###

计算机系统应用英文版:2022,31(1):65-72

View/Add Comment 过刊浏览高级检索 HTML

←前一篇 | 后一篇→

码上扫一扫！

下载全文

基于语义分割的防侵入系统

罗耀俊^1,2, 向海^1,2, 胡晓兵^1,2, 牛洪超^1,2, 魏上云^1,2

(1.四川大学机械工程学院, 成都 610065;2.四川大学宜宾园区, 宜宾 644000)

Anti-intrusion System Based on Semantic Segmentation

LUO Yao-Jun^1,2, XIANG Hai^1,2, HU Xiao-Bing^1,2, NIU Hong-Chao^1,2, WEI Shang-Yun^1,2

(1.School of Mechanical Engineering, Sichuan University, Chengdu 610065, China;2.Yibin R&D Park of Sichuan University, Yibin 644000, China)

摘要

图/表

参考文献

相似文献

本文已被：浏览 914次下载 1455次
Received:April 03, 2021 Revised:April 30, 2021

中文摘要: 对现有门式起重机的防侵入系统进行了详细分析后，针对其工作环境复杂、智能化水平较低的特点，建立了基于机器视觉和深度学习技术的防侵入监测模型.针对各目标检测算法和语义分割算法的优缺点，采用了语义分割算法作为防侵入模型，ICNet作为主要的语义分割网络.对比其他网络，ICNet网络具有99.37%的训练精度和1.81%的训练损失，都展现出了最优的精度.整体证明了基于语义分割的防侵入系统的智能性、可行性.

中文关键词: 语义分割防侵入门式起重机 ICNet

Abstract:After a detailed analysis of the existing anti-intrusion system of gantry cranes, an anti-intrusion monitoring model based on machine vision and deep learning is built in view of the complex working environments and low intelligence levels of the system. In consideration of the advantages and disadvantages of each target detection algorithm and semantic segmentation algorithm, the semantic segmentation algorithm is adopted as the anti-intrusion model, and the ICNet is used as the main semantic segmentation network. Compared with other networks, ICNet displays the best accuracy, with a training accuracy of 99.37% and a training loss of 1.81%. The results prove the intelligence and feasibility of the anti-intrusion system based on semantic segmentation.

keywords: semantic segmentation anti-intrusion system gantry crane ICNet

文章编号： 中图分类号： 文献标志码：

基金项目:中国制造2025四川行动计划（2018ZZ011）；川大-宜宾校地合作项目（2019CDYB-13）

引用文本：
罗耀俊,向海,胡晓兵,牛洪超,魏上云.基于语义分割的防侵入系统.计算机系统应用,2022,31(1):65-72
LUO Yao-Jun,XIANG Hai,HU Xiao-Bing,NIU Hong-Chao,WEI Shang-Yun.Anti-intrusion System Based on Semantic Segmentation.COMPUTER SYSTEMS APPLICATIONS,2022,31(1):65-72

Author Name	Affiliation	E-mail
LUO Yao-Jun	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China
XIANG Hai	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China
HU Xiao-Bing	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China	huxb@scu.edu.cn
NIU Hong-Chao	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China
WEI Shang-Yun	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China

Author Name	Affiliation	E-mail
LUO Yao-Jun	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China
XIANG Hai	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China
HU Xiao-Bing	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China	huxb@scu.edu.cn
NIU Hong-Chao	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China
WEI Shang-Yun	School of Mechanical Engineering, Sichuan University, Chengdu 610065, China Yibin R&D Park of Sichuan University, Yibin 644000, China