| dc.description.abstract | With the aging of the global population and the shortage of medical care manpower, home health care has become an important part of people’s livelihood.
To issue. If the elderly or those living alone are active at home, falls and injuries are a common risk, especially for the elderly.
However, if you do not get timely assistance when you fall, you may cause serious injuries. In recent years, many fall warning systems and
Wearable fall warning devices have been proposed one after another. Among them, the fall event detection technology and application based on the optical assist of the camera are introduced.
From a wide range of research concerns. However, such fall detection methods face many limitations in the home living environment, such as
Factors such as occlusion by obstacles and the camera′s field of view and angle of view.
Therefore, this paper proposes a multi-camera collaborative fall detection mechanism based on deep reinforcement learning.
Image recognition collaboration and judgment between multiple cameras to solve the difficulties encountered by a single camera in the fall event detection
Difficult, and use deep reinforcement learning to learn for dynamic groups of multi-camera collaboration, the purpose
It is to improve the accuracy of the multi-camera system and speed up the decision-making time of the system, and through the actual construction
Detection environment for single-camera decision-making, multi-camera decision-making (not using dynamic groups), and multi-camera decision-making
(Using dynamic groups) Three schemes for actual performance comparison. | en_US |