基於立體視覺的3D影像定位｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	林姿吟 Tzu-yin Lin
論文名稱：	基於立體視覺的3D影像定位 3D Image Position Based on Stereo Vision
指導教授：	高維文 Wei-wen Kao
口試委員:	張淑淨 none 陳亮光 none
學位類別：	碩士 Master
系所名稱：	工程學院 - 機械工程系 Department of Mechanical Engineering
論文出版年：	2011
畢業學年度：	99
語文別：	中文
論文頁數：	91
中文關鍵詞：	極線幾何、膚色偵測
外文關鍵詞：	epipolar geometry, color detection
相關次數：	點閱：171 下載：9
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

現今的社會上，關於定位方面，有許多的理論和研究，像是使用GPS 、紅外線、雷射等。但對於這類型的感測器，並非我們生活周遭唾手可得，而且每個人都可以上手的儀器。相較下，影像與我們的生活密不可分，不論是手機、數位相機、單眼相機、webcam 等，是我們生活中不可或缺的物品。
本論文利用影像投影幾何的方法，以雙眼網路相機做為感測器，模擬人類視覺系統，針對人物的膚色特徵做追蹤目標。首先利背景相減法，將背景中的雜訊和可能的干擾消除。然後利用正規化 RGB 分析膚色範圍後，找出其影像的輪廓，以橢圓比對的方式找出人臉所在的區域，並進一步將其餘膚色的部分，認定為人手膚色的部分。將人手的部分，使用雙眼視覺重疊視野的影像平面，將其二維座標，透過幾何關係和參數矩陣，計算出目標物的三維座標，即可知其深度資訊，以達到定位的目標。

There are many theories of positioning, such as GPS, infrared, laser, etc. However, the type of positioning sensor is not only easy to use, but also expensive. In comparison with image positioning, image positioning is more popular for us.
Now many cell phones can even take pictures like a camera, we can take many pictures anywhere you like.
In this paper, we use projective geometry of two webcams of PC to simulate human visual mechanisms, and tracking based on the analysis of color characteristics. First, we use background subtraction to reduce the influence of background pixels and improve the detection accuracy. Second, identifying the contours of human color, and we can use the contours to analysis where is the region of hand. Fnally, in order to calculate the depths of characteristics, we use camera parameters and epipolar geometry to calculate the three-dimensional coordinates.

目錄

摘要............................................. I
Abstract......................................... II
致謝............................................ III
目錄............................................. IV
圖表索引...................................... IV

第一章  緒論......................................1
1 前言........................................1
2 研究動機....................................2
3 研究目標....................... ............3
4 文獻回顧....................................3
4.1 影像追蹤..............................4
4.2 人臉辨識..............................5
4.3 立體視覺..............................7
4.3 估測基礎矩陣..........................9
5 論文架構...................................10

第二章  膚色檢測.................................12
1 光線補償....................................13
2 色彩空間轉換................................13
2.1 RGB色彩空間...........................13
2.2 正規化 RGB............................14
2.3 YC_r C_b  色彩空間.........................15
2.4 HSV 色彩空間...........................15
3 膚色檢測.....................................17
4 膚色過濾.....................................20
4.1 形態學處理.............................20

第三章  手部偵測.................................22
1 背景相減法...................................23
1.1 背景相減法的運算.......................23
2 邊緣檢測.....................................24
2.1 canny 演算法...........................25
3 人手偵測.....................................31
3.1 橢圓人頭判定...........................31
3.2 人手搜尋結果...........................35

第四章  相機幾何.................................36
1 攝影機校正原理...............................37
1.1內部參數...............................38
1.2 外部參數...............................40
2 相機校正.....................................42
3 三維幾何轉換關係.............................43

第五章  雙眼視覺原理.............................46
1 立體視像.....................................46
2 極線幾何與基礎矩陣...........................48
2.1 極線幾何限制...........................49
3 基礎矩陣(Fundamental Matrix) ................51
3.1 基本矩陣定義...........................51
3.2 八點演算法.............................53
3.3 正規化八點演算法.......................56
3.4 驗證基本矩陣正確性.....................58
4 必要矩陣（Essential Matrix）.................59
4.1 正規化座標.............................59
4.2 必要矩陣的限制.........................60
4.3 必要矩陣的特性.........................61
5 雙眼測距.....................................62
5.1 雙眼視覺求出三維座標...................62
5.2 相機擺放位置角.........................65

第六章  實驗結果.................................67
1 人手偵測.....................................67
2 雙眼視覺校正.................................69
3 三維定位結果.................................74

第七章  結論與未來展望...........................76
1 成果討論.....................................76
2 未來展望.....................................77

參考文獻.........................................78

                                

