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.
|Title of host publication
|Subtitle of host publication
|Proceedings of the 2nd European Workshop on Machine Learning and Systems
|Association for Computing Machinery, Inc
|Number of pages
|Published - Apr 2022
|2nd European Workshop on Machine Learning and Systems, EuroMLSys 2022, in conjunction with ACM EuroSys 2022 - Virtual, Online, France
Duration: 5 Apr 2022 → 8 Apr 2022
|2nd European Workshop on Machine Learning and Systems, EuroMLSys 2022, in conjunction with ACM EuroSys 2022
|5/04/22 → 8/04/22
Bibliographical noteFunding Information:
This work is part of the Real-Time Video Surveillance Search project (grant number 18038), financed by the Dutch Research Council (NWO).
© 2022 Owner/Author.
- live video analytics
- machine learning
- privacy preservation
- service systems