Smart City Gnosys

Smart city article details

Title	Iot Video Analytics For Surveillance-Based Systems In Smart Cities
ID_Doc	33935
Authors	Aminiyeganeh K.; Coutinho R.W.L.; Boukerche A.
Year	2024
Published	Computer Communications, 224
DOI	http://dx.doi.org/10.1016/j.comcom.2024.05.021
Abstract	Smart city applications are revolutionizing the way people interact with diverse systems in city-wide applications. Internet of Things (IoT) and machine learning are two enabling technologies for smart cities. IoT sensors are deployed for data collection from city environments and machine learning models are used for data processing, inference, and predictions aimed at controlling IoT actuators and providing information for users. Surveillance applications in smart cities often use cloud and edge servers for the data analytics of video streamed by IoT cameras. This approach might increase the system's latency due to the communication delay and networking congestion in the links connecting IoT cameras to distant cloud servers. A promising approach to mitigate the latency in video analytics applications is to perform the video analytics locally at the IoT devices and IoT gateways by using lightweight convolutional neural network (CNN) models. In this paper, we propose an architecture for implementing at IoT devices the data pipeline required for local video analytics in smart cities. Moreover, we instantiate the proposed framework to conduct an extensive performance evaluation of five CNN models on IoT devices, in a traffic surveillance smart city application. Obtained results show the feasibility of studied CNN models, in terms of frame processing rate and energy efficiency in the considered IoT devices.
Author Keywords	Deep learning; IoT video analytics; Smart cities

Similar Articles

Id	Similarity	Authors	Title	Published
17919	0.907	Dankan Gowda V.; Vishnu Tej Y.; Potharaju V.S.; Jakkidi P.R.; Sharma A.; Sudhakar Reddy N.	Deep Learning Techniques For Image Recognition In Iot-Enabled Surveillance Systems	2024 Asian Conference on Intelligent Technologies, ACOIT 2024 (2024)
47072	0.902	Wang F.; Hou S.; Gao J.; Wu D.	Rotating Kernel Cnn Optimization For Efficient Iot Surveillance On Low-Power Devices	Electronics (Switzerland), 13, 14 (2024)
17853	0.898	Dadheech A.; Bhavsar M.; Verma J.P.; Prasad V.K.	Deep Learning Based Smart Traffic Management Using Video Analytics And Iot Sensor Fusion	Soft Computing, 28, 23 (2024)
58351	0.894	Bellavista P.; Ota K.; Lv Z.; Mehmood I.; Rho S.	Towards Smarter Cities: Learning From Internet Of Multimedia Things-Generated Big Data	Future Generation Computer Systems, 108 (2020)
33720	0.888	Ebrahimy A.R.; Naghshnilchi A.R.; Monadjemi A.H.; Saeidehsani M.	Iot Based Smart Surveillance Monitoring By Using Model-Based Human Action Recognition Design	Proceedings of 2021 5th International Conference on Internet of Things and Applications, IoT 2021 (2021)
34074	0.887	Gorobetz M.; Timofejevs J.; Potapovs A.; Obusevs A.	Iot-Enabled Single-Camera Speed Sensor For Smart City Tasks	Electronics (Switzerland), 13, 12 (2024)
40272	0.885	Badidi E.; Moumane K.; Ghazi F.E.	Opportunities, Applications, And Challenges Of Edge-Ai Enabled Video Analytics In Smart Cities: A Systematic Review	IEEE Access, 11 (2023)
58214	0.88	Sabha A.; Selwal A.	Towards Machine Vision-Based Video Analysis In Smart Cities: A Survey, Framework, Applications And Open Issues	Multimedia Tools and Applications, 83, 22 (2024)
4385	0.876	Khochare A.; Simmhan Y.	A Scalable And Composable Analytics Platform For Distributed Wide-Area Tracking	ACM International Conference Proceeding Series (2019)
8761	0.876	Khalifa O.O.; Roubleh A.; Esgiar A.; Abdelhaq M.; Alsaqour R.; Abdalla A.; Ali E.S.; Saeed R.	An Iot-Platform-Based Deep Learning System For Human Behavior Recognition In Smart City Monitoring Using The Berkeley Mhad Datasets	Systems, 10, 5 (2022)