Falls are a major threat to the independence and quality of life of elderly people. As the worldwide population of elderly increases each year, responding to falls is essential. Computer vision systems provide a new promising solution in responding falls through detecting fall events. This paper presents a new technique in detecting falls based on human shape variation. The proposed visual based fall detection technique uses three points to represent a person instead of the conventional ellipse or bounding box. Features extracted from the lines formed by these three points are then used in shape change analysis to detect falls. In comparison with conventional techniques, our proposed three points technique not only increases the fall detection rate but reduces the computational complexity as well.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.