參考文獻
[1] R. Brunelli and T. Poggio, “Face recognition: Features versus templates”IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15,pp.1042-1052, 1993.
[2] T. Kanade, “Picture Processing by Computer Complex and Recognition of Human Faces,” PhD thesis, Kyoto University, 1973.
[3] Ara V. Nefian and Monson H. Hayes III, “Hidden Markov Models for Face Recognition,” Center for Signal and Image Processing School of Electrical and Computer Engineering Georgia Institute of Technology, Atlanta,1998.
[4] M. Turk and A. Pentland, “Eigenfaces for Recognition,” Jour. of Cognitive Neuroscience, vol. 3, pp.71-86, 1991
[5] Hua Yu, Jie Yang, “A Direct lda algorithm for high dimensional data with application to face recognition”, Pattern Recognition, pp.2067-2070, vol.34, 2001.
[6] Lawrence, S., Giles, C.L., Ah Chung Tsoi, Computer Vision and Pattern Recognition, 1996. Proceedings CVPR '96, 1996 IEEE Computer Society Conference, pp.217 -222, Jun 1996.
[7] Cover, T. M. and Thomas, J. A., Elements of Information Theory, John Willey and Sons, 1991.
[8] Malcolm Lomer，“滿足行人定位和GPS 手機需求混合式定位技術出線”，新通訊8 月號78 期，2007。
[9] M. Agrawal, K. Konolige, and L. Iocchi, “Real-time detection of independent motion using stereo,＂ IEEE Workshop on Motion and Video Computing, pp. 207-214, vol. 2, no. 2, 2005.
[10] Z. Zhang, “Determining the Epipolar Geometry and its Uncertainty: A Reveiw＂, Technical Report RR-2927, INRIA, 1996.
[11] M. Pollefeys, Self-Calibration and Metric 3D Reconstruction from Uncalibrated Image Sequences, Ph.D. thesis, ESATPSI, K. U. Leuven, 1999.
[12] O. Faugeras and Q.-T. Luong, “The fundamental matrix : Theory Algorithms, and Stability Analysis＂, Int＇l J. Computer Vision, 17, pp. 43-45, 1996.
[13] H.C. Longuet-Higgins, “A Computer Algorithm for Reconstruction A Scene from Two Projections＂, Nature, 293, pp. 133-135, 1981
[14] R. Hartley, “ In Defense of The Eight-Points Algorithm,＂ IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No. 6, pp. 580-593, June 1997.
[15] O. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint. MIT Press, 1993.
[16] T. S. Huang and O. Faugeras, “Some Properties of The E Matrix in Two-View Motion Estimation＂, IEEE Trans. Pattern Analysis and Machine Intelligence, pp. 1310-1312, 1989.
[17] Rein-Lien Hsu, Anil K Jain and Mohamed Abdel-Mottaleb, “Face Detection In Color Images,” IEEE Transactions On Pattern Analysis And Machine Intelligence, Vol.24,No.5, May 2002.
[18] Soriano, M., B. Martinkauppi, S. Huovinen and M. Laaksonen, “Skin color modeling under varying illumination conditions using the skin locus for selecting training pixels, ” Proceedings of IEEE Nordic Signal Processing Symposium, Kolmården, Sweden,2003.
[19] http://sourceforge.net/projects/opencvlibrary/
[20] R. Y. TSAI, “A Versatile Camera Calibration Technique for High-Accuracy 3D Machine Vision Metrology Using Off-the-shelf TV Cameras and Lenses,” IEEE Journal of Robotics and Automation, Volume 3, Issue 4, Page(s):323 – 344, Aug 1987.
[21] Stan Birchfield, “Elliptical Head Tracking Using Intensity Gradients and Color Histograms,” Computer Science Department Stanford University.
[22] Tsai, R.Y., “An efficient and accurate camera calibration technique for 3D machine vision,” Proc. International Conference on Computer Vision an Pattern Recognition, 1986, pp. 364-374.
[23] Zhengyou Zhang, “A Flexible New Technique for Camera Calibration,” December 2, 1998.
[24] J. H. Jean, T. P. Wu, J. H. Lai, and Y. C. Huang, “A Visual Servo System for Object Tracking Applications of Mobile Robots Based on Shape Features,” Proceedings of 2005 CACS Automatic Control Conference Tainan, Taiwan, Nov 18-19, 2005.
[25] A. Lipton, H. Fujiyoshi and R. Patil, “Moving Target Classification and Tracking from Real-time Video, ” In Proc. IEEE Workshop on Applications of Computer Vision, Princeton, NJ, 1998.
[26] K. P. Horn, B. G. Schunck, “Determining Optical Flow,” Artifical Intelligence, Vo1.17, pp. 185-203, 1981.
[27] 王科翔,Multiple Human Faces Detection and Identification System,國立成功大學工程科學系碩士論文,台南,2005
[28] 林怡政,Binocular Vision Based Human Head Tracking,國立台灣科技大學機械工程系碩士論文,台北,2008
[29] 任紹棟,A Mobile Robot with Stereo vision Range Estimation,國立台灣科技大學電機工程系碩士論文,台北,2007
[30] 李嘉欣，“多視點輔助定位系統”，國立台灣科技大學機械工程系碩士論文，台北，2007。

簡易檢索 / 詳目顯示

相關論文