身份辨識其應用場景非常廣泛，如：互動式機器人，目前市面上有許多相關的設備與產品可協助執行身分辨識，例如：無線射頻辨識(RFID)、虹膜辨識。但這些辨識大部分都是使用單一的設備，因此在應用在現實環境時，總會遇到諸多限制；例如：虹膜辨識和指紋辨識需要短距離或接觸操作。在本論文中，我們運用三種感測器進行資料融合，分別為攝影機、慣性傳感器和電子證件。雖然使用RGB視覺攝影機協助取得場景的視覺資料，但是本論文並沒有使用到人臉辨識的技術，這樣的系統一來有助於解決人臉辨識所造成的隱私問題，二來不要求所使用的攝影機必須具備高解析度且不需要預先替場景中的人員建立其人臉生物資訊，最後是融合多感測器可校正慣性感測器的定位誤差問題且可有效降低影像遮蔽所造成的負面效應。在本文的系統中，我們提出二個特徵融合算法，進行感測資料融合，同時此演算法除了考慮受試者的運動軌跡，更加入受試者運動過程的時間特徵；算法的執行不需繁瑣的數據標籤和模型訓練。實驗數據顯示，我們的系統具有高達95%以上的辨識率。我們實現並實現一原型系統來驗證我們的方法與可行性。

Person identification is always one of the most popular technology applications. There are many devices and products have been sold to do person identification, such as radio frequency identification (RFID), face recognition, and iris recognition. However, most of identifications approaches, which are all based on single technology, have limitations when applying in the real environment. For example, they are strongly restricted by specific scenarios and spatial condition of places. In this paper, we propose a data fusion method which combines three kinds of sensors, a camera, inertial sensors and compasses. The camera can capture the video of the whole space, with the video and AI algorithms, the record objects’ positions and trajectories can be calculated and identified. Each user is equipped with a wearable device, and the wearable device can capture the user’s motion without any space constraints. The video is not used for face or iris recognition so video quality is not concern here and privacy violation problem is prevented. In this paper, we propose a feature fusion algorithm, which not only considers the motion trajectory of the subject, but also the time characteristics. By the proposed methods, user and wearable devices are paired, so each user can be identified via his or her wearable device, which owns a unique id. According to experiments, our system reaches over 95% recognition rate. A prototype implementation is completed demonstrated to verify the feasibility of our proposed approach.