On-demand Serverless Video Surveillance with Optimal Deployment of Deep Neural Networks

Unai Elordi, Unai Elordi, Luis Unzueta, Jon Goenetxea, Estíbaliz Loyo, Ignacio Arganda-Carreras, Ignacio Arganda-Carreras, Ignacio Arganda-Carreras, Oihana Otaegui

Abstract

We present an approach to optimally deploy Deep Neural Networks (DNNs) in serverless cloud architectures. A serverless architecture allows running code in response to events, automatically managing the required computing resources. However, these resources have limitations in terms of execution environment (CPU only), cold starts, space, scalability, etc. These limitations hinder the deployment of DNNs, especially considering that fees are charged according to the employed resources and the computation time. Our deployment approach is comprised of multiple decoupled software layers that allow effectively managing multiple processes, such as business logic, data access, and computer vision algorithms that leverage DNN optimization techniques. Experimental results in AWS Lambda reveal its potential to build cost-effective on-demand serverless video surveillance systems.

Download


Paper Citation


in Harvard Style

Elordi U., Unzueta L., Goenetxea J., Loyo E., Arganda-Carreras I. and Otaegui O. (2021). On-demand Serverless Video Surveillance with Optimal Deployment of Deep Neural Networks.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 717-723. DOI: 10.5220/0010344807170723


in Bibtex Style

@conference{visapp21,
author={Unai Elordi and Luis Unzueta and Jon Goenetxea and Estíbaliz Loyo and Ignacio Arganda-Carreras and Oihana Otaegui},
title={On-demand Serverless Video Surveillance with Optimal Deployment of Deep Neural Networks},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={717-723},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010344807170723},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - On-demand Serverless Video Surveillance with Optimal Deployment of Deep Neural Networks
SN - 978-989-758-488-6
AU - Elordi U.
AU - Unzueta L.
AU - Goenetxea J.
AU - Loyo E.
AU - Arganda-Carreras I.
AU - Otaegui O.
PY - 2021
SP - 717
EP - 723
DO - 10.5220/0010344807170723