| Summary: | 碩士 === 國立臺灣科技大學 === 資訊工程系 === 107 === In this paper, we propose a novel and robust vision- and system on chip (SoC)-based system as a sensor to effectively detect falls for the elderly. The proposed method consists of five steps: the initial light stability confirmation, gradient difference-based foreground detection, dilation- and multi-frame-based foreground construction, solving the false fall detection problem, and fall detection determination with a general-purpose input/output based fall warning transmission. Based on the real test videos, the comprehensive experiments have justified the low-powered, low cost, and high accuracy merits of the proposed method when compared with the related methods.
|
|---|
