Design and Implementation of frost and snow recognition system for edge AI

Home > Archive>Volume 44, Issue 1, 2021 >142-149

Design and Implementation of frost and snow recognition system for edge AI
DOI:
                        
                    
CSTR:
                        
                    
Author:
                        Hu Min1Hu Min
College of Electronic and Information Engineering, Nanjing University of Information Science & Technology, Nanjing, Jiangsu 210044,China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
Pei XiaofangPei Xiaofang
1.College of Electronic and Information Engineering, Nanjing University of Information Science & Technology, Nanjing, Jiangsu 210044,China; 2.Binjiang College, Nanjing University of Information Science & Technology, Nanjing, Jiangsu 210044, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
Gu Pingyue4Gu Pingyue
Jiangsu Radio Research Institute Co. LTD，Wuxi, Jiangsu 214073, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
Hua Weidong4Hua Weidong
Jiangsu Radio Research Institute Co. LTD，Wuxi, Jiangsu 214073, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:1.College of Electronic and Information Engineering, Nanjing University of Information Science & Technology, Nanjing, Jiangsu 210044,China; 2.Binjiang College, Nanjing University of Information Science & Technology, Nanjing, Jiangsu 210044, China;3.Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing, Jiangsu 210044, China;4.Jiangsu Radio Research Institute Co. LTD，Wuxi, Jiangsu 214073, China
Clc Number:TP2
Fund Project:

Article

Figures

Metrics

Reference

Cited by

Materials

Comments

Abstract:

In order to improve the recognition rate of the frost and snow recognition system, a frost and snow recognition system powered by edge AI was designed. The design comprised the character of Hi3559A both excellent computation and low power consumption. The hardware used reduce power and resource consumption by Module reuse. For the software, by integrating the characteristics of the high computing power of Hisi, embedded processors Hi3559A and IMX334, and starting from model training, model quantization and model deployment, the author improved the MobileNetV2 image classification network and ISP adaptive processing algorithm. The final recognition rate reached 99.7%, pre-processing time reached 0.3s, image classification time reached 0.8s, module average power was 2W, and has its properties being robustness and stable. Hence，the Hi3559A intelligent phase machine module can effectively correct the inaccuracy of the data from the snow depth detector.

Key words:edged AI; Hi3559A; low power consumption; MobileNetV2; ISP adaptive processing; Module

Get Citation

Copy

Article Metrics

Abstract:
PDF:
HTML:
Cited by:

History

Received:
Revised:
Adopted:
Online: December 31,2024
Published:

Home

Introduction

Editorial Committee

Policy

Contact Us

中文版

Get Citation

Share

Article Metrics

History

Article QR Code