遙控條列式選單之手勢辨識系統

A Gesture Recognition System for Remote Control with List Menu

張譽馨(Yu-Hsin Chang)

指導教授 ： 洪一平

共同指導教授 ： 李明穗(Ming-Sui Lee)

國立臺灣大學/電機資訊學院/資訊工程學研究所/碩士(2007年)

https://doi.org/10.6342/NTU.2007.00095

摘要

近年來遠端遙控數位媒體內容已在互動式遊戲及數位家庭應用成為重要課題。在本篇論文中，我們提出一種新的使用者介面，讓使用者在空中用單手做畫圓的動作，就可以控制呈現在遠方之顯示器的條列式選單，近而達到控制數位內容的目的。在此設計中，使用者無須使用任何實體裝置，而是用一些簡單的動作就可以達成所有的工作。根據此原則，我們發展出一套基於視覺方法而偵測使用者手掌位置和其移動軌跡的系統。我們使用場景中物體的深度、移動情形與形狀來判斷使用者手掌的位置，接著再利用粒子濾波器持續追蹤使用者的手掌。接著我們再分析手掌的軌跡來決定是否有一些合法的動作發生，且此系統能夠對於不同的手勢動作即時回應。經過實驗證實，本篇論文所提出的方法能夠在有許多干擾的環境中運作良好。

關鍵字

遠端控制 ； 選擇方法 ； 人機介面 ； 手勢辨識

並列摘要

Recent years remote control of media content has become an important issue in interactive games or digital home application. In this thesis we introduce a new type of user interface which allows user to control the media via a list menu shown on a distant display by simply drawing circles in the air with one hand. Instead of using a physical device such as a hand-held remote control, user simply performs some predefined motion to accomplish all tasks. Based on this design, we develop a vision-based system to detect user's palm and its motion trajectory. Depth, motion and shape are adopted to estimate the location of a palm before a particle filter is used to track the target continuously. Then, we analyze the trajectory of the palm to determine if there is a legal motion occurs. This system can respond to user’s gesture in real-time. Experimental results confirm that it is quite robust to interferences existed in the environment.

並列關鍵字

Remote control ； Selection technique ； Human computer interaction ； Gesture recognition

參考文獻

[2] A. Azarbayejani and A. Pentland, “Real-time self-calibrating stereo person tracking using 3-d shape estimation from blob features,” Pattern Recognition, Proceedings of the 13th International Conference on, vol. 3, pp. 627–632, 1996.

[4] D. Comaniciu, V. Ramesh, and P. Meer, “Real-time tracking of non-rigid objects using mean shift,” Computer Vision and Pattern Recognition, Proceedings. IEEE Conference, vol. 2, pp. 142–149, 2000.

[7] E. W. Huang and L. C. Fu, “Real-time arm tracking system using example-based matching and local optimization,” IEEE International Conference on Systems, Man and Cybernetics, 2006.

[9] I. Laptev and T. Lindeberg, “Tracking of multi-state hand models using particle filtering and a hierarchy of multi-scale image features,” Proceedings of the Third

[10] R. Lienhart and J. Maydt, “An extended set of haar-like features for rapid object detection,” IEEE International Conference on Image Processing, vol. 1, pp. 900–903, 2002.