Power vision edge computer device design based on AI chip atlas 200

Song Deng; Changbao Xu; Mingyong Xin

doi:10.1117/12.3010648

2 November 2023 Power vision edge computer device design based on AI chip atlas 200

Song Deng, Changbao Xu, Mingyong Xin

Proceedings Volume 12919, International Conference on Electronic Materials and Information Engineering (EMIE 2023); 129191L (2023) https://doi.org/10.1117/12.3010648
Event: 3rd International Conference on Electronic Materials and Information Engineering (EMIE 2023), 2023, Guangzhou,, China

Abstract

Power vision is a technology that utilizes image processing and analysis techniques for intelligent recognition and monitoring of devices and environments in the power system. The application of power vision faces challenges such as insufficient data transmission bandwidth, poor real-time data processing, and inadequate data security and privacy protection, which limit the efficiency and quality of power vision applications. In order to address these challenges, this paper presents a design of a power vision edge computing device based on the AI chip Atlas 200, enabling real-time processing and analysis of power vision images at the edge, closer to the data source. This paper introduces the overall design of the device, software deployment, and the migration of deep learning algorithms. Furthermore, it showcases the effectiveness and advantages of the device in the specific application scenario of transmission line icing detection.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Song Deng, Changbao Xu, and Mingyong Xin "Power vision edge computer device design based on AI chip atlas 200", Proc. SPIE 12919, International Conference on Electronic Materials and Information Engineering (EMIE 2023), 129191L (2 November 2023); https://doi.org/10.1117/12.3010648

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available