Millimeter-wave sensors identify people by daily activities beyond just walking
Beyond Gait: Person Identification from Millimeter-Wave Point Clouds Across Activities of Daily Living
Computer Vision and Pattern Recognition
Summary
Identifying people using millimeter-wave sensors has mostly focused on how they walk. The authors show that other everyday activities, like sitting or standing, can also help tell people apart. They created a new dataset tracking different activities from several people and developed a method that recognizes activities first, then uses this to improve identifying who is who. Their approach improved identification accuracy significantly, even when people were doing various activities indoors. This work shows it's possible to identify individuals not just from walking but from many daily activities.
millimeter-wave sensorspoint cloudperson identificationgait recognitionactivities of daily livinghuman activity recognitionmixture of expertsre-identificationPointNetindoor sensing
Authors
Xilai Wang, Zixiong Han, Saad Rhanmouni, Chenzhe Zhao, Yunze Lu, Miodrag Bolic
Abstract
Person identification from millimeter-wave (mmWave) point clouds has mainly relied on gait. Indoor walking, however, is often brief and interrupted, while other activities of daily living (ADLs) may provide complementary identity information. We investigate identification across seven ADLs using mm-ADL, a new point-cloud dataset collected from 11 subjects under a controlled protocol. This extension introduces heterogeneous states and transitions whose spatial and temporal characteristics vary with activity. We therefore study whether activity can provide useful context for learning identity representations. We propose an activity-conditioned framework in which a human activity recognition router dispatches each clip to an activity-specific identity expert. The framework is implemented as a supervised mixture of experts, using a dual-stream static-dynamic PointNet (DS-SDPNet) to combine time-aggregated spatial structure with frame-to-frame information. We evaluate closed-set identification (ID) and subject-disjoint re-identification (ReID). With learned hard routing, ID accuracy increases from 62.1% to 68.0%. In a two-occupant ReID setting, hard routing increases mAP from 57.2% to 75.4% and Rank-1 accuracy from 59.1% to 82.1%. Under a matched gallery partition, activity-specific experts also outperform a shared embedding, showing that the gain extends beyond restricting the gallery. These results support the feasibility of using ADLs beyond gait for identification and the value of activity conditioning under controlled indoor conditions.