A Study of Fall Detection System Using Context Cognition Method
Yoon-Kyu Kang, Hee-Yong Kang, Jong-Bae Kim · 2021
Falls are one of the major causes of injury and death among elderly people aged 65 and industries too. A fall detection system is necessary to identify falling activities out of activities of daily lives. Even though new methods have shown on research paper, the number of studies in vision-based systems is still increasing. But existing vision-based fall detection systems have lot of weakness to be generalized mainly due to the difficulties such as variations in physical appearances, different camera viewpoints, occlusions, background clutter and darkness. Head and upper body location of human provides a critical information at the time of fall. This paper presents a vision-based fall tracking method where upper body joints are grouped into one segment to increase the fall classification ratio. Segment consist of Head and shoulders joints combinations represents the upper region and head region. Segment method can be beneficial to achieve an efficient tracking of human activities and provide strong technic to distinguish falls from activities of daily lives.