Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud Learning DOI Creative Commons
Ruizhi Liu, Z.-Y. Qin, Xinghui Song

и другие.

Sensors, Год журнала: 2025, Номер 25(11), С. 3377 - 3377

Опубликована: Май 27, 2025

Millimeter-wave (mmWave) radar is increasingly used in smart environments for human detection due to its rich sensing capabilities and sensitivity subtle movements. However, indoor multipath propagation causes severe ghost target issues, reducing reliability. To address this, we propose a trajectory-based suppression method that integrates multi-target tracking with point cloud deep learning. Our approach consists of four key steps: (1) pre-segmentation, (2) inter-frame trajectory tracking, (3) feature aggregation, (4) broadcasting, effectively combining spatiotemporal information point-level features. Experiments on an dataset demonstrate superior performance compared existing methods, achieving 93.5% accuracy 98.2% AUROC. Ablation studies the importance each component, particularly complementary benefits pre-segmentation processing.

Язык: Английский

A noncontact vital sign sensor demonstrating a strong correlation with an electrocardiogram electrode and a CO2 sensor DOI
Tatsuya Nagano, Nobuyuki Yamamoto,

Sae Shinomiya

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Май 6, 2025

Abstract Background: Accurate assessment of vital signs is important for reducingmortality. The aim this study was to validate the effectiveness and safety noncontactvital sign sensors. Methods: Interference tests were conducted with a noncontact sensorand medical devices. Inpatients’ heart respiratory rates monitored via sensor, measurements sensor compared those reference equipment. Results: Noncontactvital sensors devices did not interferewith each other. A total 21 patients (10 adults 11 children,including 1 baby) analysed. For all patients, correlation coefficients HR RR 0.86 0.96, respectively. In adult 0.75 paediatric 0.82 0.94, No effects on surrounding or equipment observed. Conclusion: are accurate safe.

Язык: Английский

Процитировано

0

A noncontact vital sign sensor demonstrating a strong correlation with an electrocardiogram electrode and a CO2 sensor DOI Creative Commons
Tatsuya Nagano, Nobuyuki Yamamoto,

Sae Shinomiya

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 19, 2025

Accurate assessment of vital signs is important for reducing mortality. The aim this study was to validate the effectiveness and safety noncontact sign sensors. Interference tests were conducted with a sensor medical devices. Inpatients' heart respiratory rates monitored via sensor, measurements compared those reference equipment. Noncontact sensors devices did not interfere each other. A total 21 patients (10 adults 11 children, including 1 baby) analysed. For all patients, correlation coefficients HR RR 0.86 0.96, respectively. In adult 0.75 paediatric 0.82 0.94, No effects on surrounding or equipment observed. are accurate safe.

Язык: Английский

Процитировано

0

Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud Learning DOI Creative Commons
Ruizhi Liu, Z.-Y. Qin, Xinghui Song

и другие.

Sensors, Год журнала: 2025, Номер 25(11), С. 3377 - 3377

Опубликована: Май 27, 2025

Millimeter-wave (mmWave) radar is increasingly used in smart environments for human detection due to its rich sensing capabilities and sensitivity subtle movements. However, indoor multipath propagation causes severe ghost target issues, reducing reliability. To address this, we propose a trajectory-based suppression method that integrates multi-target tracking with point cloud deep learning. Our approach consists of four key steps: (1) pre-segmentation, (2) inter-frame trajectory tracking, (3) feature aggregation, (4) broadcasting, effectively combining spatiotemporal information point-level features. Experiments on an dataset demonstrate superior performance compared existing methods, achieving 93.5% accuracy 98.2% AUROC. Ablation studies the importance each component, particularly complementary benefits pre-segmentation processing.

Язык: Английский

Процитировано

0