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

Sajid Nazir; Yovin Poorun; Mohammad Kaleem

doi:10.1109/ICECCME52200.2021.9591027

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

Sajid Nazir, Yovin Poorun, Mohammad Kaleem

Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Citations (Scopus)

298 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 language	English
Title of host publication	2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	9781665412629
ISBN (Print)	9781665429436
DOIs	https://doi.org/10.1109/ICECCME52200.2021.9591027
Publication status	Published - 15 Nov 2021
Event	The International Conference on Electrical, Computer, Communications and Mechatronics Engineering 2021 - , Mauritius Duration: 7 Oct 2021 → 8 Oct 2021 http://ww.iceccme.com/home

Publication series

Name	Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)
ISSN (Electronic)	2994-2454

Conference

Conference	The International Conference on Electrical, Computer, Communications and Mechatronics Engineering 2021
Abbreviated title	ICECCME 2021
Country/Territory	Mauritius
Period	7/10/21 → 8/10/21
Internet address	http://ww.iceccme.com/home

Keywords

deep learning
cloud computing
web services
image edge detection
smart homes
infrared sensors
security
embedded programming
remote monitoring
edge computing
motion detection
communications protocol
artificial intelligence
false positive

ASJC Scopus subject areas

Information Systems and Management
Artificial Intelligence
Mechanical Engineering
Safety, Risk, Reliability and Quality
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Hardware and Architecture
Computer Networks and Communications

Documents and Links

10.1109/ICECCME52200.2021.9591027

Nazir, S. et al (2021) Person detection with deep learning and IoT for smart home security on Amazon Cloud
Copyright © 2021 IEEE. This is a post-peer review, pre-copy edited version of the article and may differ slightly from the final published version of the work. This work is made available in line with the publisher policy. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Author accepted manuscript, 314 KB

Cite this

Nazir, S., Poorun, Y., & Kaleem, M. (2021). Person detection with deep learning and IoT for smart home security on Amazon Cloud. In 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) (Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)). IEEE. https://doi.org/10.1109/ICECCME52200.2021.9591027

@inproceedings{1ac021c62aa44665ada910746d2e3212,

title = "Person detection with deep learning and IoT for smart home security on Amazon Cloud",

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.",

keywords = "deep learning, cloud computing, web services, image edge detection, smart homes, infrared sensors, security, embedded programming, remote monitoring, edge computing, motion detection, communications protocol, artificial intelligence, false positive",

author = "Sajid Nazir and Yovin Poorun and Mohammad Kaleem",

note = "Acceptance in SharePoint. ST 01/09/21 AAM: no embargo; The International Conference on Electrical, Computer, Communications and Mechatronics Engineering 2021, ICECCME 2021 ; Conference date: 07-10-2021 Through 08-10-2021",

year = "2021",

month = nov,

day = "15",

doi = "10.1109/ICECCME52200.2021.9591027",

language = "English",

isbn = "9781665429436",

series = "Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)",

publisher = "IEEE",

booktitle = "2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)",

address = "United States",

url = "http://ww.iceccme.com/home",

}

Nazir, S, Poorun, Y & Kaleem, M 2021, Person detection with deep learning and IoT for smart home security on Amazon Cloud. in 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME). Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), IEEE, The International Conference on Electrical, Computer, Communications and Mechatronics Engineering 2021, Mauritius, 7/10/21. https://doi.org/10.1109/ICECCME52200.2021.9591027

Person detection with deep learning and IoT for smart home security on Amazon Cloud. / Nazir, Sajid; Poorun, Yovin; Kaleem, Mohammad.
2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME). IEEE, 2021. (Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Person detection with deep learning and IoT for smart home security on Amazon Cloud

AU - Nazir, Sajid

AU - Poorun, Yovin

AU - Kaleem, Mohammad

N1 - Acceptance in SharePoint. ST 01/09/21 AAM: no embargo

PY - 2021/11/15

Y1 - 2021/11/15

N2 - 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.

AB - 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.

KW - deep learning

KW - cloud computing

KW - web services

KW - image edge detection

KW - smart homes

KW - infrared sensors

KW - security

KW - embedded programming

KW - remote monitoring

KW - edge computing

KW - motion detection

KW - communications protocol

KW - artificial intelligence

KW - false positive

U2 - 10.1109/ICECCME52200.2021.9591027

DO - 10.1109/ICECCME52200.2021.9591027

M3 - Conference contribution

SN - 9781665429436

T3 - Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)

BT - 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)

PB - IEEE

T2 - The International Conference on Electrical, Computer, Communications and Mechatronics Engineering 2021

Y2 - 7 October 2021 through 8 October 2021

ER -

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

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Documents and Links

Fingerprint

Cite this