標題: 以RGB-D 攝影機為媒介之二維編輯系統
Using RGB-D Sensor as a Medium for a Two-Dimensional Editing System
作者: 陳心凱
黃世強
Chen, Hsin-Kai
Wong, Sai-Keung
多媒體工程研究所
關鍵字: 手勢辨識;形狀辨識;人機互動;RGB-D攝影機;hand gesture recognition;shape recognition;human and computer interaction;RGB-D sensor
公開日期: 2016
摘要: 本篇論文提出一個藉由手勢偵測與真實的簡單形狀物體來操作的二維編輯系統。我們有兩種方法可以跟場景中的虛擬物件做互動,其分別是1)藉由操作真實物件來控制虛擬場景中的物體,2)藉由手勢來下達對虛擬場景中物體的操作命令。我們的系統使用彩色及深度攝影機來擷取使用者的手以及物體的影像。我們提出了一個以輪廓為基底的手勢與物體辨識方法。實驗結果顯示我們的系統可以達到良好的辨識率。我們的系統可以輕易的操作一些基本的物件編輯命令如移動、放大縮小、旋轉、以及複製。我們也有做使用者測試來評量我們的系統。
This paper presents a two-dimensional editing system which is controlled by hand gestures and real objects of simple shape. There are two ways to interact with the virtual objects in the scene: 1) manipulating the real objects to control the virtual objects; and 2) using hand gestures as editing operations to the virtual objects. The system uses a RGB-D sensor to capture the color and depth images of the hands and real objects. We propose a contour-based algorithm to perform hand gesture and shape recognition. Experimental results indicate that our system achieves a good recognition rate. Our system can easily perform the basic editing operations to the virtual objects, such as ‘move’, ‘scale’, ‘rotate’, and ‘copy’. We also conducted a user study to evaluate our system.
URI: http://etd.lib.nctu.edu.tw/cdrfb3/record/nctu/#GT070356603
http://hdl.handle.net/11536/138752
Appears in Collections:Thesis