Hand Gesture Recognition Using FSK Radar Sensors

Area of Science:

• Computer Science
• Electrical Engineering
• Human-Computer Interaction

Background:

• Hand gesture recognition is crucial for intuitive human-computer interaction (HCI).
• Radio detection and ranging (RADAR) sensors offer robustness in diverse environments for gesture sensing.
• Existing continuous-wave (CW) radar systems have distance limitations for hand gesture recognition.

Purpose of the Study:

• To develop an advanced hand gesture recognition system capable of operating effectively across varying distances.
• To address the distance-specific performance issues inherent in prior CW radar-based approaches.
• To leverage frequency-shift keying (FSK) radar for enhanced distance-aware gesture recognition.

Main Methods:

• Implementation of a hand gesture recognition system utilizing frequency-shift keying (FSK) radar technology.
• Adoption of a convolutional neural network (CNN) model for sophisticated pattern analysis and recognition.
• Experimental validation of the system's performance across a range of distances.

Main Results:

• The proposed FSK radar system successfully performs hand gesture recognition.
• The system demonstrates effective operation across a significant range, from 30 cm to 180 cm.
• An overall accuracy of 93.67% was achieved across the entire tested distance spectrum.

Conclusions:

• The FSK radar-based hand gesture recognition system offers a significant improvement over CW radar methods.
• The system's ability to function accurately at various distances enhances its practical applicability in HCI.
• The integration of CNNs with FSK radar provides a robust solution for advanced gesture recognition.