A Sungkyunkwan University research team has developed an artificial intelligence (AI)-based system to prevent subway door-related accidents in collaboration with the Korea Advanced Institute of Science and Technology (KAIST) and Texas Tech University. The university said researchers from the three institutions worked together to develop an AI-based passenger movement estimation system to help prevent subway door entrapment accidents. The system is designed to predict passenger movements using CCTV footage by detecting passengers and classifying their movement types. Unlike conventional reactive methods, the new system is capable of proactively identifying risks before passengers even reach the platform, according to the university. The research team was led by Chong Jo-woon, a professor at Sungkyunkwan University’s School of Electronics and Electrical Engineering. Jo Hee, a doctoral student, contributed to analyzing data and designing an AI model for the accident prevention system. The team was joined by Lisa Lim, a professor of civil and environmental engineering at KAIST, and Yifan Li
KAIST, Nvidia deepen AI collaboration with joint research facilities