From Perception to Prediction! The Next-Gen Vehicle Pre-Crash Safety Warning Evolves Toward Proactive Intelligence
Candidate for:EE Awards - EE Challenge Award
The system combines object detection, intention inference, and trajectory prediction, optimized via model lightweighting. It operates at 30 FPS on an automotive edge AI platform and has passed on-vehicle tests. Leveraging temporal attention, gated mechanisms, and multi-modal inference, it improves dynamic risk recognition. Powered by Taiwan's first risky road user dataset (TaRRD), it demonstrates strong predictive accuracy and real-world deployment potential in complex traffic scenarios. The system is applicable to sudden risk alerts, autonomous driving behavior prediction, and traffic risk forecasting.
Malicious vote manipulation is expressly forbidden in this voting event. The organizers reserve the right to evaluate the fairness and accuracy of the voting results. AspenCore retains the authority to interpret the rules of this event.