跳到主要內容

臺灣博碩士論文加值系統

(18.205.192.201) 您好!臺灣時間:2021/08/05 02:13
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:鄭浩恩
研究生(外文):Hao-EnCheng
論文名稱:應用OpenGL於居家服務機器人之抗視角變換SIFT即時影像處理法之研究
論文名稱(外文):OpenGL Based Affine SIFT Real-time Image Processing Method for Home Service Robots
指導教授:李祖聖
指導教授(外文):Tzuu-Hseng Li
學位類別:碩士
校院名稱:國立成功大學
系所名稱:電機工程學系碩博士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:英文
論文頁數:84
中文關鍵詞:GPUOpenGL物件辨識即時影像處理
外文關鍵詞:GPUOpenGLObject recognitionReal-time image processing
相關次數:
  • 被引用被引用:0
  • 點閱點閱:298
  • 評分評分:
  • 下載下載:21
  • 收藏至我的研究室書目清單書目收藏:2
本論文係研究應用OpenGL (Open Graphics Library) 於居家服務機器人之抗視角變換SIFT (Scale-Invariant Feature Transform) 即時影像處理法。首先本論文提出一個六步驟的資料庫建立方法,SIFT演算法在偵測這個資料庫中的圖片特徵時,錯誤特徵被偵測之情況可降低。也可以增加手動建立資料庫之時間。本論文的第二部份介紹使用Affine-SIFT演算法完成之物件辨識系統,並加入OpenGL與SiftGPU平行化技術,OpenGL平行化了Affine投影的運算過程,SiftGPU則平行化了SIFT演算法,最終完成具有能力即時運算之影像辨識系統。本論文的第三部份描述如何完成人臉辨識系統,該系統結合了Haar-Like人臉偵測、特徵臉辨識與骨架偵測。使用骨架偵測與Haar-Like人臉偵測技術,排除偵測錯誤之情況,加入五官偵測,校正人臉辨識因攝影機視角度造成之傾斜,提高人臉辨識之準確度。本論文第四部份描述OpenGL完成的人機介面,該介面整合各種感測器資訊,用立體的方式呈現在人機介面上,使操作者可以快速得知觀測資訊。最後,將本論文提出的影像辨識系統應用於居家服務型機器人,並透過實驗結果與2012 RoboCup@Home日本公開賽的比賽成果證明本系統之可行性與強健性。
This thesis mainly discusses the OpenGL (Open Graphics Library) based affine SIFT (Scale-Invariant Feature Transform) real-time image processing method for home service robots. Firstly, a six-step method is proposed to create image database. When SIFT algorithm is adopted to detect features with this database, the rate of error features is reduced. Integration of the six-step method and SIFT can significantly decrease time for setting up the database. Secondly, the object recognition vision system is built up by parallel Affine-SIFT (ASIFT) algorithm, where OpenGL reduces the calculation time of affine projection and SiftGPU (Graphics Processing Unit) accomplishes the real-time operation speed of SIFT. Thirdly, the human recognition vision system is established by combining face detection of Haar-Like features method, the face recognition of Eigenfaces method and human skeleton detection. Integration of human skeleton and face detection lowers the false rate of facial detection. Adding facial organs detection augments the identification rate of face recognition. Furthermore, a user friendly human-computer interface with OpenGL is constructed and described. Operators can easily obtain the information from the interface such as dimensional image of home environment, values of sensors, and the recognition result of vision system. Finally, both the experimental results in the laboratory and competition consequents of 2012 Robocup@home Japan Open demonstrate the validity, effectiveness, and robustness of the proposed real-time vision system on our home service robot.
Abstract Ⅰ
Acknowledgement Ⅲ
Contents Ⅳ
List of Figures Ⅵ
List of Tables XI

Chapter 1. Introduction 1
1.1 Motivation 1
1.2 Software and Hardware 2
Chapter 2. The Construction of Vision System Database 6
2.1 Introduction 6
2.2 The Construction of Object Database 6
2.2.1 ROI Analysis 9
2.2.2 Capture ROI 11
2.2.3 Inpainting 14
2.3 The Construction of Facial Database 15
2.4 Summary 16
Chapter 3. Design of Object Recognition Vision System 17
3.1 Introduction 17
3.2 Affine SIFT 18
3.2.1 Affine Projection 21
3.2.2 SIFT (Scale-Invariant Feature Transform) 24
3.3 OpenGL Based Affine Projection 33
3.4 GPU Based SIFT 40
3.5 Experimental Results 44
3.6 Summary 46
Chapter 4. Design of Facial Recognition Vision System 48
4.1 Introduction 48
4.2 Facial Analysis 49
4.2.1 Facial Features Detection 51
4.2.2 Facial Normalization 55
4.3 Eigenfaces based Face Recognition 58
4.4 Experimental Results 62
4.5 Summary 64
Chapter 5. Design of Human-Computer Interface 65
5.1 Introduction 65
5.2 System Architecture of Human-Computer Interface 66
5.3 Construct 3D Environment Based on OpenGL 67
5.3.1 Visualization of Environment 70
5.3.2 Walk into environment 73
5.4 Summary 77
Chapter 6. Conclusion and Future Work 78
6.1 Conclusion 78
6.2 Future Work 82
References 83

