues and Legal Compliance , 2015 .

[33]  Peizhen Guo,et al.  Potluck: Cross-Application Approximate Deduplication for Computation-Intensive Mobile Applications , 2018, ASPLOS.

[34]  Aakanksha Chowdhery,et al.  Optasia: A Relational Platform for Efficient Large-Scale Video Analytics , 2016, SoCC.

[35]  Gregory R. Ganger,et al.  Mainstream: Dynamic Stem-Sharing for Multi-Tenant Video Processing , 2018, USENIX Annual Technical Conference.

[36]  Suman Banerjee,et al.  ParaDrop: a multi-tenant platform to dynamically install third party services on wireless gateways , 2014, MobiArch '14.

[37]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[38]  Khaled A. Harras,et al.  Workload management for dynamic mobile device clusters in edge femtoclouds , 2017, SEC.

[39]  Alec Wolman,et al.  MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints , 2016, MobiSys.

[40]  Xiao Zeng,et al.  NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision , 2018, MobiCom.

[41]  Samvit Jain,et al.  Scaling Video Analytics Systems to Large Camera Deployments , 2018, HotMobile.

[42]  Paramvir Bahl,et al.  Live Video Analytics at Scale with Approximation and Delay-Tolerance , 2017, NSDI.