Open-Set Gait Recognition from Sparse mmWave Radar Point Clouds

2025-03-10

AI Summary

To address the challenge of rejecting unknown subjects in open-set gait recognition using sparse millimeter-wave (mmWave) radar point clouds, this paper pioneers the application of open-set learning to this domain. We propose a joint supervised classification and unsupervised reconstruction neural architecture that learns a highly regularized latent space, coupled with a tunable speed–accuracy trade-off probabilistic novelty detection algorithm. Our method integrates sparse point cloud modeling, hybrid supervised/self-supervised learning, and probabilistic anomaly discrimination. Evaluated on our newly established mmGait10 dataset (10 subjects × 5 hours), the approach achieves a 24% average F1-score improvement over state-of-the-art methods and supports multi-level open-set evaluation. We publicly release both the first large-scale mmWave radar gait point cloud dataset and the corresponding codebase, significantly enhancing recognition robustness and privacy preservation in real-world deployments.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The adoption of Millimeter-Wave (mmWave) radar devices for human sensing, particularly gait recognition, has recently gathered significant attention due to their efficiency, resilience to environmental conditions, and privacy-preserving nature. In this work, we tackle the challenging problem of Open-set Gait Recognition (OSGR) from sparse mmWave radar point clouds. Unlike most existing research, which assumes a closed-set scenario, our work considers the more realistic open-set case, where unknown subjects might be present at inference time, and should be correctly recognized by the system. Point clouds are well-suited for edge computing applications with resource constraints, but are more significantly affected by noise and random fluctuations than other representations, like the more common micro-Doppler signature. This is the first work addressing open-set gait recognition with sparse point cloud data. To do so, we propose a novel neural network architecture that combines supervised classification with unsupervised reconstruction of the point clouds, creating a robust, rich, and highly regularized latent space of gait features. To detect unknown subjects at inference time, we introduce a probabilistic novelty detection algorithm that leverages the structured latent space and offers a tunable trade-off between inference speed and prediction accuracy. Along with this paper, we release mmGait10, an original human gait dataset featuring over five hours of measurements from ten subjects, under varied walking modalities. Extensive experimental results show that our solution attains F1-Score improvements by 24% over state-of-the-art methods, on average, and across multiple openness levels.

Problem

• Open-set gait recognition using sparse mmWave radar point clouds.
• Addressing noise and fluctuations in sparse point cloud data.
• Detecting unknown subjects with a probabilistic novelty detection algorithm.

Innovation

• Combines supervised classification with unsupervised reconstruction
• Introduces probabilistic novelty detection algorithm
• Releases mmGait10 dataset for varied walking modalities