B4W: A Smart Wireless Intruder Detection System

Conference Paper (2023)
Author(s)

Suryansh Sharma (TU Delft - Networked Systems)

Prabhakar V (Indian Institute of Science)

Shalakha Singhal (Indian Institute of Science)

Gogineni Gopi Sunanth Kuma (Indian Institute of Science)

Rangarao Venkatesha Prasad (TU Delft - Networked Systems)

Research Group
Networked Systems
Copyright
© 2023 Suryansh Sharma, Prabhakar Venkata T., Shalakha Singhal, Gogineni Gopi Sunanth Kuma, Ranga Rao Venkatesha Prasad
DOI related publication
https://doi.org/10.1109/ICC45041.2023.10279723
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Suryansh Sharma, Prabhakar Venkata T., Shalakha Singhal, Gogineni Gopi Sunanth Kuma, Ranga Rao Venkatesha Prasad
Research Group
Networked Systems
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.@en
Pages (from-to)
191-197
ISBN (print)
978-1-5386-7463-5
ISBN (electronic)
978-1-5386-7462-8
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Surveillance and monitoring are highly critical in many application scenarios like wildlife conservation, restricted areas such as nuclear spillover, and border security. Moreover, in these scenarios, intrusions do not happen frequently thus, conventional surveillance is overkill and expensive that also requires extensive human involvement which can be arduous, expensive, and inefficient. To address these issues we propose an end-to-end smart acoustic surveillance solution for intrusion detection using a simple low-cost system called Balls for Walls (B4 W). The objective is to create a network of sensors that could also be remotely launched. The nodes responsible for surveillance employ audio sensors which are packaged within hard balls thus allowing the launch of these sensors from a distance of over 500 m. We use microphones for detecting human activity inferred through sensing the sound of footsteps against background noise. We evaluate the systems across five different terrain types. We propose a novel, low complexity detection algorithm called SEED which leverages signal energy and shape to distinguish humans from ambient noise. B4 W offers a maximum detection rate of 98.3% on dry leaves and a low false alarm rate of 0.9%. The system is energy efficient to last a maximum of 170 days and it is orientation agnostic. The proposed system has been extensively tested across varying terrains and ambient signal scenarios to demonstrate its efficacy.

Files

B4W_A_Smart_Wireless_Intruder_... (pdf)
(pdf | 6.7 Mb)
- Embargo expired in 23-04-2024
License info not available