(3.236.214.19) 您好!臺灣時間:2021/05/06 21:34
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:林格沂
研究生(外文):Ge-Yi Lin
論文名稱:基於雙攝影機與模糊系統之三維人體剪影建構與姿態辨識
論文名稱(外文):Fuzzy System-based Three Dimensional Human Silhouette Construction and Posture Recognition using Two Cameras
指導教授:莊家峰
指導教授(外文):Chia-Feng Juang
口試委員:徐超明丁川康
口試委員(外文):Chao-Ming HsuChuan-Kang Ting
口試日期:2016-07-19
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:2016
畢業學年度:104
語文別:英文
論文頁數:47
中文關鍵詞:姿態辨識相機校正三維剪影模糊系統
外文關鍵詞:posture recognitioncamera calibrationthree-dimensional silhouettefuzzy system
相關次數:
  • 被引用被引用:0
  • 點閱點閱:84
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本文提出了一種基於模糊系統利用三維剪影建構的人體姿態辨識方法,藉由兩部攝影機擷取人體的輪廓資訊。首先運用高斯混合模型 (GMM) 及最小矩形框 (MER) 建立背景,運用以RGB三原色為基礎的分割演算法從背景中切割出人體,並去除雜訊及陰影,最後得到兩組相對應的二維之人體剪影。運用模糊類神經網路 (FNN) 做相機校正得到一個三維的立體剪影。特徵值擷取部份,將包住人體剪影的最小立方體 (MEC) 均勻切割,求得剪影在每個小立方體的體積比例並以此作為特徵值。分類器部份,運用模糊分類器 (FC) 並分別使用選擇性梯度下降(MSGD)和支持向量機(SVM)做前件部和後件部的學習,後件部為零階Takagi-Sugeno-Kang (TSK)形式(TSK)模糊規則,在FC的結構學習上使用激發量分群(FSC)演算法。本論文中的三維剪影建構的特徵值有不錯的辨識效果且在分類器的參數量較少。在實驗結果中比較不同的分類器和相機校正的方法,以驗證所提出的模糊系統方法上的優勢。

This thesis proposes a fuzzy system-based human posture recognition method using three-dimensional (3D) reconstruction. Two cameras capture two sets of image sequences at the same time to get the human posture. A Gaussian-mixture model (GMM) method and a minimum enclosing rectangle (MER) are used for establishing background. An Angle-Compensated RGB (AC-RGB) segmentation algorithm is proposed to segment the human body from background and reduce shadow influence. After segmentation, two-dimensional silhouettes of the human body are obtained. This thesis uses fuzzy neural network (FNN) to construct a three-dimensional silhouette. For feature extraction, the minimum enclosing cube (MEC) of the 3D body silhouette is uniformly partitioned and the volume ratio of the silhouette in each partitioned box is calculated and used as a set of features. For classification, this thesis uses fuzzy classifier (FC) with margin-selective gradient descent (MSGD) and support vector machine (SVM) for antecedent and consequent part learning, respectively. The FC consists of zero-order Takagi-Sugeno-Kang (TSK) fuzzy rules and uses firing-strength-based clustering (FSC) in structure learning. Experimental results show that the 3D reconstruction and recognition rates. A set of 3D features has the advantage of the smaller feature dimension with better or competitive classification performance. Comparisons with different classifiers and calibration methods are conducted to verify the advantage of the fuzzy system-based method.

Content
摘 要 i
Abstract ii
List of Tables iv
List of Figures v
Chapter 1 Introduction 1
1.1 Survey and Literature Review 1
1.2 Thesis Organization 3
Chapter 2 Human Body Segmentation 4
2.1 Background Registration 4
2.2 Shadow Elimination and Morphological Operation 7
2.3 Minimum Enclosing Rectangle Window of Human Body 9
Chapter 3 Three-Dimensional Silhouette Reconstruction 13
3.1 Calibration 13
3.1.1 Projection Matrix 13
3.1.2 Fuzzy Neural Network 14
3.2 Silhouette Volume Intersection 17
Chapter 4 Human Body Feature Extraction 18
4.1 Three-Dimensional Minimum Enclosing Cube 18
4.2 Three-Dimensional Feature Extraction 20
Chapter 5 Human Body Posture Recognition 22
5.1 Multi-Class Fuzzy Classification 22
5.2 Structure and Parameter Learning 23
Chapter 6 Experiments 29
6.1 Experimental Results 29
6.2 Comparisons with Different Methods 38
Chapter 7 Conclusion 43
References 44



