Fall detection for elderly people using depth video data obtained by kinect
Type : Master's thesis
Publication Status : unpublished
Access : restrictedAccess
Automatic detection of unusual events such as falls is very important especially for elderly people living alone. Real-time detection of these events can reduce the health risks associated with a fall. There has been a series of ongoing researches in the ?eld of unusual event detection using the Microsoft`s depth sensor Kinect. It has been applied in areas like fall detection using only the depth images and features derived from skeletal data having exaggerated dimensionality. This thesis will propose a novel method for automatic detection of fall event by using depth cameras. Depth images generated by these cameras are used in estimating the skeletal data of a person. The contribution here is to use features extracted from this data to form a strong set of features which can help us achieve an increased precision at low redundancy. The achievements indicate that the calculated features which are derived from skeletal data are moderately powerful for detecting unusual events such as fall.
Date : 2013-08
Share this page