適用於人機介面之單一攝影機手勢辨識技術

Abstract

在本篇論文中，我們提出了一個僅利用一台可見光攝影機便可遙控操作人機介面之手勢辨識技術。此系統主要是由一台投影機及一台安裝在大型面板左側的可見光攝影機組成，我們希望此系統能讓操作區域不再侷限於面板之前，以達到可以遙控操作的目的。在此條件下，背景可能是非常雜亂的，我們主要探討的議題包括如何在此情況下快速地找到手的位置，以及辨識使用者的手勢，以取代滑鼠的使用。在我們的演算法中，我們會先利用簡單的校正過程來取得手的初始位置，以及影像座標系和投影螢幕坐標的相對位移關係，接著，我們利用追縱演算法來取得手的位置，並使用手部偵測來輔助追縱演算法的判斷，使這兩種演算法能夠發揮相輔相成的作用。此外，我們並使用手勢辨識來判斷目前的手勢為何。最後，我們將影像中手的位置投影回投影幕上，這樣即可利用手的移動來控制游標的移動並讓系統做出對應的手勢反應。

In this thesis, we propose a novel hand gesture recognition technique for a remote-control human computer interface (HCI) using a single visible-light camera. The system is mainly composed of an image projector and a camera installed on the left side of the panel. We wish to develop a human computer interface that is not limited to finger touching on the board, but allows remotely controlling the system. In this system, we develop our human computer interface in order to find the hand location and to recognize human hand gesture in cluttered backgrounds in real time. In our approach, we first use a simple calibration process to get the initial position of the hand and the relation between image coordinates and the projected board coordinates. After that, we develop a tracking algorithm to get the position of hand, with the help of a hand detection algorithm. Next, we use a gesture recognition technique to recognize the current gesture. We also integrate the detection algorithm with the tracking algorithm to boost the performance. Finally, by projecting the detected hand position onto the projected screen, we can replace the use of mouse and use hand gesture to control the system.