Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/6684
標題: 基於電腦視覺之即時人體分割和三維虛擬人體模型建立
Vision-based Real-Time Human Body Segmentation And 3D Virtual Human Model Construction
作者: 杜偉勤
Du, Wei-Chin
關鍵字: Computer Vision;電腦視覺
出版社: 電機工程學系所
引用: [1] T. Noma, I. Oishi, H. Futsuhara, H. Baba, T. Ohashi, and T. Ejima, “Motion generator approach to translating human motion from video to animation,” Proc. 7th Pacific Conf. Computer Graphics and Applications, pp. 50-58, Oct. 1999. [2] K. Watanabe and M. Hokari, “Kinematical analysis and measurement of sports form,” IEEE Trans. Syst., Man, and Cyber., Part A: Systems and Humans, vol. 36, no. 3, pp. 549- 557, 2006. [3] Xbox- Kinect. http://www.xbox.com/en-US/kinect [4] http://www.3ds.com/products/3dvia/3dvia-virtools/ [5] I. Haritaoglu, D. Harwood and L. S. Davis, “ real-time surveillance of people and their activities,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 809 - 830, Aug. 2000. [6] S. Y. Chen, S. Y. Ma, and L. G. Chen, “Efficient moving object segmentation algorithm using background registration technique,” IEEE Trans. Circuits and Systems for Video Technique, vol. 12, no. 7, pp. 577-586, July 2002. [7] C. Kim, J. Cho, and Y. Lee, “The relational properties among results of background subtraction”, Proc. of Int. Conf. on Advanced Communication Technology, vol. 3, pp. 1887-1890, 2008. [8] C. F. Juang, C. M. Chang, J. R. Wu, and D. M. Lee, “Computer vision-based human body segmentation and posture estimation,” IEEE Trans. Syst., Man, and Cyber., Part A: Systems and Humans, vol. 39, no. 1, pp. 119-133, Jan. 2009. [9] H.D. Cheng, X.H. Jiang, Y. Sun and J. Wang, “Color image segmentation: advances and prospects”, Pattern Recognition, vol. 34, pp. 2259-2281, 2001. [10] Q. Zhou and J.K. Aggarwal, “Tracking and classifying moving objects from video”, Proc. IEEE Int. Workshop Performance Evaluation of Tracking and Surveillance, pp. 52-59, Dec. 2001. [11] Razali M.T. and Adznan B.J., “Detection and classification of moving object for smart vision sensor,” Proc. Information and Communication Technologies Conf., vol. 1, pp. 733-737, 2006. [12] T. Horprasert, D. Harwood, and L.S. Davis, “A statistical approach for real-time robust background subtraction and shadow detection,” Proc. IEEE Int. Conf. Computer Vision, Frame-Rate Workshop, pp. 1-19, Greece, Sept. 1999. [13] D. Anderson, R. H. Luke, J. M. Keller, M. Skubic, M. J. Rantz, and M. A. Aud, “Modeling human activity from voxel person using fuzzy logic,” IEEE Trans. Fuzzy Systems, vol. 17, no. 1, pp. 39-49, Feb. 2009. [14] R. Rosales, M. Siddiqui, J. Alon, and S. Sclaroff, “Estimating 3D body pose using uncalibrated cameras,” Proc. of IEEE Computer Society Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 821 - 827, 2001. [15] I. Mikic, M. Trivedi, E. Hunter, and P. Cpsman, “Articulated body posture estimation from multi-camera voxel data,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 455 - 460, 2001. [16] T. Matsuyama, X. Wu, T. Takai, and S. Nobuhara, “Real-time dynamic 3D object shape reconstruction and high-fidelity texture mapping for 3-D video,” IEEE Trans. Circuits and Systems for Video Technology, vol. 14, no. 3, pp. 357-369, March 2004. [17] K. Takahashi, Y. Nagasawa, and M. Hashimoto, “Remarks on 3D human posture estimation system using simple multi-camera system”, Proc. IEEE Int. Conf. Syst., Man, and Cyber., pp. 1962-1967, 2006. [18] T. C. Chen, Vision-Based Real-Time 3D Human Posture Significant Points Estimation, Master Thesis, National Chung-Hsing University, Taiwan, July 2009. [19] C. F. Juang, C. M. Chang, J. R. Wu, and D. M. Lee, “Computer vision-based human body segmentation and posture estimation,” IEEE Trans. Syst., Man, and Cyber., Part A: Systems and Humans, vol. 39, no. 1, pp. 119-133, Jan. 2009. [20] C. K. Chui and G. Chen, Kalman Filtering with Real-Time Applications. Springer Series in Information Sciences. Vol. 17 (4th ed.). New York: Springer. 2009. [21] V. Vapnik, The Nature of Statistical Learning Theory, Springer, New York, 1995. [22] W. N. Martin and J. K. Aggarwal, “Volumetric description of objects from multiple views”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 2, pp. 150-158, 1987. [23] M. Potmesil, “Generating octree models of 3D objects from their silhouette in a sequence of images”, Computer Vision, Graphics, and Image Processing, vol. 40, pp. 1-29, 1987. [24] P. Strivasan, P. Lang, and S. Hackwood, “Computational geometric methods in volumetric intersections for 3D reconstruction”, Patter Recognition, vol. 28, no. 8, pp. 843-857, 1990. [25] S. Iwasawa, K. Ebihara, J. Ohya, and S. Morishima, “Real-time estimation of human body posture from monocular thermal images,” Proc. of IEEE Computer Society Conf. Computer Vision and Pattern Recognition, pp. 15-20, 1997
摘要: 
本論文首先提出一種即時三維人體特徵點估測方法然後利用特徵點來建立虛擬三維人物模型。尋找三維人體特徵點包含頭、身體的中心點、雙腳尖末端、雙手末端點以及手肘和膝蓋。在此藉由兩部攝影機同時擷取兩組連續影像。考慮陰影影響,提出利用線性向量支持機從背景分割出移動物體。從兩張各別影像,利用人體輪廓的凸點和人體幾何的特性,去實現二維人體特徵點的估測。利用特徵點體積交集法(SPVI)建構出三維人體的特徵點,再利用Kalman filter演算法進行特徵點的預估與修正。再將得到的三維座標點資訊傳入虛擬三維人物模型。在本論文根據人體結構的幾何限制去預估三維虛擬人體模型的旋轉角度。實驗結果顯示,提出基於向量支持機人體分割方法,相較於其他不同色彩模式的影像切割方法,有較好的切割結果。本論文也建構一個即時三維虛擬模型系統,來驗證提出的方法是可行的。此系統也具有娛樂性可顯示出三維之間互動與遊戲的動作。