[1]C. Rougier, J. Meunier, A. St-Arnaud, and J. Rousseau, “Robust video surveillance for fall detection based on human shape deformation,” IEEE Trans. Circuits Syst. Video Technol., vol. 21, no. 5, pp. 611-622, May 2011.
[2]L. Weilun, H. Jungong, and P. With, “Flexible human behavior analysis framework for video surveillance applications,” Int. J. Digital Multimedia Broadcast., vol. 2010, pp. 920121-1–920121-9, Jan. 2010.
[3]D. Brulin, Y. Benezeth, and . Courtial, “Posture recognition based on fuzzy logic for home monitoring of the elderly,” IEEE Trans. Inf. Technol. Biomed., vol. 16, no. 5, pp. 974-982, Sep. 2012.
[4]M. Yu, Y. Yu, A. Rhuma, S. Naqvi, L. Wang and J. Chambers, “An online one class support vector machine-based person-specific fall detection system for monitoring an elderly individual in a room environment,” IEEE J. Biomed. Health Informat., vol. 17, no. 6, pp. 1002-1014, Nov. 2013.
[5]M. Yu, A. Rhuma, S. Naqvi, J. Chambers, and L. Wang, “A posture recognition-based fall detection system for monitoring an elderly person in a smart home environment,” IEEE Trans. Inf. Technol. Biomed., vol. 16, no. 6, pp. 1274-1286, Nov. 2012.
[6]Z. Bian, J. Hou, L. Chau, and N. Magnenat-Thalmann, “Fall detection based on body part tracking using a depth camera,” IEEE J. Biomed. Health Informat., vol. 19, no. 2, pp. 430-439, Mar. 2015.
[7]E. Stone, and M. Skubic, “Fall detection in homes of older adults using the Microsoft Kinect,” IEEE J. Biomed. Health Informat., vol. 19, no. 1, pp. 290-301, Jan. 2015.
[8]A. Iosifidis, A. Tefas, and I. Pitas, “View-Invariant action recognition based on artificial neural networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 23, no. 3, pp. 412-424, Mar. 2012.
[9]F. Xie, G. Xu, Y. Cheng, Y. Tian, “Human body and posture recognition system based on an improved thinning algorithm,” IET Image Process., vol. 5, iss. 5, pp. 420-428, 2011.
[10]C. Rougier and J.Meunier, “3D head trajectory using a single camera,” Int. J. Future Gener. Commun. Netw., Invited paper Spec. Issue Image Signal Process., vol. 3, no. 4, pp. 43–54, 2010.
[11]N. Friedman, S. Russell, Image segmentation in video sequences: a probabilistic approach. , Proc. 13th Conf. on Uncertainty in Artificial Intelligence, pp. 175-181, 1997.
[12]C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., vol. 2, pp. 246-252, Jun. 1999.
[13]T. C. Chen, Vision-based Real-Time 3D Human Posture Significant Points Estimation, Master Thesis, National Chung-Hsing University, Taiwan, 2009.
[14]R. C. Gonzalez and R. E. Woods, Digital Image Processing 2/e, Prentice Hall, 2008.
[15]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, Oct. 2006.
[16]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.
[17]C. F. Juang and C. T Lin, “An on-line self-constructing neural fuzzy inference network and its applications,” IEEE Trans. Fuzzy Systems, vol. 6. no. 1, pp., 12-32, Feb. 1998.
[18]M. E. Yuksel and A. Basturk, “Application of type-2 fuzzy logic filtering to reduce noise in color images,” IEEE Computational Intelligence Magazine, vol. 7, no. 3, pp. 25-35, Jul. 2012.
[19]G. C. Chen and C. F. Juang, “Object detection using color entropies and a fuzzy classifier,” IEEE Computational Intelligence Magazine, vol. 8, no. 1, pp. 33-45, Feb. 2013.
[20]C. F. Juang and G. C. Chen, “A TS fuzzy system learned through a support vector machine in principal component space for real-time object detection,” IEEE Trans. Industrial Electronics, vol. 59. no. 8, pp. 3309-3320, Aug. 2012.
[21]W. C. Chiang, A simplified fuzzy classifier with application to object detection using fuzzy color histogram, Master Thesis, National Chung-Hsing University, Taiwan, 2014.
[22]C. F. Juang, S. H. Chiu, and S. J. Shiu, “Fuzzy system learned through fuzzy clustering and support vector machine for human skin color segmentation,” IEEE Trans. Syst., Man, and Cyber., Part A: Systems and Humans, vol. 37, no. 6, pp. 1077-1087, Nov. 2007.
[23]W. Y. Cheng and C. F. Juang, “A fuzzy model with online incremental SVM and margin-selective gradient descent learning for classification problems,” IEEE Trans. Fuzzy Systems, vol. 22, no. 2, pp. 324-337, Apr. 2014.
[24]N. Cristianini and J. S.-Taylor, “An Introduction to Support Vector Machines And Other Kernel-based Learning Methods,” Cambridge University Press, 2000.
[25]O. Chapelle, P. Haffner, and V. Vapnik, “Support vector machines for histogram-based image classification,” IEEE Trans. Neural Networks, vol. 10, pp. 1055-1064, Sep. 1999.
[26]Y. Kim and H. Ling, “Human activity classification based on micro-doppler signatures using a support vector machine,” IEEE Trans. Geoscience and Remote Sensing, vol. 47, no. 5, pp. 1328 – 1337, May 2009.
[27]S. Essid, G. Richard, and B. David, “Musical instrument recognition by pairwise classification strategies,” IEEE Trans. Audio, Speech, and Language Processing, vol. 14, no. 4, pp. 1401 – 1412, Jul. 2006.
[28]C. L. Lee, Human Body Feature Extraction And Posture Recognition Using Neural Fuzzy Network, Master Thesis, National Chung-Hsing University, Taiwan, 2010.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
無相關期刊
 
無相關點閱論文
 
系統版面圖檔 系統版面圖檔