DETECTING AND VALIDATING A USER ACTIVITY CAPTURED FROM MULTIPLE SENSORS
Conventionally, activity detection has been through one mode i.e., smart watch. Though it works in reasonable cases, there are chances of false positives considerably. Other approaches include surveillance which limits itself to object detection. Embodiments of present disclosure provide systems and...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | English French German |
Published |
27.10.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Conventionally, activity detection has been through one mode i.e., smart watch. Though it works in reasonable cases, there are chances of false positives considerably. Other approaches include surveillance which limits itself to object detection. Embodiments of present disclosure provide systems and methods for detecting activities performed by user from data captured from multiple sensors. A first input (FI) comprising accelerometer data, heart rate and gyroscope data and second input (SI) comprising video data are obtained. Features are extracted from FI and preprocessed for a first activity (FA) detection using activity prediction model. Frames from SI are processed for creating bounding box of user and resized thereof to extract pose coordinates vector. Distance between vector of pose coordinates and training vectors of pose coordinates stored in the system is computed and a second activity (SA) is detected accordingly. Both the FA and SA are validated for determining true and/or false positive. |
---|---|
AbstractList | Conventionally, activity detection has been through one mode i.e., smart watch. Though it works in reasonable cases, there are chances of false positives considerably. Other approaches include surveillance which limits itself to object detection. Embodiments of present disclosure provide systems and methods for detecting activities performed by user from data captured from multiple sensors. A first input (FI) comprising accelerometer data, heart rate and gyroscope data and second input (SI) comprising video data are obtained. Features are extracted from FI and preprocessed for a first activity (FA) detection using activity prediction model. Frames from SI are processed for creating bounding box of user and resized thereof to extract pose coordinates vector. Distance between vector of pose coordinates and training vectors of pose coordinates stored in the system is computed and a second activity (SA) is detected accordingly. Both the FA and SA are validated for determining true and/or false positive. |
Author | BALAJI, Ramesh DHANASEKARAN, Harish Kumar SRINIVASA RAGHAVAN, Venkatachari |
Author_xml | – fullname: BALAJI, Ramesh – fullname: SRINIVASA RAGHAVAN, Venkatachari – fullname: DHANASEKARAN, Harish Kumar |
BookMark | eNrjYmDJy89L5WRwd3ENcXUO8fRzV3D0c1EIc_TxdHGEcBVCg12DFByBkmGeIZEKzo4BIaFBri4KbkH-vgq-oT4hngE-rgrBrn7B_kHBPAysaYk5xam8UJqbQcHNNcTZQze1ID8-tbggMTk1L7Uk3jXA2NLA0MLQ0tHQmAglAKN1LhE |
ContentType | Patent |
DBID | EVB |
DatabaseName | esp@cenet |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: EVB name: esp@cenet url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Chemistry Sciences Physics |
DocumentTitleAlternate | ERKENNUNG UND VALIDIERUNG EINER VON MEHREREN SENSOREN ERFASSTEN BENUTZERAKTIVITÄT DÉTECTION ET VALIDATION D'UNE ACTIVITÉ D'UTILISATEUR SAISIE PAR PLUSIEURS CAPTEURS |
ExternalDocumentID | EP3901819A1 |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_EP3901819A13 |
IEDL.DBID | EVB |
IngestDate | Fri Jul 19 12:56:24 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English French German |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_EP3901819A13 |
Notes | Application Number: EP20210154381 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211027&DB=EPODOC&CC=EP&NR=3901819A1 |
ParticipantIDs | epo_espacenet_EP3901819A1 |
PublicationCentury | 2000 |
PublicationDate | 20211027 |
PublicationDateYYYYMMDD | 2021-10-27 |
PublicationDate_xml | – month: 10 year: 2021 text: 20211027 day: 27 |
PublicationDecade | 2020 |
PublicationYear | 2021 |
RelatedCompanies | Tata Consultancy Services Limited |
RelatedCompanies_xml | – name: Tata Consultancy Services Limited |
Score | 3.3686998 |
Snippet | Conventionally, activity detection has been through one mode i.e., smart watch. Though it works in reasonable cases, there are chances of false positives... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTING COUNTING PHYSICS |
Title | DETECTING AND VALIDATING A USER ACTIVITY CAPTURED FROM MULTIPLE SENSORS |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211027&DB=EPODOC&locale=&CC=EP&NR=3901819A1 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb8IwDLYQe942tgn2Ug5Tb9VKW4o4oKkkKXSiD7UFsRNq-pC4FDQ67e8vyYDtst2SWLESS7bzJbYD8JTmXY31ioGqc7LK8VeqsjIVuTJ8ArNSYyCz3j3fmszM10Vv0YDVPhdG1gn9lMURuUZlXN9raa83P5dYRMZWbp_Zig-tX5xkSJQdOhZoRu8rZDSkYUACrGDMW4ofDQW0587P5kDpSJyiRZl9Oh-JpJTNb4_iXMBxyJlV9SU0iqoFZ3j_8VoLTr3de3cLTmSAZrblgzsl3F7BmNCE4sT1x8j2CZrbU5fY3100i2mERGDI3E3eELZDEdVAkBMFHvJm08QNpxTF1I-DKL4G5NAET1S-tuVBDksaHnZh3ECzWldFG1CuMz01mWYxLTNz1mXMKA0jy8s0twyNlR3o_Mnm9h_aHZwLgQo7rffvoVm_fxQP3AHX7FGK7gtuhoVj |
link.rule.ids | 230,309,786,891,25594,76906 |
linkProvider | European Patent Office |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb8IwDLYQe7DbxjaNPXOYeqtW2lLEAU0lSaFbX2oLYifU9CFxKWh02t9f0gHbZbslsWIllmznS2wH4DHJugrr5QNZ5WSZ469EZkUicmX4BGYk2qDOenc9YzLVX-a9eQOWu1yYuk7oZ10ckWtUyvW9qu31-ucSi9SxlZsntuRDq2crHhJpi44FmlH7EhkNaeATH0sY85bkhUMB7bnzMzlQOuiL4rzi5DQbiaSU9W-PYp3CYcCZldUZNPKyDS28-3itDcfu9r27DUd1gGa64YNbJdycw5jQmOLY9sbI9AiamY5NzO8umkY0RCIwZGbHbwibgYhqIMgKfRe5Uye2A4eiiHqRH0YXgCwa44nM17bYy2FBg_0utEtolqsyvwKUqUxNdKYYTEn1jHUZ0wpNS7MiyQxNYUUHOn-yuf6H9gCtSew6C8f2Xm_gRAhX2Gy1fwvN6v0jv-POuGL3tRi_ANRWiFA |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=DETECTING+AND+VALIDATING+A+USER+ACTIVITY+CAPTURED+FROM+MULTIPLE+SENSORS&rft.inventor=BALAJI%2C+Ramesh&rft.inventor=SRINIVASA+RAGHAVAN%2C+Venkatachari&rft.inventor=DHANASEKARAN%2C+Harish+Kumar&rft.date=2021-10-27&rft.externalDBID=A1&rft.externalDocID=EP3901819A1 |