[1]伍静,刘德丰,张松,等.智能摔倒检测监控系统设计[J].计算机技术与发展,2018,28(04):6-10.[doi:10.3969/ j. issn.1673-629X.2018.04.002]
　WU Jing,LIU De-feng,ZHANG Song,et al.Design of an Intelligent Monitoring System for Tumble Detection[J].,2018,28(04):6-10.[doi:10.3969/ j. issn.1673-629X.2018.04.002]
点击复制

智能摔倒检测监控系统设计()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年04期
页码:
6-10
栏目:
智能、算法、系统工程
出版日期:
2018-04-10

文章信息/Info

Title:
Design of an Intelligent Monitoring System for Tumble Detection
文章编号:
1673-629X(2018)04-0006-05
作者:
伍静; 刘德丰; 张松; 余旭伟; 钟天扬; 陈飞
江南大学 数字媒体学院,江苏 无锡 214122
Author(s):
WU Jing; LIU De-feng; ZHANG Song; YU Xu-wei; ZHONG Tian-yang; CHEN Fei
School of Digital Media,Jiangnan University,Wuxi 214122,China
关键词:
智能视频监控; EasyDarwin; 行为检测; 语音识别
Keywords:
intelligent video monitor; EasyDarwin; behavior detection; speech recognition
分类号:
TP302
DOI:
10.3969/ j. issn.1673-629X.2018.04.002
文献标志码:
A
摘要:
现代社会人口老龄化加剧,空巢老人现象日益普遍,室内老人摔倒成为广泛关注的社会问题。 并且,传统以安防为目的的监控系统侧重于人流检测以及人脸识别等方面,而缺乏对室内人员行为尤其是摔倒事件的检测。 对此,设计了一种居家环境中用于检测老人摔倒的智能监控系统。 该系统选用 EasyDarwin 作为服务器,实现视频推流、在客户端拉取视频流播放等工作,利用帧间差分法、背景减除法等算法对监控场景进行目标行为的分析,使用科大讯飞 SDK 实现语音识别的功能,最终通过 Zabbix 实现系统的告警。 在摄像头拍摄到老人摔倒行为后,视音频检测代码分析视频片段得到告警信息,通过邮件形式发送给用户。 该系统融合了网络视频传输和视频内容分析技术,为现代社会中普遍存在的空巢老人生活安全问题提供了一种可靠的解决方案。
Abstract:
The aging of the modern society and the prevalence of empty nesters are aggravated,which make the tumble of solitary people a widely concerned social problem. The traditional security monitoring systems are commonly utilized in the public or private residence for human flow monitoring or face detection,but without consideration of behavior detection,especially tumble detection. In this regard,we design an intelligent monitoring system of home environment for the detection of old people fall. In this system,EasyDarwin is utilized as a streaming server for video content delivery and storage. Specifically,the behavior recognition is implemented with the algorithms,such as the inner-frame difference and the background subtraction. The speech recognition is realized with iFLYTEK SDK. The alarm module design is based on Zabbix. After the camera shoots the old man，s fall behavior,the video and audio detection code analyzes video clip to get the warning message and sends it to the user by email. Combining the network video transmission and video content analysis technology,the whole system can provide a practical solution for the life security problem of empty nesters in modern society.

相似文献/References:

[1]侯宏录 李宁鸟 刘迪迪 陈杰.智能视频监控中运动目标检测的研究[J].计算机技术与发展,2012,(02):49.
　HOU Hong-lu,LI Ning-niao,LIU Di-di,et al.Research on Moving Target Detection of Intelligent Video Surveillance[J].,2012,(04):49.
[2]武琦,王夏黎,王博学,等.一种基于监控视频的有效的人脸识别方法[J].计算机技术与发展,2018,28(12):59.[doi:10．3969/j． issn．1673－629X．2018．12．012]
　WU Qi,WANG Xiali,WANG Boxue,et al.An Effective Face Recognition Method Based on Surveillance Video[J].,2018,28(04):59.[doi:10．3969/j． issn．1673－629X．2018．12．012]

更新日期/Last Update: 2018-05-29