跳到主要內容

臺灣博碩士論文加值系統

(18.97.9.169) 您好!臺灣時間:2025/02/18 02:15
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

我願授權國圖
: 
twitterline
研究生:張家偉
研究生(外文):Chia-Wei Chang
論文名稱:基於混合模糊特徵與粒子濾波器之即時二維手部影像動作追蹤
論文名稱(外文):Real-Time Hand Motion Tracking in 2D Image by Mixture of Fuzzy Features and Particle Filter
指導教授:莊家峰
口試委員:呂俊鋒蘇武昌
口試日期:2017-07-18
學位類別:碩士
校院名稱:國立中興大學
系所名稱:電機工程學系所
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:2017
畢業學年度:105
語文別:英文
論文頁數:75
中文關鍵詞:手部追蹤粒子濾波器多重模糊特徵粒子遷移
外文關鍵詞:Hand trackingParticle filterMultiple fuzzy featuresParticle migration
相關次數:
  • 被引用被引用:0
  • 點閱點閱:143
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文提出粒子濾波器結合多重模糊特徵在單鏡頭完整人體站姿影像中雙手掌心追蹤的新方法。本方法首先將人體從影像中分割出來後,再透過人體輪廓凸點和幾何特徵定位出頭和腳部位置,考量到手部遮蔽的問題,依據人體輪廓凸點、膚色區域中心點或上一刻掌心位置,可決定出兩手的候選位置。然而為了準確地追蹤掌心,論文利用到以下四個特徵:光流、屬於前景程度值、膚色資訊和以掌心候選位置為中心之搜尋區域。從以上特徵導出四個模糊歸屬值(FMVs)並合併成單一任意像素屬於掌心的模糊歸屬值。最後,論文提出基於整體模糊歸屬值、粒子遷移方法和手部移動方向的粒子濾波器來追蹤並分辨兩手掌心位置。論文利用三組不同影片的手部追蹤表現及與其它不同的手部追蹤方法的必較,來證明提出之手部追蹤方法的有效性和準確性。
This thesis proposes a new method to track the two hands of a complete human body in standing posture using particle filtered fusion of multiple fuzzy features from monocular video. The proposed method first segments human body and then localizes the head and the feet based on the convex points of the body contour and body geometrical characteristics. With the consideration of the hand occlusion problem, hand candidates are determined according to the convex points of the segmented body contour, the center of skin color region, or the last hand palm locations. To accurately track the hand palms, the four features of optical flows, the degree a pixel belonging to foreground, skin color information, and the search area around the hand palm candidate are used. Four fuzzy membership values (FMVs) are derived from the four features and are then integrated into a single one to represent the overall FMV that a pixel belongs to a hand palm. Finally, particle filter based on the FMVs, a new particle migration technique, and hand moving directions is proposed to track the two hand palms. Experiments in three videos with comparisons with different hand tracking methods are performed to verify the effectiveness and accuracy of the proposed hand tracking method.
摘要 i
Abstract ii
Content iii
List of Figure v
List of Table x
Chapter 1 Introduction 1
1.1 Survey 1
1.2 Organization of the Thesis 6
Chapter 2 Human Body Segmentation 7
2.1 RGB-based Background Registration and Update 10
2.1.1 Frame Difference 10
2.1.2 Background Registration 11
2.1.3 Background Update 12
2.2 Object Segmentation 12
2.2.1 Background Difference 13
2.2.2 Shadow Removal 14
2.2.3 Morphological Operator 16
2.2.4 Post Processing 17
Chapter 3 Two-Dimensional Posture Estimation 18
3.1 Localization of the Convex Point 19
3.2 Features for Posture Estimation 23
3.3 Posture Estimation Rules 24
3.3.1 Locating the Head 25
3.3.2 Locating the Tips of the Feet 25
3.3.3 Locating the Hands 26
Chapter 4 Hand Fuzzy Feature Extraction 27
4.1 Optical Flow 27
4.2 Foreground Degree 29
4.3 Skin Color 30
4.3.1 Fuzzy Skin Color Degree 30
4.3.2 Facial Skin Color Removal 31
4.4 Search Area 33
4.5 Mixture of Fuzzy Features 38
Chapter 5 Particle Filter Tracking Based on Mixture of Fuzzy Features 40
5.1 Particle Filter 41
5.1.1 Dynamic Model and Observation Model 42
5.1.2 Resampling 44
5.1.3 Particle Migration 45
5.1.4 Hand Palm Location Estimation 46
5.2 Two-Target Tracking Rules 47
Chapter 6 Experiments 51
6.1 Experimental Results 51
6.2 Discussions 61
Chapter 7 Conclusion 70
References 72
[1]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.
[2]R. Jiang, M. L. Parry, P. A. Legg, D. H. S. Chung, and I. W. Griffiths, “Automated
3-D animation from snooker videos with information-theoretical optimization,” IEEE Trans. Computational Intelligence and AI in Games, vol. 5, no. 4, pp. 337-345, 2013.
[3]L. Rincon, H. Yamasaki, and S. Shimoda, “Design of a video game for rehabilitation using motion capture, EMG analysis and virtual reality,’ Proc. 2016 Int. Conf. Electronics, Communications and Computers (CONIELECOMP), pp. 198-204, 2016.
[4]N. Jojic, M. Turk, and T. S. Huang, “Tracking self-occluding articulated objects in dense disparity maps,” Proc. 7th IEEE Int. Conf. Computer Vision, vol. 1, pp. 123-130, 1999.
