Round trip time meets transformers: high-fidelity human counting in cluttered environments

Yonekura, Haruki; Rizk, Hamada; Yamaguchi, Hirozumi

doi:https://doi.org/10.1007/s00521-025-11540-8

Round trip time meets transformers: high-fidelity human counting in cluttered environments

Yonekura, Haruki; Rizk, Hamada; Yamaguchi, Hirozumi

Neural Computing and Applications, 2025, 37(28), 23591-23617

アクセス数:122件（2026-02-15 23:21 集計）

固定URL: https://hdl.handle.net/11094/103004

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
NeuralComputAppl_37_28_23591	pdf	なし	4.05 MB	89	2025.11.07

Creative Commons : 表示

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Round trip time meets transformers: high-fidelity human counting in cluttered environments
著者	著者名 Yonekura, Haruki
	NRID 1000030890280 1000030890280 ORCID 0000-0002-8278-8801 0000-0002-8278-8801 researchmap permalink rizk rizk Scopus Author ID 57204967686 57204967686 著者名 Rizk, Hamada
	NRID 1000080314409 1000080314409 ORCID 0000-0003-2273-4876 0000-0003-2273-4876 researchmap permalink hirozumi.yamaguchi hirozumi.yamaguchi Scopus Author ID 7404274201 7404274201 著者名 Yamaguchi, Hirozumi
キーワード等	Cluttered environments
	Multi-label classification
	Multivariate transformer
	People counting
	Round trip time
内容	The version of record of this article, first published in Neural Comput & Applic 37, 23591 (2025), is available online at Publisher’s website: https://doi.org/10.1007/s00521-025-11540-8
抄録	Accurate human counting in indoor environments is essential for optimizing people-centric applications, such as crowd management, disaster response, and monitoring in settings like shopping malls and healthcare facilities. Traditional vision approaches face challenges with poor lighting conditions and raise privacy concerns. WiFi-based solutions enable device-free human counting by detecting disruptions in wireless signals caused by human presence. However, methods using received signal strength indicator are unreliable due to physical obstructions, multipath fading, radio interference, and fluctuating access point power. While WiFi channel state information-based systems are more sensitive to environmental changes, they lack standardization, limiting their practicality. To overcome these limitations, this paper presents Time4Count, an innovative device-free indoor human counting system that leverages round trip time measurements to achieve high accuracy and scalability. Time4Count capitalizes on human-induced fluctuations in signal propagation time to accurately estimate the number of individuals in a space. By employing a multivariate transformer-based feature extraction method, the system effectively mitigates non-line-of-sight errors and signal distortions, ensuring robust performance even in cluttered indoor environments. Additionally, Time4Count integrates spatial discretization and multi-label classification techniques, enabling it to count an unlimited number of individuals in real-time. The system was rigorously evaluated in two realistic, cluttered environments using commodity hardware, involving up to 15 participants. Experimental results reveal that Time4Count achieves an high counting accuracy of 92.7%. To our knowledge, Time4Count is the first RTT-based indoor counting system, providing a precise solution for indoor monitoring. Implementation is available at: https://github.com/mclab-osaka/time4count.
出版者	Springer Science and Business Media Deutschland GmbH
収録物名	Neural Computing and Applications
巻(号)	37(28)
ページ	23591-23617
刊行年月	2025-08-29
言語	英語
ハンドルURL	https://hdl.handle.net/11094/103004
PISSN	09410643
eISSN	14333058
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1007/s00521-025-11540-8
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Neural Computing and Applications. 2025, 37(28), p. 23591-23617
DC.title	Round trip time meets transformers: high-fidelity human counting in cluttered environments
DC.creator	Yonekura, Haruki
	Rizk, Hamada
	Yamaguchi, Hirozumi
DC.publisher	Springer Science and Business Media Deutschland GmbH
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-08-29
DC.identifier	https://doi.org/10.1007/s00521-025-11540-8
DC.subject	Cluttered environments
	Multi-label classification
	Multivariate transformer
	People counting
	Round trip time
DC.description	The version of record of this article, first published in Neural Comput & Applic 37, 23591 (2025), is available online at Publisher’s website: https://doi.org/10.1007/s00521-025-11540-8
DCTERMS.abstract	Accurate human counting in indoor environments is essential for optimizing people-centric applications, such as crowd management, disaster response, and monitoring in settings like shopping malls and healthcare facilities. Traditional vision approaches face challenges with poor lighting conditions and raise privacy concerns. WiFi-based solutions enable device-free human counting by detecting disruptions in wireless signals caused by human presence. However, methods using received signal strength indicator are unreliable due to physical obstructions, multipath fading, radio interference, and fluctuating access point power. While WiFi channel state information-based systems are more sensitive to environmental changes, they lack standardization, limiting their practicality. To overcome these limitations, this paper presents Time4Count, an innovative device-free indoor human counting system that leverages round trip time measurements to achieve high accuracy and scalability. Time4Count capitalizes on human-induced fluctuations in signal propagation time to accurately estimate the number of individuals in a space. By employing a multivariate transformer-based feature extraction method, the system effectively mitigates non-line-of-sight errors and signal distortions, ensuring robust performance even in cluttered indoor environments. Additionally, Time4Count integrates spatial discretization and multi-label classification techniques, enabling it to count an unlimited number of individuals in real-time. The system was rigorously evaluated in two realistic, cluttered environments using commodity hardware, involving up to 15 participants. Experimental results reveal that Time4Count achieves an high counting accuracy of 92.7%. To our knowledge, Time4Count is the first RTT-based indoor counting system, providing a precise solution for indoor monitoring. Implementation is available at: https://github.com/mclab-osaka/time4count.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	103004
citation_title	Round trip time meets transformers: high-fidelity human counting in cluttered environments
citation_author	Yonekura, Haruki
	Rizk, Hamada
	Yamaguchi, Hirozumi
citation_publisher	Springer Science and Business Media Deutschland GmbH
citation_language	英語
citation_date	2025-08-29
citation_journal_title	Neural Computing and Applications
citation_volume	37
citation_issue	28
citation_firstpage	23591
citation_lastpage	23617
citation_doi	https://doi.org/10.1007/s00521-025-11540-8
citation_public_url	https://hdl.handle.net/11094/103004

Round trip time meets transformers: high-fidelity human counting in cluttered environments

閲覧可能ファイル

論文情報

論文詳細を表示