Real-Time Fall Detection Using Uncalibrated Fisheye Cameras

2020 ◽  
Vol 12 (3) ◽  
pp. 588-600
Author(s):  
Konstantina N. Kottari ◽  
Konstantinos K. Delibasis ◽  
Ilias G. Maglogiannis
Keyword(s):  
2021 ◽  
Author(s):  
Jincheng Lu ◽  
Zixuan Ou ◽  
Ziyu Liu ◽  
Cheng Han ◽  
Wenbin Ye

2019 ◽  
Vol 48 (1) ◽  
pp. 22-42 ◽  
Author(s):  
Insoo Kim ◽  
Kyung-Suk Lee ◽  
Kyungran Kim ◽  
Kyungsu Kim ◽  
Hye-Seon Chae ◽  
...  

Author(s):  
Paul C.-P. Chao ◽  
Li-Chi Hsu ◽  
Yu-Feng Li ◽  
Chin-Wei Chun

A novel wireless circuit module is designed in this study to perform ubiquitous fall detections and then real-time fall detections of help messages. It is a common trend that as the demand for living quality increases tremendously while the technologies of electronics and medicine advances greatly, personal cares are elevated to the next level. As for the aging society, the issue of injuries due to falls among senior population arises rapidly [1,2]. Costly prices are often paid as the elderly falls without notice from companions at the site. Therefore, various modules and/or systems of automatic and wireless fall detection are developed into a past pace. Such fall-detection modules are demanded to be able to automatically detect falls of subjects and then send the help message to a remote hospital for an immediate help.


Author(s):  
Nadia Baha ◽  
Eden Beloudah ◽  
Mehdi Ousmer

Falls are the major health problem among older people who live alone in their home. In the past few years, several studies have been proposed to solve the dilemma especially those which exploit video surveillance. In this paper, in order to allow older adult to safely continue living in home environments, the authors propose a method which combines two different configurations of the Microsoft Kinect: The first one is based on the person's depth information and his velocity (Ceiling mounted Kinect). The second one is based on the variation of bounding box parameters and its velocity (Frontal Kinect). Experimental results on real datasets are conducted and a comparative evaluation of the obtained results relative to the state-of-art methods is presented. The results show that the authors' method is able to accurately detect several types of falls in real-time as well as achieving a significant reduction in false alarms and improves detection rates.


Sign in / Sign up

Export Citation Format

Share Document