Live video analytics as a service
- 5 April 2022
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM) in Proceedings of the 2nd European Workshop on Machine Learning and Systems
Abstract
Many private and public organizations deploy large numbers of cameras, which are used in application services for public safety, healthcare, and traffic control. Recent advances in deep learning have demonstrated remarkable accuracy on computer analytics tasks that are fundamental for these applications, such as object detection and action recognition. While deep learning opens the door for the automation of camera-based applications, deploying pipelines for live video analytics is still a complicated process that requires domain expertise in the fields of machine learning, computer vision, computer systems, and networks. The problem is further amplified when multiple pipelines need to be deployed on the same infrastructure to meet different users' diverse and yet dynamic needs. In this paper, we present a live-video-analytics-as-a-service vision, aiming to remove the complexity barrier and achieve flexibility, agility, and efficiency for applications based on live video analytics. We motivate our vision by identifying its requirements and the shortcomings of existing approaches. Based on our analysis, we present our envisioned system design and discuss the challenges that need to be addressed to make it a reality.Keywords
Funding Information
- Dutch Research Council (NWO) (18038)
This publication has 25 references indexed in Scilit:
- Edge Video Analytics for Public Safety: A ReviewProceedings of the IEEE, 2019
- Scaling Video Analytics Systems to Large Camera DeploymentsPublished by Association for Computing Machinery (ACM) ,2019
- VideoEdge: Processing Camera Streams using Hierarchical ClustersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- AWStreamPublished by Association for Computing Machinery (ACM) ,2018
- ChameleonPublished by Association for Computing Machinery (ACM) ,2018
- Real-Time Video Analytics: The Killer App for Edge ComputingComputer, 2017
- NoScopeProceedings of the VLDB Endowment, 2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics DatasetPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- MCDNNPublished by Association for Computing Machinery (ACM) ,2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016