Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud Learning

Millimeter-wave (mmWave) radar is increasingly used in smart environments for human detection due to its rich sensing capabilities and sensitivity to subtle movements. However, indoor multipath propagation causes severe ghost target issues, reducing radar reliability. To address this, we propose a t...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruizhi Liu, Zhenhang Qin, Xinghui Song, Lei Yang, Yue Lin, Hongtao Xu
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3377
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330941623795712
author Ruizhi Liu
Zhenhang Qin
Xinghui Song
Lei Yang
Yue Lin
Hongtao Xu
author_facet Ruizhi Liu
Zhenhang Qin
Xinghui Song
Lei Yang
Yue Lin
Hongtao Xu
author_sort Ruizhi Liu
collection DOAJ
description Millimeter-wave (mmWave) radar is increasingly used in smart environments for human detection due to its rich sensing capabilities and sensitivity to subtle movements. However, indoor multipath propagation causes severe ghost target issues, reducing radar reliability. To address this, we propose a trajectory-based ghost suppression method that integrates multi-target tracking with point cloud deep learning. Our approach consists of four key steps: (1) point cloud pre-segmentation, (2) inter-frame trajectory tracking, (3) trajectory feature aggregation, and (4) feature broadcasting, effectively combining spatiotemporal information with point-level features. Experiments on an indoor dataset demonstrate its superior performance compared to existing methods, achieving 93.5% accuracy and 98.2% AUROC. Ablation studies demonstrate the importance of each component, particularly the complementary benefits of pre-segmentation and trajectory processing.
format Article
id doaj-art-4e91f687a3cc4bfca8195cdd7f189824
institution Kabale University
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-4e91f687a3cc4bfca8195cdd7f1898242025-08-20T03:46:46ZengMDPI AGSensors1424-82202025-05-012511337710.3390/s25113377Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud LearningRuizhi Liu0Zhenhang Qin1Xinghui Song2Lei Yang3Yue Lin4Hongtao Xu5State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai 201203, ChinaState Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai 201203, ChinaState Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai 201203, ChinaICLegend Micro, Shanghai 201203, ChinaICLegend Micro, Suzhou 215134, ChinaState Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai 201203, ChinaMillimeter-wave (mmWave) radar is increasingly used in smart environments for human detection due to its rich sensing capabilities and sensitivity to subtle movements. However, indoor multipath propagation causes severe ghost target issues, reducing radar reliability. To address this, we propose a trajectory-based ghost suppression method that integrates multi-target tracking with point cloud deep learning. Our approach consists of four key steps: (1) point cloud pre-segmentation, (2) inter-frame trajectory tracking, (3) trajectory feature aggregation, and (4) feature broadcasting, effectively combining spatiotemporal information with point-level features. Experiments on an indoor dataset demonstrate its superior performance compared to existing methods, achieving 93.5% accuracy and 98.2% AUROC. Ablation studies demonstrate the importance of each component, particularly the complementary benefits of pre-segmentation and trajectory processing.https://www.mdpi.com/1424-8220/25/11/3377millimeter-wave radarghost suppressionmulti-target trackingpoint cloud segmentationmultipath
spellingShingle Ruizhi Liu
Zhenhang Qin
Xinghui Song
Lei Yang
Yue Lin
Hongtao Xu
Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud Learning
Sensors
millimeter-wave radar
ghost suppression
multi-target tracking
point cloud segmentation
multipath
title Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud Learning
title_full Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud Learning
title_fullStr Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud Learning
title_full_unstemmed Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud Learning
title_short Indoor mmWave Radar Ghost Suppression: Trajectory-Guided Spatiotemporal Point Cloud Learning
title_sort indoor mmwave radar ghost suppression trajectory guided spatiotemporal point cloud learning
topic millimeter-wave radar
ghost suppression
multi-target tracking
point cloud segmentation
multipath
url https://www.mdpi.com/1424-8220/25/11/3377
work_keys_str_mv AT ruizhiliu indoormmwaveradarghostsuppressiontrajectoryguidedspatiotemporalpointcloudlearning
AT zhenhangqin indoormmwaveradarghostsuppressiontrajectoryguidedspatiotemporalpointcloudlearning
AT xinghuisong indoormmwaveradarghostsuppressiontrajectoryguidedspatiotemporalpointcloudlearning
AT leiyang indoormmwaveradarghostsuppressiontrajectoryguidedspatiotemporalpointcloudlearning
AT yuelin indoormmwaveradarghostsuppressiontrajectoryguidedspatiotemporalpointcloudlearning
AT hongtaoxu indoormmwaveradarghostsuppressiontrajectoryguidedspatiotemporalpointcloudlearning