■  Developed face recognition framework including data augmentation, training and inferencing.

■  Optimized detection and recognition models, and balancing the trade-off between accuracy and latency.

■  Developed an algorithm of virtual index that encompasses body tracking, body landmark detection, hand landmark detection, gesture classification, and coordinate transformation.

■  Implemented coordinate transformation on AR-HUD to align virtual images with real objects.

■  Developed an automatic calibration method on AR-HUD to correct the windshield distortion.