Abstract
We present a methodology for obtaining a low memory and low computational load for a radar signal processing pipeline of a Frequency-Modulated Continuous-Wave (FMCW) radar tailored to embedded systems. Our analysis covers the entire radar signal processing pipeline, including radar signal conditioning, feature extraction, and neural network models, including pruning and quantization. We focus on a complex dataset of aircraft marshalling signals captured from an ultra-low-power, single-input, single-output (SISO) FMCW radar. With our methodology, we achieve a new state-of-the-art classification accuracy of 71.4\%, marking a significant improvement of over six percentage points while maintaining a reduced memory footprint and minimal computing requirements. This advancement contributes to developing efficient radar signal processing systems for resource-constrained applications and represents a crucial step toward realizing highly efficient and accurate radar-based gesture recognition systems.
Original language | English |
---|---|
Title of host publication | 2024 21st European Radar Conference, EuRAD 2024 |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 457-460 |
Number of pages | 4 |
ISBN (Electronic) | 978-2-87487-079-8 |
DOIs | |
Publication status | Published - 4 Nov 2024 |
Event | 21st European Radar Conference, EuRAD 2024 - Paris, France Duration: 25 Sept 2024 → 27 Sept 2024 Conference number: 21 https://www.eumweek.com/ |
Conference
Conference | 21st European Radar Conference, EuRAD 2024 |
---|---|
Abbreviated title | EuRAD 2024 |
Country/Territory | France |
City | Paris |
Period | 25/09/24 → 27/09/24 |
Internet address |
Funding
This work has been funded by the Dutch Organization for Scientific Research (NWO) with Grant OCENWM.22.331.
Funders | Funder number |
---|---|
Nederlandse Organisatie voor Wetenschappelijk Onderzoek | OCENWM.22.331 |
Keywords
- Gesture Recognition
- Human Activity Monitoring
- Deep Learning Methods
- Radar signal processing
- FMCW Radar
- Radar
- Embedded Device
- Aircraft Marshalling Signals
- Deep Learning
- Human Gesture Classification