[1] D. G. Lowe, “Distinctive image features from scale-invariant Keypoints, International Journal of Computer Vision, Vol. 60, No. 2, pp. 91-110, 2004.
[2] G. Yu and J.M. Morel, “A fully affine invariant image comparison method, in Proc. of the IEEE Int’l Conf. Acoustics, Speech and Signal Processing, pp. 1597-1600, 2009.
[3] C. Wu, “SiftGPU: A GPU implementation of scale invariant feature transform (SIFT), http://cs.unc.edu/ ccwu/siftgpu
[4] Geforce310M: http://www.nvidia.com.tw/object/product_geforce_310m_tw.html
[5] Kinect: http://www.xbox.com/zh-tw/kinect
[6] Kinect for Windows SDK: http://www.microsoft.com/en-us/kinectforwindows/
[7] Kinect for Windows Sensor Components and Specifications: http://msdn.microsoft.com/en-us/library/jj131033
[8] H. Freeman and R. Shapira, “Determining the minimum-area encasing rectangle for an arbitrary closed curve, Communications of the ACM, Vol. 18, pp. 409-413, 1975.
[9] The minimum area enclosing rectangle for a convex polygon: http://cgm.cs.mcgill.ca/~orm/maer.html
[10] S. Pereira and T. Pun, “Robust template matching for affine resistant image watermarks, IEEE Trans. Image Processing, Vol. 9, No. 6, pp. 1123-1129, 2000.
[11] A. Telea, “An image inpainting technique based on the fast marching method, J. Graphics Tools, Vol. 9, No. 1, pp. 23-34, 2004.
[12] 2012 Robocup@home Japan Open: http://www.robocup.or.jp/
[13] Microsoft Speech Platform: http://msdn.microsoft.com/en-us/library/hh361572
[14] D.G. Lowe, “Object recognition from local scale-invariant features, in Proc. Seventh Int’l Conf. Computer Vision, pp. 1150- 1157, 1999.
[15] J. Morel and G. Yu, “ASIFT: A new framework for fully affine invariant image comparison, SIAM Journal on Imaging Sciences, Vol. 2, No. 2, 2009.
[16] G. Van de Wouwer, P. Scheunders, S. Livens, and D. Van Dyck, “Wavelet correlation signatures for color texture characterization, Pattern Recognition, Vol. 32, pp.443-451, 1999.
[17] M. Woo, J. Neider, and T. Davic, OpenGL programming guide. Addison-Wesley, second edition, 1996.
[18] Creating an OpenGL Window from Scratch: http://www.falloutsoftware.com/tutorials/gl/gl2.htm
[19] J. D. Owens, M. Houston, D. Luebke, S. Green, J. E. Stone, and J. C. Phillips, “GPU computing, Proceedings of the IEEE, Vol. 96, No. 5, pp. 879-899, 2008.
[20] About the OpenMP ARB and OpenMP.org: http://openmp.org/wp/about-openmp/
[21] Visual C++ Editions, Visual Studio 2010, Microsoft .NET Compact Framework Multi-threading Tips: http://msdn.microsoft.com/en-us/library/aa446540.aspx
[22] Intel® Core™ i7-3920XM Processor:
http://ark.intel.com/products/64887/Intel-Core-i7-3920XM-Processor-Extreme-Edition-(8M-Cache-up-to-3_80-GHz)
[23] GeForce GTX690 Specifications: http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-690/specifications
[24] P. Viola and M. Jones, “Robust real-time object detection, Intl. J. Computer Vision, Vol. 57, No. 1, pp. 137-154, 2001.
[25] Face Recognition: http://www.shervinemami.info/faceRecognition.html
[26] S. Martin, J. Suarez, and R. Orea, “GLSV: Graphics library stereo vision for OpenGL, Virtual Reality, Vol.13, No. 1, pp. 51-57, 2009.
[27] D. Maupu, M.H. Van Horn, S. Weeks and E. Bullitt, “3D Stereo Interactive Medical Visualization, IEEE Computer Graphics and Applications, Vol. 25, No. 5, pp. 67-71, 2005.
[28] NeHe Productions: http://nehe.gamedev.net/
[29] L. Bavoil, Rendering huge triangle meshes with OpenGL, OpenGL VBO Benchmarks, 2005.
[30] RoboCup@Home Rules and Regulations 2011

連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top