Hardware and Software Integration of Machine Learning Vision System based on NVIDIA Jetson Nano

Manolescu, Vasile Denis and Reid, David and Secco, Emanuele Lindo (2023) Hardware and Software Integration of Machine Learning Vision System based on NVIDIA Jetson Nano. In: Future of Information and Communication Conference (FICC) 2024. (Accepted for Publication)

Text SAIConference_Jetson_SEL.pdf - Accepted Version Restricted to Repository staff only Download (596kB)

Abstract

This study investigates the capabilities and flexibility of edge devices for real-time data processing near the source. A configurable Nvidia Jetson Nano system is used to deploy nine pre-trained computer vision models, demonstrating proficiency in local data processing, analysis and providing real-time feedback. Additionally, the system offers deployment control via a customized Graphical User Interface (GUI) and proves very low-latency inference re-stream to other local devices using the G-Streamer framework.
The Machine Learning models, covering a wide range of applications, including image classification, object recognition or detection, depth estimation and semantic segmentation, show potential for IoT and industrial applications. Further, the fusion of these capabilities with AI and machine learning algorithms unveils a promising perspective for substantial industrial redevelopment. This research underscores the strategic significance of edge devices in modern computational frameworks and their potential role in future technological advancements.

Item Type:	Conference or Workshop Item (Paper)
Faculty / Department:	Faculty of Human and Digital Sciences > Mathematics and Computer Science
Depositing User:	Emanuele Secco
Date Deposited:	20 Sep 2023 08:20
Last Modified:	20 Sep 2023 08:20
URI:	https://hira.hope.ac.uk/id/eprint/4021

Actions (login required)

View Item