Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers

Bisma Amjad; Qasim Z. Ahmed; Faheem A. Khan; Zaharias D. Zaharis; Pavlos Lazaridis

doi:10.1109/WINCOM62286.2024.10655945

Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers

Bisma Amjad, Qasim Z. Ahmed, Faheem A. Khan, Zaharias D. Zaharis, Pavlos Lazaridis

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

Abstract

The implementation of indoor localization is being facilitated through commercially available low-cost mm-wave sensors. These sensors generate point cloud outputs containing noisy estimates of detected targets due to hardware noise and multipath reflections. In contrast to previously studied regression approaches, this study introduces a classification-based approach to predict the angle-of-arrival (AoA) and range of a human target from point clouds obtained from an mm-wave sensor. Our proposed methodology achieves a 7% and 26% improvement in AoA and range prediction, respectively, compared to the baseline models. All experiments have been conducted and validated using real data recorded by the mm-wave sensor.

Original language	English
Title of host publication	Proceedings - 11th International Conference on Wireless Networks and Mobile Communications, WINCOM 2024
Editors	Syed Ali Raza Zaidi, Khalil Ibrahimi, Mohamed El Kamili, Abdellatif Kobbane, Nauman Aslam
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	5
ISBN (Electronic)	9798350377866
ISBN (Print)	9798350377873
DOIs	https://doi.org/10.1109/WINCOM62286.2024.10655945
Publication status	Published - 5 Sep 2024
Event	11th International Conference on Wireless Networks and Mobile Communications - Leeds, United Kingdom Duration: 23 Jul 2024 → 25 Jul 2024 Conference number: 11

Publication series

Name	International Conference on Wireless Networks and Mobile Communications (WINCOM)
Publisher	IEEE
Volume	2024
ISSN (Print)	2769-9986
ISSN (Electronic)	2769-9994

Conference

Conference	11th International Conference on Wireless Networks and Mobile Communications
Abbreviated title	WINCOM 2024
Country/Territory	United Kingdom
City	Leeds
Period	23/07/24 → 25/07/24

Access to Document

10.1109/WINCOM62286.2024.10655945Licence: Unspecified

Cite this

Amjad, B., Ahmed, Q. Z., Khan, F. A., Zaharis, Z. D., & Lazaridis, P. (2024). Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers. In S. A. R. Zaidi, K. Ibrahimi, M. El Kamili, A. Kobbane, & N. Aslam (Eds.), Proceedings - 11th International Conference on Wireless Networks and Mobile Communications, WINCOM 2024 [10655945] (International Conference on Wireless Networks and Mobile Communications (WINCOM); Vol. 2024). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WINCOM62286.2024.10655945

Amjad, Bisma ; Ahmed, Qasim Z. ; Khan, Faheem A. et al. / Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers. Proceedings - 11th International Conference on Wireless Networks and Mobile Communications, WINCOM 2024. editor / Syed Ali Raza Zaidi ; Khalil Ibrahimi ; Mohamed El Kamili ; Abdellatif Kobbane ; Nauman Aslam. Institute of Electrical and Electronics Engineers Inc., 2024. (International Conference on Wireless Networks and Mobile Communications (WINCOM)).

@inproceedings{c4fe9fbb690841b4ac1bf25209848703,

title = "Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers",

abstract = "The implementation of indoor localization is being facilitated through commercially available low-cost mm-wave sensors. These sensors generate point cloud outputs containing noisy estimates of detected targets due to hardware noise and multipath reflections. In contrast to previously studied regression approaches, this study introduces a classification-based approach to predict the angle-of-arrival (AoA) and range of a human target from point clouds obtained from an mm-wave sensor. Our proposed methodology achieves a 7% and 26% improvement in AoA and range prediction, respectively, compared to the baseline models. All experiments have been conducted and validated using real data recorded by the mm-wave sensor.",

keywords = "angle of arrival, deep learning, indoor positioning system, localization, mm-Wave",

author = "Bisma Amjad and Ahmed, {Qasim Z.} and Khan, {Faheem A.} and Zaharis, {Zaharias D.} and Pavlos Lazaridis",

note = "Funding Information: This research work is supported by the Horizon 2020 Marie Sklodowska- Curie Innovative Training Networks Programme \{"}Mobility and Training for beyond 5G Ecosystems (MOTOR5G)\{"} under grant agreement no. 861219. Publisher Copyright: {\textcopyright} 2024 IEEE.; 11th International Conference on Wireless Networks and Mobile Communications , WINCOM 2024 ; Conference date: 23-07-2024 Through 25-07-2024",

