tinyRadar: mmWave Radar based Activity Classification for Edge Computing

Number of Students : 1
Guides : Chetan Singh Thakur

The rising need for elderly care, child care, and intrusion detection challenges the sustainability of traditional systems that depend on in-person monitoring and surveillance. The current state-of-the-art technology heavily relies on InfraRed (IR) and camera-based systems, which often require cloud computing. It can lead to higher latency, data theft, and privacy issues of being continuously monitored. In this project, we will work on tinyML-based single-chip radar solution for on-edge sensing and detection of human activity. Edge computing within a small form factor solves the issue of data theft and privacy concerns as radar provides point cloud information. Also, it can operate in adverse environmental conditions like fog, dust, and low light. This work used the Texas Instruments IWR6843 millimeter wave (mmWave) radar board to implement signal processing and Neural Network (CNN) for various activity classification. The skillsets required in this project are embedded system, basic machine learning, hardware-software codesign. We will build a complete hardware prototype including mechanical casing, which will be deployed on the field for real-time application.