Volume : V, Issue : VII, July - 2016

FALL DETECTION SYSTEM BASED ON ANGLE CHANGE RATE WITH KINECT SENSOR

Jiajia Wang

Abstract :

 Falling is one of the most dangerous emergency situations for elderly people who live alone. But how to detect falling effectively is a difficult problem. In recent years, angle feature-based methods are widely used in fall detection. However, the methods based on angle feature easily misjudge leaning, stooping motions as falling. To improve the detection rate, this paper presents a fall detection algorithm based on angle change rate. Firstly, skeleton images are obtained by using Kinect sensor, then the orientation of major axis is derived from skeleton data, and the time of each frame is marked by using the time stamp. Lastly, the angle change rate is calculated. When the angle change rate exceeds the given threshold, it shows that the fall has occurred. Experimental results show that the proposed algorithm has higher detection rate than the algorithm based on angle.

Keywords :

Article: Download PDF    DOI : https://www.doi.org/10.36106/gjra  

Cite This Article:

Jiajia Wang FALL DETECTION SYSTEM BASED ON ANGLE CHANGE RATE WITH KINECT SENSOR Global Journal For Research Analysis, Volume : 5 | Issue : 7|July 2016

Number of Downloads : 634

References :