Indoor Vision-Based Fall Detection System with Improved Optical Dynamic Flow

Fall is one of the major causes of death for older people, where 30 % of falls cause severe injuries such as fractures to the limbs or a concussion. Falls can also indicate that the person is suffering from an acute condition such as a heart attack, seizures which can be life threatening if not treated immediately. Hence, fall detection is an important problem which could help report falls experienced by such people immediately, ensuring the medical attention needed. This project focuses on addressing the problem of automated fall detection using deep learning algorithms.