Enabling Real-Time AI Edge Video Analytics
Tsakanikas, V. and Dagiuklas, A. (2021). Enabling Real-Time AI Edge Video Analytics. IEEE International Conference on Communications. Montreal 14 - 23 Jun 2021 Institute of Electrical and Electronics Engineers (IEEE).
|Authors||Tsakanikas, V. and Dagiuklas, A.|
This paper introduces a novel distributed AI model for managing in real-time, edge based intelligent analytics, such as the ones required for smart video surveillance. The novelty relies on distributing the applications in several decomposed functions which are linked together, creating virtual chain func- tions, where both computational and communication limitations are considered. Both theoretical analysis and simulation analysis in a real-case scenario have shown that the proposed model can enable real-time surveillance analytics on a low-cost edge network. Finally, a caching mechanism is proposed and evaluated, reducing further the operational costs of the edge network.
|Keywords||Edge Computing; AI applications; Virtual Function Chaining|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Accepted author manuscript|
File Access Level
|Publication process dates|
|Accepted||10 Feb 2021|
|Deposited||02 Mar 2021|
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Accepted author manuscript
2views this month
0downloads this month