Radar-based in-cabin sensing using 60 GHz stepped-frequency continuous-wave radar

Child safety in vehicles has become a critical concern, with numerous fatalities and injuries occurring due to improper seatbelt usage and heatstroke deaths from children being left in hot cars. To address this issue, this research presents a radar-based in-cabin sensing system designed to monitor the occupants' presence in the car and classify them as children, adults, or pets for targeted safety measures. The proposed method combines occupancy detection and vital sign detection to provide accurate information about the occupants and their health status. Our approach employs a Stepped-Frequency Continuous-Wave (SFCW) millimeter wave radar, which offers a high resolution and signal-to-noise ratio. We explore three methods for occupancy detection: power loss profiling, Fast Fourier Transform (FFT), and Multiple Signal Classification (MUSIC). Vital sign detection is achieved using Doppler-based techniques. We developed a robust in-cabin sensing that utilizes the benefits from occupancy detection and vital sign detection to complement each other to achieve more robust sensing and promising accuracy. Preliminary results demonstrate the potential of this system, but further research and access to super-computational resources are required to optimize the processing methods, improve memory management, and incorporate reinforcement learning techniques. Our goal is to significantly reduce the number of child-related fatalities and injuries in motor vehicles by enhancing vehicle safety through advanced sensing and detection technologies.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2023

Author dc:creator

• Yao, Chun-Kai (Sean)

Contributors dc:contributor

• Soltanaghai, Elahe

• Stepped-frequency Continuous-wave (sfcw) Radar
• In-cabin Sensing
• Digital Signal Processing

Statement dc:rights

• Copyright 2023 Chun-Kai (Sean) Yao

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/121378

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F121378