This thesis first proposes a real-time three-dimensional (3D) human body significant-point estimation method and then constructs a virtual 3D human model using the significant points. The located 3D significant body points include the head, center of the body, tips of the feet, tips of the hands, the elbows and the knees. This thesis uses two cameras to capture two sets of image sequences at the same time. A linear support vector machine (SVM)-based segmentation method is proposed to segment moving objet from background with the consideration of shadow influence. Two-dimensional (2D) significant-point estimation is performed on each of the two images by using body-contour convex points and body geometrical characteristics. A Significant Point Volume Intersection (SPVI) method is used to estimate the 3D locations of the significant body points and the estimated locations are further corrected using Kalman filter algorithm. Three-dimensional locations of the significant points are sent to the Virtools software to reconstruct a virtual 3D human model. This thesis estimates orientation of the 3D virtual model according to the geometrical limitation of body structure. Experimental results show that the proposed SVM-based human body segmentation outperforms other segmentation methods used for comparison. This thesis sets up a real-time 3D virtual model construction system to verify the effectiveness of the proposed approach. The system is also applied to interactive 3D and exercise-with-me games to show its potential in entertainments.
URI: http://hdl.handle.net/11455/6684
其他識別: U0005-1708201122152500
Appears in Collections:電機工程學系所

Show full item record
 

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.