CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12707 > Article
Paper
8 June 2023 Research on model compression based model front end chip transplantation for power equipment defect detection
Yongbo Zhou, Jing Wang, Qiong Wang
Author Affiliations +
Proceedings Volume 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023); 127074V (2023) https://doi.org/10.1117/12.2681168
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 2023, Changsha, China
Abstract
As an important part of the power system, the safe and stable operation of power equipment is very important to ensure the reliability of power supply. Some defects of power equipment are difficult to detect manually, and hidden dangers caused by aging of equipment are also difficult to detect in time. In this paper, a target detection algorithm for power device defect detection based on improved RetinaNet is presented, and the defect detection model is transplanted to the front-end chip by model compression. First, select RetinaNet target detection algorithm by analyzing the requirements of power equipment defect recognition algorithm, then quantify and compress the target detection algorithm model. Finally, embed the algorithm into Rk3399 Pro front-end chip, and set up an intelligent identification system for power equipment defects, which can realize real-time intelligently identifying power equipment faults. It has a very high engineering application value.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Yongbo Zhou, Jing Wang, and Qiong Wang "Research on model compression based model front end chip transplantation for power equipment defect detection", Proc. SPIE 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 127074V (8 June 2023); https://doi.org/10.1117/12.2681168
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
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
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 7 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Detection and tracking algorithms
Instrument modeling
Data modeling
Performance modeling
Target detection
Intelligence systems
Neural networks
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top