Deep Learning Based Couple-like Cooperative Computing Method for IoT-based Intelligent Surveillance Systems

Given vast expansion of video/data in many Internet of things (IoT) based intelligent surveillance systems, transferring data consumes many internet resources. Real-time intelligent analysis of multichannel digital video streams also poses substantial challenges to traditional central-based computing when applying ubiquitous IoT. In this paper, we put forth a couple-like computing method using cooperative computing between a central server and edge terminal for timely detection of potential risks at construction sites. Specifically, we assemble NVIDIA Jetson TX2 on each surveillance terminal and compute video at 3 frames per second for coarse detection. If the target is identified, the video is then transmitted to the central server for precise detection. The main contributions of this paper are twofold: reducing network traffic and reducing the computational burden for the central server. Our experiment is conducted using IoTbased intelligent surveillance systems at a real construction site to confirm the feasibility of the proposed method.

[1]  Roger Zimmermann,et al.  Dynamic Urban Surveillance Video Stream Processing Using Fog Computing , 2016, 2016 IEEE Second International Conference on Multimedia Big Data (BigMM).

[2]  Yunju Baek,et al.  CamThings: IoT Camera with Energy-Efficient Communication by Edge Computing based on Deep Learning , 2018, 2018 28th International Telecommunication Networks and Applications Conference (ITNAC).

[3]  Weisong Shi,et al.  Edge Computing: Vision and Challenges , 2016, IEEE Internet of Things Journal.

[4]  Yifan Li,et al.  Parallel video processing using embedded computers , 2017, 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[5]  Mohsen Guizani,et al.  Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications , 2015, IEEE Communications Surveys & Tutorials.

[6]  Randy H. Katz,et al.  A view of cloud computing , 2010, CACM.

[7]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  John A. Stankovic,et al.  Research Directions for the Internet of Things , 2014, IEEE Internet of Things Journal.

[9]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[10]  Rui Peng,et al.  Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures , 2016, ArXiv.

[11]  Ying Chen,et al.  Energy Efficient Scheduling and Management for Large-Scale Services Computing Systems , 2017, IEEE Transactions on Services Computing.

[12]  Tao Jiang,et al.  Edge Computing Framework for Cooperative Video Processing in Multimedia IoT Systems , 2018, IEEE Transactions on Multimedia.

[13]  Bo Chen,et al.  MnasNet: Platform-Aware Neural Architecture Search for Mobile , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Guan Gui,et al.  Deep Learning for Risk Detection and Trajectory Tracking at Construction Sites , 2019, IEEE Access.

[15]  Liu Wei,et al.  Edge Computing—An Emerging Computing Model for the Internet of Everything Era , 2017 .