year = "2024",

month = sep,

day = "5",

doi = "10.1109/WINCOM62286.2024.10655945",

language = "English",

isbn = "9798350377873",

series = "International Conference on Wireless Networks and Mobile Communications (WINCOM)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Zaidi, {Syed Ali Raza} and Khalil Ibrahimi and {El Kamili}, Mohamed and Abdellatif Kobbane and Nauman Aslam",

booktitle = "Proceedings - 11th International Conference on Wireless Networks and Mobile Communications, WINCOM 2024",

address = "United States",

}

Amjad, B , Ahmed, QZ , Khan, FA, Zaharis, ZD & Lazaridis, P 2024, Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers. in SAR Zaidi, K Ibrahimi, M El Kamili, A Kobbane & N Aslam (eds), Proceedings - 11th International Conference on Wireless Networks and Mobile Communications, WINCOM 2024., 10655945, International Conference on Wireless Networks and Mobile Communications (WINCOM), vol. 2024, Institute of Electrical and Electronics Engineers Inc., 11th International Conference on Wireless Networks and Mobile Communications , Leeds, United Kingdom, 23/07/24. https://doi.org/10.1109/WINCOM62286.2024.10655945

Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers. / Amjad, Bisma ; Ahmed, Qasim Z.; Khan, Faheem A. et al.

Proceedings - 11th International Conference on Wireless Networks and Mobile Communications, WINCOM 2024. ed. / Syed Ali Raza Zaidi; Khalil Ibrahimi; Mohamed El Kamili; Abdellatif Kobbane; Nauman Aslam. Institute of Electrical and Electronics Engineers Inc., 2024. 10655945 (International Conference on Wireless Networks and Mobile Communications (WINCOM); Vol. 2024).

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

TY - GEN

T1 - Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers

AU - Amjad, Bisma

AU - Ahmed, Qasim Z.

AU - Khan, Faheem A.

AU - Zaharis, Zaharias D.

AU - Lazaridis, Pavlos

N1 - Conference code: 11

PY - 2024/9/5

Y1 - 2024/9/5

N2 - The implementation of indoor localization is being facilitated through commercially available low-cost mm-wave sensors. These sensors generate point cloud outputs containing noisy estimates of detected targets due to hardware noise and multipath reflections. In contrast to previously studied regression approaches, this study introduces a classification-based approach to predict the angle-of-arrival (AoA) and range of a human target from point clouds obtained from an mm-wave sensor. Our proposed methodology achieves a 7% and 26% improvement in AoA and range prediction, respectively, compared to the baseline models. All experiments have been conducted and validated using real data recorded by the mm-wave sensor.

AB - The implementation of indoor localization is being facilitated through commercially available low-cost mm-wave sensors. These sensors generate point cloud outputs containing noisy estimates of detected targets due to hardware noise and multipath reflections. In contrast to previously studied regression approaches, this study introduces a classification-based approach to predict the angle-of-arrival (AoA) and range of a human target from point clouds obtained from an mm-wave sensor. Our proposed methodology achieves a 7% and 26% improvement in AoA and range prediction, respectively, compared to the baseline models. All experiments have been conducted and validated using real data recorded by the mm-wave sensor.

KW - angle of arrival

KW - deep learning

KW - indoor positioning system

KW - localization

KW - mm-Wave

UR - http://www.scopus.com/inward/record.url?scp=85204302843&partnerID=8YFLogxK

U2 - 10.1109/WINCOM62286.2024.10655945

DO - 10.1109/WINCOM62286.2024.10655945

M3 - Conference contribution

AN - SCOPUS:85204302843

SN - 9798350377873

T3 - International Conference on Wireless Networks and Mobile Communications (WINCOM)

BT - Proceedings - 11th International Conference on Wireless Networks and Mobile Communications, WINCOM 2024

A2 - Zaidi, Syed Ali Raza

A2 - Ibrahimi, Khalil

A2 - El Kamili, Mohamed

A2 - Kobbane, Abdellatif

A2 - Aslam, Nauman

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th International Conference on Wireless Networks and Mobile Communications

Y2 - 23 July 2024 through 25 July 2024

ER -

Amjad B , Ahmed QZ , Khan FA, Zaharis ZD, Lazaridis P. Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers. In Zaidi SAR, Ibrahimi K, El Kamili M, Kobbane A, Aslam N, editors, Proceedings - 11th International Conference on Wireless Networks and Mobile Communications, WINCOM 2024. Institute of Electrical and Electronics Engineers Inc. 2024. 10655945. (International Conference on Wireless Networks and Mobile Communications (WINCOM)). doi: 10.1109/WINCOM62286.2024.10655945

Target Localization from mm-Wave Point Clouds Using Deep Learning Based Classifiers

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this