Sub-field · 12 papers
Crowd Counting via Wireless Sensing
Crowd counting and density estimation across diverse environments—bus stops, restaurants, metro systems, and large surveillance areas—is the central problem, addressed through methods ranging from passive WiFi probe request sniffing and Bluetooth sensing to millimeter-wave radar and camera-based deep learning. A prominent sub-theme involves fusing multiple sensing modalities, particularly WiFi signals combined with video, to improve accuracy where single-sensor approaches fall short. CNN-based density map estimation and machine learning models for bridging raw sensor signals to ground-truth counts are the dominant technical approaches throughout the literature.
Papers in this community
- A survey of recent advances in CNN-based single image crowd counting and density estimation 2018 DOI ↗
- Toward Accurate Crowd Counting in Large Surveillance Areas Based on Passive WiFi Sensing 2023 DOI ↗
- Heterogeneous Dual-Attentional Network for WiFi and Video-Fused Multi-Modal Crowd Counting 2024 DOI ↗
- MMCOUNT: Stationary Crowd Counting System Based on Commodity Millimeter-Wave Radar 2024 DOI ↗
- <i>STRmt</i>: A state transition based model for real‐time crowd counting in a metro system 2024 DOI ↗
- Recent trends in crowd analysis: A review 2021 DOI ↗
- Crowd Counting in Large Surveillance Areas by Fusing Audio and WiFi Sniffing Data 2024 DOI ↗
- Constructing WiFi-Video-Fused Multi-Modal Synthetic Datasets for Crowd Counting 2025 DOI ↗
- Counting and Tracking People to Avoid from Crowded in a Restaurant Using mmWave Radar 2023 DOI ↗
- Motion estimation of high density crowd using fluid dynamics 2020 DOI ↗
- Bluetooth-Based Vehicle Counting: Bridging the Gap to Ground-Truth With Machine Learning 2023 DOI ↗
- A low-cost automatic people-counting system at bus stops using Wi-Fi probe requests and deep learning 2025 DOI ↗