SensiGeRec

SensiGeRec is an automotive-grade AI gesture recognition system developed under the BonsApps Horizon 2020 programme. Unlike conventional button-based or touchscreen interfaces, SensiGeRec enables drivers to control in-vehicle infotainment, navigation, and climate systems through natural hand gestures — significantly reducing cognitive load, eye diversion, and distraction-related risk. The system employs a compact convolutional neural network architecture optimised for real-time video inference on embedded automotive-grade SoCs, delivering low-latency recognition across a rich and extensible gesture vocabulary. The BonsApps programme supported end-to-end development and validation of the model against real-world automotive deployment scenarios, including varying lighting, occupant diversity, and driver posture variations. SensiGeRec complements Sensifai's proprietary SensiGesture dataset, leveraging its 350K+ annotated frames as a pre-training foundation.

This project reflects Sensifai's applied innovation approach, combining research-grade AI capabilities with practical product and deployment requirements.

This project supports several practical scenarios across research, commercialization, and deployment contexts:

• Computer vision inference in production scenarios
• On-device or edge AI for visual understanding
• Automotive Gesture AI workflow automation
• BonsApps — Horizon 2020 innovation validation
• Cross-functional product and research collaboration