Traffic and Accident Monitoring using Wi-Fi and mmWave (Joint Communication & Sensing)
Problem Statement:
Efficient traffic management is essential for modern cities to ensure smooth transportation, reduce congestion, and improve safety for drivers, cyclists and pedestrians. Traditional traffic monitoring systems, such as cameras and inductive loop detectors, face limitations in scalability (e.g., infrastructural changes to roads for inductive loops), privacy concerns (with video), and environmental robustness. Additionally, these systems often fail to provide real-time, granular data that can enable adaptive and smart infrastructure solutions, such as dynamic traffic light adjustments, rerouting traffic, or monitoring accidents and road conditions. Unobtrusive sensing technologies, such as mmWave radar and Wi-Fi Channel State Information (CSI), offer innovative solutions for real-time traffic monitoring and smart infrastructure. mmWave radar provides high-resolution data (vehicle speed, position, movement patterns, etc), while Wi-Fi CSI can detect subtle changes in signal propagation caused by vehicles, cyclists and pedestrians. This could enable the monitoring of road usage and pedestrian traffic without the need for intrusive solutions. Together, these technologies can provide a comprehensive and cost-effective approach to managing traffic flow, detecting accidents, and adapting city infrastructure dynamically to changing traffic conditions.
Task:
This project explores the development of a smart traffic monitoring system using mmWave radar and Wi-Fi CSI technologies. The goal is to create a solution that can monitor traffic flow, detect accidents, and provide data-driven insights for adaptive infrastructure, such as dynamic traffic light control or rerouting strategies. Students will work on sensor fusion, real-time data processing, and the integration of embedded machine learning to analyze and visualize traffic 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. The system should not only demonstrate its capability for traffic flow optimization but also explore applications such as pedestrian safety monitoring, emergency vehicle prioritization, and environmental impact reduction through smoother traffic management.
Example RQS:
- How accurately can traffic flow and vehicle behaviours, such as speed and direction, be quantified using mmWave radar and Wi-Fi CSI technologies in real-time outdoors?
- What is the impact of embedded AI models on the accuracy and latency of detecting traffic anomalies (e.g., accidents, congestion) and optimizing smart traffic lights using ESP32 or Raspberry Pi platforms?
- How can mmWave radar and Wi-Fi CSI data be combined to provide a comprehensive understanding of both vehicular and pedestrian traffic in urban environments while ensuring data privacy and minimizing computational costs?
- How can dynamic orchestration of edge devices and their computing resources be optimized to enable real-time and energy efficiency traffic and accident monitoring to enable smart cities?
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/landscape-photography-of-cars-7674/