Abstract
In the area of health care, fall is a dangerous problem for aged persons. Sometimes, they are a serious cause of death. In addition to that, the number of aged persons will increase in the future. Therefore, it is necessary to develop an accurate system to detect fall. In this paper, we present spatiotemporal method to detect fall form videos filmed by surveillance cameras. Firstly, we computed key points of human skeleton. We calculated distances and angles between key points of each two pair sequences frames. After that, we applied Principal Component Analysis (PCA) to unify the dimension of features. Finally, we utilized Support Vector Machine (SVM), Decision Tree, Random Forest and K Nearest Neighbors (KNN) to classify features. We found that SVM is the best classifier to our method. The results of our algorithm are as follow: accuracy is 98.5%, sensitivity is 97% and the specificity is 100%.
Highlights
INTRODUCTION UNion Nation published a report in 2005 [1] which presents statistics about the population of aged people in the world
They show the percentage of older adults (60 years or over) in the past, and in the future. They cited that the proportion in 1950 is 8%, they mentioned that this percentage grew to 11% in 2009 and they estimated that the rate would increase to 22% in 2050. They show that these statistics include developed, developing countries and even countries of the third world
We just utilize the key points of the person, if we want to detect the position of the body in the video
Summary
Nion Nation published a report in 2005 [1] which presents statistics about the population of aged people in the world They show the percentage of older adults (60 years or over) in the past, and in the future. The World Health Organization [2] show statics about fall causes They cited that each year, an estimated 646000 persons die from fall. Elderly persons (65 years of age or over) represent the highest percentage of fatal falls. There are a lot of proposed works to decrease injuries for aged persons. They used different support to build their algorithms.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.