Large-scale City-wide People Flow Monitoring using Wi-Fi and mmWave
Problem Statement:
Understanding the large-scale movement of people within a city is critical for effective urban planning, disaster management, and public health monitoring, especially during events like natural disasters, pandemics, or large public gatherings. Traditional monitoring systems, such as CCTV networks or manual surveys, face limitations in scalability, privacy concerns, and real-time adaptability. Joint Communication and Sensing (including both mmWave radar and Wi-Fi Channel State Information) offer scalable, privacy-preserving solutions for monitoring the flow of people across a city. mmWave radar can detect movement patterns and density changes with high spatial resolution, while Wi-Fi CSI leverages existing Wi-Fi infrastructure to analyze signal variations caused by human movement, providing an unobtrusive way to monitor flow patterns across large areas. By integrating these technologies, it is possible to generate citywide insights into population dynamics, aiding in disaster response and disease outbreak mitigation. The focus will be on developing a system that can track the global flow of people between city centers and suburban areas, identify population density shifts during critical events, and provide actionable insights for urban management. Students will work on sensor fusion, large-scale data processing, and visualization techniques, with an emphasis on privacy-preserving algorithms that ensure compliance with regulations such as GDPR.
Task:
This project investigates the use of mmWave radar and Wi-Fi CSI technologies to monitor large-scale human movement across urban areas. You will start small-scale with available technologies (such as Wi-Fi and mmWave radar) to estimate and model groups (size and densities) as flows between rooms and buildings. This will then include positioning of the devices, real-time data processing, and the integration of (embedded) AI to analyze and visualize group flow patterns. The project will focus on designing a scalable and robust solution that can operate efficiently on cost-effective platforms like ESP32 or Raspberry Pi.
Example RQS:
- How accurately can large-scale human movement patterns be quantified using mmWave radar and Wi-Fi CSI across a citywide network?
- What is the impact of distributed, on-device AI models on the scalability and latency of analyzing citywide human movement patterns using mmWave and Wi-Fi CSI technologies?
- How can data from mmWave radar and Wi-Fi CSI systems be optimized and combined to provide actionable insights for disaster response or public health monitoring while ensuring privacy and regulatory compliance?
What am I looking for:
I am looking for motivated students who go beyond the 'sixes' attitude, ideally motivated to publish their results in the future.
Due to the flexibility of the assignment, I wish to have a coffee with you to ensure it’s a good match before I agree to supervise! ;)
Work:
40% implementation (hardware/software), 40% Data analysis, 20% Writing
Contact:
Jeroen Klein Brinke (j.kleinbrinke@utwente.nl)
Allow multiple students: YES
Photo: https://www.pexels.com/photo/aerial-photo-of-city-2921137/