This research studies vision-based autonomous driving perception with a focus on occlusion and visibility challenges. By integrating temporal reasoning, multi-view geometry, and contextual modeling, the work aims to improve scene understanding and safety under limited or obstructed visual conditions.
This research explores intelligent haptic feedback systems that integrate sensing and AI to support intuitive human–machine interaction in medical, sports, and interactive environments.
This research focuses on interpretable video-based AI for clinical motion analysis, with an emphasis on gait and posture assessment using deep learning, multimodal fusion, and multi-view human understanding.
This research studies video-based sports analytics using deep learning and 3D human pose estimation to analyze athletic movements, performance, and technique in real-world environments.