Meta-Learning-Based People Counting and Localization Models Employing CSI from Commodity WiFi NICs

2025-02-05

AI Summary

Commercial WiFi network interface cards (NICs) suffer from hardware offsets and multi-device interference in uncontrolled environments, degrading the accuracy of CSI-based human counting and localization. To address this, we propose a low-latency CSI preprocessing method and an adaptive sensing framework. Our approach introduces a novel zero-filter offset correction mechanism for CSI calibration and establishes a meta-learning framework based on a modified Model-Agnostic Meta-Learning (MAML) algorithm to enable rapid cross-scenario generalization. The model employs a hybrid CNN-LSTM architecture to jointly capture spatiotemporal CSI features. Extensive experiments across multiple real-world environments demonstrate that our method achieves an average counting error of less than 0.8 persons and a localization RMSE of 0.42 m. Compared to conventional supervised learning baselines, it improves accuracy by over 37%. The proposed framework significantly enhances the robustness and practicality of WiFi-based contactless sensing.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this paper, we consider people counting and localization systems exploiting channel state information (CSI) measured from commodity WiFi network interface cards (NICs). While CSI has useful information of amplitude and phase to describe signal propagation in a measurement environment of interest, CSI measurement suffers from offsets due to various uncertainties. Moreover, an uncontrollable external environment where other WiFi devices communicate each other induces interfering signals, resulting in erroneous CSI captured at a receiver. In this paper, preprocessing of CSI is first proposed for offset removal, and it guarantees low-latency operation without any filtering process. Afterwards, we design people counting and localization models based on pre-training. To be adaptive to different measurement environments, meta-learning-based people counting and localization models are also proposed. Numerical results show that the proposed meta-learning-based people counting and localization models can achieve high sensing accuracy, compared to other learning schemes that follow simple training and test procedures.

Problem

• Develops people counting and localization models
• Utilizes meta-learning for environmental adaptability
• Improves accuracy in WiFi-based CSI applications

Innovation

• Meta-learning for adaptive models
• Preprocessing CSI for offset removal
• Commodity WiFi NICs utilization