近年來5G環境的布建日益普遍,博物館也開始思考如何應用AI的學習和判斷能力,並結合5G高速低延遲特性,改善博物館的文物導覽服務。因此,國立故宮博物院於近年推出了名為「雅集鏡遇」的智慧眼鏡導覽服務,以微軟Hololens智慧眼鏡為載具,以故宮繪畫及展廳空間為對象,應用Google Tensorflow進行機器學習找出文物及展廳空間特徵後,運算主機即可判斷觀眾所見之文物特徵及所在空間為何,再應用5G訊號將判讀結果及渲染之動畫等材料傳輸回智慧眼鏡,讓觀眾可以戴著智慧眼鏡自由在各個文物前和展廳空間內走動,即時獲得文物解說動畫和空間路線引導動畫的AR服務。本研究首先整理分析博物館5G應用的未來場景為何,其後以個案研究法,探討故宮此一服務之開發及服務歷程。最後則總結此一專案之特徵及優缺點,並對其他博物館未來在開發5G或AI應用專案上提出建議。
With recent expansion in the applications of 5G technology, museums have begun to think about how to adopt the learning and predictive capabilities of AI and the high-speed and low-latency characteristics of 5G to improve cultural relics guide services. As such, the National Palace Museum recently launched its Elegant Encounters guide service, which incorporates Microsoft Hololens smart glasses. Google Tensorflow for machine learning is used to identify the characteristics of the museum’s cultural relics and exhibition halls and mainframe to determine the characteristics and locations of cultural relics seen by visitors. Subsequently, interpretation results, rendered animations, and other materials are transmitted to the smart glasses via 5G signals. Visitors wearing these smart glasses can walk freely through the museum and view its cultural relics and exhibition halls, obtaining interpretive animations of the cultural relics, as well as real-time AR space and route information. The purposes of this study are to analyze future scenarios of 5G applications in museums and to apply the case study method to discuss the development and history of the Elegant Encounters guide service provided by the National Palace Museum. Finally, the characteristics, advantages, and disadvantages of this project are summarized and suggestions for museums seeking to develop 5G or AI applications are provided.