[5]J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, and A. Blake, “Real-time human pose recognition in parts from single depth images,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1297-1304, 2011.
[6]X. Suau, J. Ruiz-Hidalgo, J. R. Casas, ”Real-Time Head and Hand Tracking Based on 2.5D Data,” IEEE Transactions on multimedia, vol. 14, no. 3, pp. 575-585, June 2012.
[7]C. F. Juang and S. L. Wong “Real-Time Human body Posture Estimation Using Depth Camera,” Master Thesis, National Chung Hsing University, Taiwan, R.O.C., Aug. 2014
[8]I. Laptev and T. Lindeberg, “Tracking of multi-state hand models using particle filtering and a hierarchy of multi-scale image features,” Proc. IEEE Workshop on Scale-Space and Morphology, 2001.
[9]C. Shan, T. Tan, and Y. Wei, “Real-time hand tracking using a mean shift embedded particle filter,” Pattern Recognition, pp.1958-1970, Dec. 2006.
[10]P. C. Hernandez, J. Czyz, F. arques, T. Umeda, X. Marichal and B. Macq, “Bayesian Approach for Morphology-Based 2-D Human Motion Capture,” IEEE Transactions on multimedia, vol. 9, no. 4, pp. 754-765, June 2007.
[11]C. Colombo, A. Del Bimbo, and A. Valli,”A real-time full body tracking and humanoid animation system,” Parallel Computing, vol. 34, no. 12, pp. 718-726, Dec. 2008.
[12]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, January 2009.
[13]M. Kristan, J. Perš, S. Kovačič, and A. Leonardis, “A local-motion-based probabilistic model for visual tracking,” Pattern Recognition, vol. 42, pp. 2160-2168, 2009.
[14]B. J. Chen, C. M. Huang, T. E. Tseng, and L. C. Fu, “Robust head and hands tracking with occlusion handling for human machine interaction,” Proc. IEEE/RSJ Int. Cnf. Intelligent Robots and Systems (IROS), pp. 2141-2146, Oct. 2012.
[15]U. Soni, A. Trivedi, N. Roberts, ”Real-time hand tracking using integrated optical flow and CAMshift algorithm,” International Conference on Research in Computational Intelligence and Communication Networks(ICRCICN), 2016.
[16]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.
[17]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.
[18]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.
[19]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.
[20]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.
[21]M. T. Razali and B. J. Adznan, “Detection and classification of moving object for smart vision sensor,” Proc. Information and Communication Technologies Conf., vol. 1, pp. 733-737, 2006.
[22]H. J. Jiang, T. C. Chen, and C. F. Juang, “Stereo camera-based real-time 3D character construction and human behavior following with interactive entertainment application,” Proc. Nat. Symp. System Science and Engineering, pp. 501-506, Taiwan, R.O.C., June 2012.
[23]C. Stauffer and W. Grimson, “Adaptive background mixture models for real-time tracking,” Proc. CVPR, pp. 246–252, 1999.
[24]Z. Zivkovic and F. van der Heijden, “Efficient adaptive density estimation per image pixel for the task of background subtraction,” Pattern Recognition Letters, vol. 27, no. 7, pages 773-780, 2006.
[25]M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, “A tutorial on particle filters for online nonlinear/non-gaussian Bayesian tracking,” IEEE Trans. Signal Processing, vol. 50, no. 2, pp. 174-188, Feb. 2002.
[26]C. F. Juang, W. C. Du, and T. C. Chen, “Human body 3D posture estimation using significant points and two cameras,” Scientific World Journal, vol.2014, Article ID 670953, pp.1-17, May 2014.
[27]C. Arcelli and G. S. di Baja, “A one-pass two-operation process to detect the skeletal pixels on the 4-distance transform,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 4, pp. 411-414, April 1989.
[28]C. F. Juang, J. R. Wu, and W. J. Lin, “Automatic Human Body Extraction and Posture Analysis in Consecutive Images,” Master Thesis, National Chung Hsing University, Taiwan, R.O.C., July 2007.
[29]R. Jain, R. Kasturi, and B. G. Schunck, Machine Vision, Inc. New York, McGraw-Hill, 1995, pp. 43-48.
[30]C. J. Chua, “Hand Motion Estimation Using Mixture of Features with Humanoid Robot Imitation Application,” Master Thesis, National Chung Hsing University, Taiwan, R.O.C., July 2015.
[31]J. H. Holland, “Genetic algorithms,” Scientific American, vol. 267, no. 1, pp. 44-50m 1992.
[32]OpenNiTE: http://openni.ru/files/nite/index.html
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
無相關期刊