• 首页
  • 期刊简介
  • 编委会
  • 投稿指南
  • 收录情况
  • 杂志订阅
  • 联系我们
引用本文:董伟鑫.基于人物识别的智慧视频监控在机房中的应用[J].软件工程,2023,26(8):44-47.【点击复制】
【打印本页】   【下载PDF全文】   【查看/发表评论】  【下载PDF阅读器】  
←前一篇|后一篇→ 过刊浏览
分享到: 微信 更多
基于人物识别的智慧视频监控在机房中的应用
董伟鑫
(中南空中交通管理局, 广东 广州 510000)
843291850@qq.com
摘 要: 传统机房采用人工巡视和视频监控结合的管理模式,耗费人力、物力,并且机房的安全性容易受到管理人员主观因素的影响。将基于人物识别的智慧视频技术应用到机房监控中,可以对监控视频进行实时处理分析,提取视频中的人物并自动识别人脸信息,将之与数据库中的信息进行对比。此外,该系统可以对机房内人员的行为进行识别并监测,自动识别异常行为并发出告警。经实验证明,该系统对机房内人员识别的准确率约为87.86%,对人员昏迷倒地行为识别的准确率约为92.61%,可以较好地识别机房内人员信息及其行为,有效地辅助使用单位对机房进行管理。
关键词: 智慧视频;机房监控;人物识别;人脸识别
中图分类号: TP391.7    文献标识码: A
Application of Intelligent Video Monitoring Based on Human Recognition in Computer Rooms
DONG Weixin
(Central South Air Traffic Management Bureau, Guangzhou 510000, China)
843291850@qq.com
Abstract: The management mode in traditional computer rooms that combines manual inspection and video monitoring consumes manpower and material resources. Moreover, computer room safety is easily affected by subjective factors of management personnel. This paper proposes to apply intelligent video technology based on human recognition to computer room monitoring. It can perform real-time processing and analysis of monitoring videos, extract characters from the videos, and automatically recognize facial information which is then compared with information in the database. In addition, the system can identify and monitor the behavior of personnel in the computer room, automatically identifying abnormal behaviors and issuing warnings. Experimental results show that the accuracy of the system in identifying personnel in the computer room is about 87.86% , and the accuracy of identifying coma and falling behaviors of personnel is about 92.61% . It can effectively identify information and behaviors of personnel in the computer room and assist users in managing the computer room.
Keywords: intelligent video; computer room monitoring; human recognition; face recognition


版权所有:软件工程杂志社
地址:辽宁省沈阳市浑南区新秀街2号 邮政编码:110179
电话:0411-84767887 传真:0411-84835089 Email:semagazine@neusoft.edu.cn
备案号:辽ICP备17007376号-1
技术支持:北京勤云科技发展有限公司

用微信扫一扫

用微信扫一扫