cs.CVNov 14, 2026

Floorplan-Context-Aware Cross-Environment Human Activity Recognition from mmWave Radar Point Clouds

Authors: Zixiong Han, Xilai Wang, Chenzhe Zhao, Amr Mourad, Miodrag Bolic

Organizations: Computational Analysis and Applications Research Group, University of Ottawa, Ottawa, Canada

Abstract

Human activity recognition (HAR) models based on mmWave radar point clouds and trained in controlled open spaces often experience performance degradation when deployed in furnished rooms. We propose a Floorplan-Context-Aware (FCA) HAR enhancement method that augments the input with subject-furniture relative position information to improve cross-environment performance. Because existing mmWave point-cloud datasets lack registered floorplans, we introduce a pseudo-landmark augmentation strategy for training the FCA model. In cross-environment evaluation on the mm-ADL-Home dataset, FCA achieves 77.70% accuracy and 65.49% macro-F1, improving upon the point-cloud-only direct-transfer baseline by 10.73 and 10.05 percentage points, respectively, and exceeding the strongest evaluated adaptation baseline by 7.37 and 6.27 percentage points. At deployment, FCA requires only a one-time registration of furniture landmarks, with no target-domain activity annotations or model weight updates.

Figures & tables

Explore similar work

May 10, 2026

DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition

Millimeter-wave (mmWave) radar provides privacy-preserving sensing and is valuable for human action recognition (HAR). Existing mmWave point cloud datasets are limited in scale and mostly collected under homogeneous single-source settings, preventing current methods from handling real-world distribution shifts caused by heterogeneous radar sources, such as different devices and frequency bands. To address this, we introduce UniMM-HAR, the largest and first mmWave point cloud HAR dataset for heterogeneous multi-source scenarios, standardizing three distinct radar configurations to realistically evaluate cross-source generalization. We further propose the Doppler-aware Point Cloud Network (DAP-Net) to tackle heterogeneity challenges. DAP-Net enhances intra-modal representations and performs cross-modal alignment to learn source-invariant action semantics. Leveraging action-consistent spatio-temporal Doppler patterns as anchors, the Dual-space Doppler Reparameterization (D2R) module performs sample-adaptive geometric densification and Doppler-guided feature recalibration, while the Text Alignment Module (TAM) provides stable semantic anchors via a pretrained textual space. Experiments show that DAP-Net significantly outperforms existing methods under heterogeneous radar settings, achieving state-of-the-art accuracy and strong cross-source robustness.
Sep 13, 2026

EdgeHAR: An Edge-Native Compact Sensor Foundation Model for Human Activity Recognition

Sensor-based human activity recognition (HAR) is fundamental to ubiquitous and wearable computing, yet existing foundation models are largely designed for cloud-scale deployment and struggle with real-world sensing shifts, including unseen users, devices, sampling rates, and sensor placements. We present EdgeHAR, an edge-native compact sensor foundation model designed for wearable intelligence. Unlike conventional models that entangle activity knowledge with acquisition variations, EdgeHAR learns transferable representations by factorizing sensor signals into three latent codes: an (i)Activity-Semantic Code capturing reusable activity knowledge, a (ii)Motion-Dynamics Code modeling temporal patterns, and an (iii)Acquisition-Context Code representing sensor-specific variations. This disentangled design enables efficient adaptation to new users, devices, placements, and activity classes with limited target-domain data. By incorporating lightweight adaptation modules, EdgeHAR achieves foundation-model-level transferability while satisfying edge constraints in computation, memory, latency, and privacy. Experiments across heterogeneous HAR datasets demonstrate that EdgeHAR maintains competitive recognition performance under distribution shifts with substantially reduced deployment cost. EdgeHAR establishes a practical paradigm for compact, edge-first foundation models for ubiquitous sensing systems.
Mar 9, 2026

mmGAT: Pose Estimation by Graph Attention with Mutual Features from mmWave Radar Point Cloud

Pose estimation and human action recognition (HAR) are pivotal technologies spanning various domains. While the image-based pose estimation and HAR are widely admired for their superior performance, they lack in privacy protection and suboptimal performance in low-light and dark environments. This paper exploits the capabilities of millimeter-wave (mmWave) radar technology for human pose estimation by processing radar data with Graph Neural Network (GNN) architecture, coupled with the attention mechanism. Our goal is to capture the finer details of the radar point cloud to improve the pose estimation performance. To this end, we present a unique feature extraction technique that exploits the full potential of the GNN processing method for pose estimation. Our model mmGAT demonstrates remarkable performance on two publicly available benchmark mmWave datasets and establishes new state of the art results in most scenarios in terms of human pose estimation. Our approach achieves a noteworthy reduction of pose estimation mean per joint position error (MPJPE) by 35.6% and PA-MPJPE by 14.1% from the current state of the art benchmark within this domain.