Population of old generation is increasing in most countries. Falling is one of the most dangerous events that may happen for these people and needs immediate medical care. Automatic fall detection systems help them stay alone at home and reduce the burden on healthcare system. Visual systems have advantage over wearable devices that do not disturb the normal life of the people. They extract some features form video sequences and decide based on them. Commonly used features have disadvantage of being view dependent. Using several cameras to solve this problem increases the complexity of final system. In this project we exploit a drawback of one simple background subtraction method and propose the variations in silhouette area as a feature that is robust to view direction. We use running average method for background subtraction and show experimentally and mathematically that variations in silhouette area can be a measure of rapid motion during the fall, impact to surrounding environment and inactivity after fall. We use support vector machines for justify; MARGIN: 0cm 0cm 10pt" Key words fall detection, visual surveillance, silhouette area, view invariant, support vector machines
