A Novel Algorithm for Human Fall Detection using Height, Velocity and Position of the Subject from Depth Maps

摘要: Human fall detection systems play an important role in our daily life, because falls are the main obstacle for elderly people to live independently and it is also a major health concern due aging population. Different approaches used develop human with special needs. The three basic include some sort of wearable devices, ambient based devices or non-invasive vision-based using cameras. Most such either on sensor which very often rejected by users high false alarm difficulties carrying them during their life activities. This paper proposes system height, velocity position subject depth information from Microsoft Kinect sensor. Classification other activities accomplished height extracted information. Finally identified confirmation. From experimental results, proposed was able achieve average accuracy 94.81% sensitivity 100% specificity 93.33%.