隨著人口老齡化的加劇，智慧長照的需求也日益增長。在智慧長照場景下，如何快速、準確地識別長者身份成為了一個亟待解決的問題。人臉辨識技術因其非接觸式、高效率的優點而受到廣泛關注，也成為智慧長照場景下人員識別的重要手段之一。 本論文採用樹莓派作為邊緣裝置，透過YOLO和三元組網路來實現人臉辨識，並利用邊緣運算的概念，樹莓派可以在本地端完成人臉辨識任務，不必將數據傳輸到伺服器或雲端進行集中式處理，同時也能保障用戶的隱私和資料安全。最後，本研究將辨識結果儲存於AWS雲端服務中，如果有狀況發生，可透過Line Bot通知相關人員進行處理。這種基於邊緣運算的人臉辨識系統可以大大減少數據傳輸和處理時間，提高了系統的即時性和效率。 ;With the intensification of population aging, the demand for smart elderly care is increasing. In the context of smart elderly care, how to quickly and accurately identify the identity of the elderly has become an urgent problem. Face recognition technology has received wide attention in the field of smart elderly care due to its non-contact and efficient advantages, and it has become an important means of personnel identification. This thesis uses Raspberry Pi as an edge device to implement face recognition through YOLO and triplet networks. By utilizing the concept of edge computing, Raspberry Pi can complete the face recognition task locally without transmitting data to a server or cloud for centralized processing, thus ensuring user privacy and data security. Finally, this study stores the recognition results in AWS cloud services. If any issues occur, relevant personnel can be notified through a Line Bot for further handling. This edge computing-based face recognition system significantly reduces data transmission and processing time, thereby improving the system′s real-time performance and efficiency.
