臺灣博碩士論文加值系統

智慧生活，意指將各領域發展之技術與生活做結合，使生活各方面更為便利。
身體語言(Body Language)是人類互動時最自然的表達方式，故在人機互動領域裡，透過影像辨識技術進行人體動作捕捉或是手勢識別，與系統之間進行溝通，亦是主要的研究方向。身體語言包含臉部表情、肢體動作、手勢…等，其中人類最常使用的便是手勢，將手勢辨識功能應用於人機互動之中一直是大家感興趣的主題。論文中運用深度體感器進行手部辨識系統開發，藉由手勢直接與電腦進行溝通，以較自然且直覺的方式與系統進行互動。
本論文主要研究如何利用簡單手勢便能有效地與系統產生互動。透過運用Kinect提供的深度資訊以及PrimeSense NITE的SDK，在空間中追蹤人體手部位置，記錄並計算手部在空間中的運動狀態，包括移動的方向及速度；同時透過影像處理技術取得手掌中心位置，紀錄單位時間內手掌面積的變化狀況，搭配人機互動時的使用慣性，決策手掌狀態，本系統中手掌狀態分為張開與閉合兩狀態；最後結合手部在空間中的運動狀態以及手掌狀態，對照事前定義好的行為對照表，將有效的手部行為轉成指令傳達給系統，達到用手勢便能與系統進行互動的目的。

Intelligent life is a kind of living style that means combining technologies of all fields and sciences, making our living more convenient and intelligent.
In the field of human computer interaction, interacts with computers through human body movement or hand gestures recognized by various image processing techniques is also an important direction of all research and discussions, since body language is the most natural expression while people communicate with each other.
In this paper, we develop a hand gesture recognition system using Microsoft Kinect. Through accessing the depth information provided by Kinect and using PrimeSense NITE API, we can easily track user’s hand and analyze the meaning of the movement in real time. In the meanwhile, we use image processing techniques to analyze the status of user’s hand, which is defined to be “hand-open” or “hand-close”. Finally, through mixing the meaning of movement and hand status, we defined a set of gesture instructions with the spirit of natural human interaction.

摘　要 I
ABSTRACT II
誌　謝 III
目　錄 IV
表目錄 VI
圖目錄 VII
第一章　緒論 1
1.1 研究動機 1
1.2 研究目的 3
1.3 研究範圍與限制 4
1.4 論文架構 5
第二章　相關研究與文獻探討 6
2.1 人機介面與人機互動 6
2.2 電視的操作型態介紹 8
2.3 手勢辨識 12
2.4 Kinect體感攝影機 13
2.5 Kinect驅動軟體 15
2.5.1 Microsoft Kinect SDK for Windows 15
2.5.2 OpenNI 16
2.5.3 歸納整合 18
2.6 Kinect手部偵測與辨識 19
第三章　系統架構 22
3.1 手勢辨識系統概述 22
3.2 手勢辨識系統架構流程 23
第四章　空間中手部行為辨識 25
4.1 手部位置偵測與更新 25
4.2 各偵測器之介紹與測試 27
4.3 行為辨識系統設計 28
4.3.1 偵測器之搭配與組合 28
4.3.2 進行空間中手部行為辨識 29
第五章　手掌狀態辨識 30
5.1 手掌區塊擷取與正規化 31
5.2 特徵擷取 33
5.2.1 手掌特徵描述 33
5.2.2 手掌掌心與最大內切圓半徑之獲取 35
5.2.3 手掌外接圓半徑之獲取 36
5.3 進行手掌狀態辨識 37
第六章　指令集與人機互動之設計與介紹 39
6.1 指令集 40
6.2 人機介面與互動 42
第七章　實驗結果 47
7.1 實驗方法與環境 47
7.2 實驗結果與探討 49
第八章　結論與未來展望 52
8.1 結論 52
8.2 未來展望 52
參考文獻 53

[1]Juan Pablo Wachs, Mathias Kolsch, Helman Stern, and Yael Edan, “Vision-Based Hand-Gesture Applications,” Communications of the ACM, Vol.54, No.2, pp. 60-71, February 2011
[2]User Interface, online available at: http://zh.wikipedia.org/wiki/用戶介面
[3]Wii, online available at: http://www.nintendo.com/wii
[4]Play Station, online available at: http://asia.playstation.com/tw/cht
[5]Microsoft Kinect, online available at: http://www.xbox.com/zh-TW/kinect
[6]LG電子, online: available at: http://www.lg.com/tw
[7]廣寰科技, online: available at: http://tw.kworld-global.com/main/
[8]新鎧科技, online: available at: http://www.krctech.com.tw/index1.php
[9]Samsung Electronics., “Samsung Smart TV ES8000,” online: available at: http://www.samsung.com/tw/consumer/televisions/televisions/smart-tv/UA55ES8000MXZW
[10]Pragati Garg, Naveen Aggarwal and Sanjeev Sofat ,“Vision Based Hand Gesture Recognition”, World Academy of Science, Engineering and Technology 49 2009.
[11]PrimeSense Inc., online available at: http://www.primesense.com
[12]身體就是控制器，微軟Kinect是怎麼做到的？ online available at: http://www.techbang.com.tw/posts/2936-get-to-know-how-it-works-kinect
[13]OpenNI, "OpenNI UserGuide", online available at: http://OpenNI.org
[14]SensorKinect, online available at: https://github.com/avin2/SensorKinect/
[15]PrimeSense Inc., “NITE 1.3 Controls Programmer’s Guide”
[16]Heresy’s Space, online available at: http://kheresy.wordpress.com/
[17]Guan-Feng He, Sun-Kyung Kang, Sung-Tae Jung , Won-Chang Song, “Real-time Gesture Recognition using 3D Depth Camera,” Software Engineering and Service Science(ICSESS), IEEE 2nd International Conference, July 2011, pp. 187-190
[18]Cheoljong Yang, Yujeong Jang, Jounghoon Beh, David Han, Hanseok KO, “Gesture Recognition using Depth-based Hand Tracking for Contactless Controller Application,” Consumer Electronics(ICCE), IEEE International Conference, Jan. 2012, pp. 297-298
[19]L. Rabiner, “A tutorial on hidden Markov models and selected applications in speech recognition,” Proc. of the IEEE, vol.77, no. 2, 1989, pp. 257-289
[20]C. Yang, J. Yoon, J. Beh, H. Ko, “Modeling for Gesture Set Design toward Realizing Effective Human-Vehicle Interface,” Computers, Networks, Systems, & Industrial Eng., SCI, vol.365, 2011, pp.171-180.
[21]L. E. Baum. “An Inequality and Associated Maximization Technique in Statistical Estimation for Probabilistic Functions of Markov Processes.” Inequalities, vol. 3, 1972:1-8.
[22]Matthew Tang, “Recognizing Hand Gestures with Microsoft’s Kinect,” online: available at: http://www.stanford.edu/class/ee368/Hand_Gesture_Recognition.pdf, 2011
[23]M. J. Jones and J. M. Rehg. “Statistical Color Models with Application to Skin Detection.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999.
[24]H. Bay, T. Tuytelaars, L. Van Gool. “SURF: Speeded Up Robust Features,” Lecture Notes in Computer Science, 2008.
[25]Real Steel, online: available at: http://en.wikipedia.org/wiki/Real_Steel