Person detection with deep learning and IoT for smart home security on Amazon Cloud

Sajid Nazir, Yovin Poorun, Mohammad Kaleem

Research output: Chapter in Book/Report/Conference proceedingConference contribution

25 Downloads (Pure)

Abstract

A smart home provides better living environment by allowing remote Internet access for controlling the home appliances and devices. Security of smart homes is an important application area commonly using Passive Infrared Sensors (PIRs), image capture and analysis but such solutions sometimes fail to detect an event. An unambiguous person detection is important for security applications so that no event is missed and also that there are no false alarms which result in waste of resources. Cloud platforms provide deep learning and IoT services which can be used to implement an automated and failsafe security application. In this paper, we demonstrate reliable person detection for indoor and outdoor scenarios by integrating an application running on an edge device with AWS cloud services. We provide results for identifying a person before authorizing entry, detecting any trespassing within the boundaries, and monitoring movements within the home.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Electrical, Computer, Communications and Mechatronics Engineering 2021 (ICECCME 2021)
PublisherIEEE
Publication statusAccepted/In press - 17 Jul 2021
EventThe International Conference on Electrical, Computer, Communications and Mechatronics Engineering 2021 - , Mauritius
Duration: 7 Oct 20218 Oct 2021
http://ww.iceccme.com/home

Conference

ConferenceThe International Conference on Electrical, Computer, Communications and Mechatronics Engineering 2021
Abbreviated titleICECCME 2021
Country/TerritoryMauritius
Period7/10/218/10/21
Internet address

Keywords

  • embedded programming, remote monitoring, edge computing, motion detection, communications protocol, artificial intelligence, false positive

Fingerprint

Dive into the research topics of 'Person detection with deep learning and IoT for smart home security on Amazon Cloud'. Together they form a unique fingerprint.

Cite this