Privacy-Preserved Behavior Analysis and Fall Detection by an Infrared Ceiling Sensor Network 英文参考文献.docVIP

下载本文档

2
0
约3.34万字
约 17页
2017-05-12 发布于上海
举报
版权申诉

Privacy-Preserved Behavior Analysis and Fall Detection by an Infrared Ceiling Sensor Network 英文参考文献.doc

1、本文档共17页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Privacy-Preserved Behavior Analysis and Fall Detection by an Infrared Ceiling Sensor Network 英文参考文献

Sensors2012,12,16920-16936;doi:10.3390/s121216920 OPENACCESS sensors ISSN1424-8220 /journal/sensors Article Privacy-PreservedBehaviorAnalysisandFallDetectionbyan InfraredCeilingSensorNetwork ShuaiTao ,MineichiKudoandHidetoshiNonaka ? DivisionofComputerScience,HokkaidoUniversity,Kita8Nishi5,Kita-ku,Sapporo060-0808,Japan; E-Mails:mine@main.ist.hokudai.ac.jp(M.K.);nonaka@main.ist.hokudai.ac.jp(H.N.) *Authortowhomcorrespondenceshouldbeaddressed;E-Mail:taoshuai@main.ist.hokudai.ac.jp; Tel.:+81-011-706-6854. Received:30September2012;inrevisedform:19November2012/Accepted:3December2012/ Published:7December2012 Abstract: An infrared ceiling sensor network system is reported in this study to realize behavior analysis and fall detection of a single person in the home environment. The sensorsoutputmultiplebinarysequencesfromwhichweknowtheexistence/non-existence ofpersonsunderthesensors.Theshortdurationaveragesofthebinaryresponsesareshown tobeabletoberegardedaspixelvaluesofatop-viewcamera,butmoreadvantageousinthe senseofpreservingprivacy. Usingthe“pixelvalues”asfeatures,supportvectormachine classi?erssucceededinrecognizingeightactivities(walking,reading,etc.) performedby ?vesubjectsatanaveragerecognitionrateof80.65%.Inaddition,weproposedamartingale framework for detecting falls in this system. The experimental results showed that we attained the best performance of 95.14% (F1 value), the FAR of 7.5% and the FRR of 2.0%. Thisaccuracyisnotsuf?cientingeneralbutsurprisinglyhighwithsuchlow-level information. Insummary, itisshownthatthissystemhasthepotentialtobeusedinthe home environment to provide personalized services and to detect abnormalities of elders wholivealone. Keywords: behavior analysis; fall detection; privacy-preserved; ceiling sensor network; infraredsensors Sensors2012,12 16921 1.Introduction In recent years, human behavior analysis such as person tracking and activity/action recognition has progressed signi?cantly [1–7]. They are becoming indispensable for