智慧型機器人其應用廣泛，未來將是人類忠實及信賴的夥伴，也將是人們家庭生活、醫療健康、生活休閒與社會安全的好助手，隨著人類文明發展與個性化生活型態的改變，智慧型機器人將逐漸融入人們的生活中。在日常生活中，有著許許多多能使生活更為便利的機器，而能隨時跟隨著人們的機器人更是一種趨勢，只要機器能夠判斷出需要跟隨的目標，我們就可以不需要操控機器人而使機器人跟著使用者一起行動。 本系統即是使用即時的影像辨識和處理的前提下，設計出一台可以自動跟隨的自走車，設計此自走車共有四大部份：影像處理、距離感測、微控制處理、馬達控制。單一目標的追蹤是自動跟隨系統中最重要的一部分，本系統的追蹤演算法是結合了行人偵測、顏色直方圖的比對、區塊匹配法。當發生衣服顏色相近的情境時，我們透過Kalman Filter的預測器產生的結果找出哪個才是我們追蹤的目標以避免誤判的情形。而距離感測我們使用ZED鏡頭提供的SDK進行測距。最後將追蹤的結果傳回車上的微控制系統進行處理，經由其結果對馬達進行控制，並透過距離感測與目標保持一定的距離，使其成為一台能夠正確辨別目標物及跟隨的自動跟隨自走車。 ;In daily life, there are many machines that can make life more convenient. Robots that can follow people at any time has become more trend. As long as the robot can identify the targets that need to be followed, the robot can be operated from the user without having to manipulate the robot. The design of this Human Following Mobile Robot has four parts: image processing, distance sensing, micro-control processing, and motor control. The ability to detect and track specific people is considered a key prerequisite for serving mobile robots. This paper presents a tracker using a binocular camera capable of tracking a specific human in both indoor and outdoor environments. The proposed tracker detects the target with the combination of human detection, color histogram, and block matching algorithm (BMA). When the color of the object is similar, the position of the object is determined by the predictor of the Kalman filter. Finally, the mobile robot is controlled based on the depth information of the target object.
