Embedded human detection system for home security

Oscar Arturo González González, Alina Mariana Pérez Soberanes, Víctor Hugo García Ortega, Julio César Sosa Savedra

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents the development of an embedded system prototype that performs the home security monitoring, through image processing and classification algorithms to detect human form. If human presence is detected, the system will send an alert message to the user. The embedded system is implemented on a Raspberry Pi 3 B, supported by a Pyroelectric Infrared Radial (PIR) motion sensor and a Raspberry Pi Camera V2. The algorithms are implemented in C language and were designed to take advantage of the hardware resources of the platform, through High Performance Computing (HPC) techniques. The selected classifier is a multilayer perceptron. This classifier obtained an accuracy of 96%, approximately.

Original languageEnglish
Title of host publicationTelematics and Computing - 9th International Congress, WITCOM 2020, Proceedings
EditorsMiguel Félix Mata-Rivera, Roberto Zagal-Flores, Cristian Barria-Huidobro
PublisherSpringer Science and Business Media Deutschland GmbH
Pages48-60
Number of pages13
ISBN (Print)9783030625535
DOIs
StatePublished - 2020
Event9th International Congress on Telematics and Computing, WITCOM 2020 - Puerto Vallarta, Mexico
Duration: 2 Nov 20206 Nov 2020

Publication series

NameCommunications in Computer and Information Science
Volume1280
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference9th International Congress on Telematics and Computing, WITCOM 2020
Country/TerritoryMexico
CityPuerto Vallarta
Period2/11/206/11/20

Keywords

  • Embedded system
  • HPC
  • Image processing
  • Multilayer perceptron
  • Raspberry Pi

Fingerprint

Dive into the research topics of 'Embedded human detection system for home security'. Together they form a unique fingerprint.

Cite this