跳到主要內容

臺灣博碩士論文加值系統

(44.211.24.175) 您好!臺灣時間:2024/11/05 05:35
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:林佩靜
研究生(外文):Peiching Lin
論文名稱:以二維形狀特徵為基礎的人體姿勢辨識系統
論文名稱(外文):Human Posture Recognition System Using 2-D Shape Features
指導教授:胡竹生胡竹生引用關係
指導教授(外文):Jwu-Sheng Hu
學位類別:碩士
校院名稱:國立交通大學
系所名稱:電機與控制工程系所
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:2006
畢業學年度:95
語文別:中文
論文頁數:75
中文關鍵詞:姿勢辨識粒子濾波器傅利業描述子背景濾除
外文關鍵詞:Posture RecognitionParticle FilterFourier DescriptorsBackground Removal
相關次數:
  • 被引用被引用:1
  • 點閱點閱:261
  • 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:1
本論文中建立一個以影像形狀為基礎的人體姿勢辨識系統並加以分析與實現。此一系統利用混合高斯機率模型建構背景模型,對目前影像做背景濾除以取得前景,並結合肯尼邊緣偵測法與加速的梯度向量流動態輪廓偵測法得到人體姿勢的輪廓。分析目前主要形狀特徵描述子應用在人體姿勢辨識的適應性,比較傅立葉描述子與曲率比例空間描述子的特性以選定適當的描述子。此一姿勢辨識系統建構在一個以2D形狀特徵為基礎的3D姿勢特徵資料庫,解決同一姿勢因不同視角所導致的特徵差異而建立過多的姿勢類別。並同時建構一個針對人體姿勢行為的機率建模機制以輔助此辨識系統,以預防不同姿勢間不合理的轉換並提高其辨識率。實驗結果分別呈現對特徵的選取、機率建模機制、姿勢類別多寡的辨識率與序列行為的姿態辨識結果並加以分析與討論。
In this thesis, a human posture recognition system based on shape-based descriptors is proposed and implemented. The foreground image of human is acquired by the background model built by Gaussian Mixture Model method. We applied the Canny Edge Detection and Speedy GVF Snake to obtain the contour of the foreground as the input of the human posture recognition system. The suitability of the major contour descriptors, Fourier Descriptors and Curvature Scale Space Descriptors, applied to human posture issues are discussed. The 3D postures databases are constructed by 2D contour-based features to avoid the posture classes increase with the different points of view for the same posture. In order to prevent the unreasonable transitions between postures and improve the recognition rate, we integrate a probability map based on human behaviors to the recognition system. Lastly, the results of Experiments for different features, a probability map, different numbers of posture classes, and the recognition of the behavior sequence are listed and discussed.
摘要 II
ABSTRACT III
致謝 IV
目錄 V
表目錄 VII
圖目錄 VIII
第一章 序論 1
1.1 研究動機與背景 1
1.2 相關研究回顧 1
1.3 論文主題與貢獻 4
1.4 章節概要 5
第二章 擷取2D影像中人體姿勢輪廓之方法 6
2.1 前背景分離 6
2.1.1 高斯混合模型的背景建立 6
2.1.2 以顏色為基礎之背景濾除[22] 7
2.1.3 以梯度為基礎的背景濾除 7
2.1.4 區域階層處理 8
2.1.5 陰影濾除 9
2.2 肯尼邊緣偵測法(CANNY EDGE DETECTION) 12
2.3 梯度向量流動態輪廓模型(GRADIENT VECTOR FLOW SNAKE) 14
2.3.1 主動式輪廓偵測法 14
2.3.2 內部能量與外部能量 15
2.3.3 梯度向量流動態輪廓模型 16
2.3.4 實現的架構與加速方法 17
2.4 後處理 18
2.4.1 點數取樣 (Sample)與大小正規化 (Scale) 18
2.4.2 點間距相等 (Equal Distance) 19
第三章 分析以輪廓為基礎之特徵比對方法 21
3.1 傅利葉描述子 (FOURIER DESCRIPTOR) 21
3.1.1 以質心距離為基礎的傅利葉描述子 22
3.1.2 以位置座標為基礎的傅利葉描述子 23
3.1.3 結合位置座標為基礎的傅利葉描述子之輔助特徵 25
3.2 曲率比例空間描述子(CURVATURE SCALE SPACE DESCRIPTORS) 27
3.2.1 曲率比例空間描述子之特徵擷取 29
3.2.2 曲率比例空間描述子之特徵比對 31
第四章 建構3D姿勢資料庫及辨識系統 33
4.1 建立人體姿勢之3D資料庫 33
4.2 以粒子濾波器為基底的辨識機制 39
4.2.1 粒子濾波器理論架構 39
4.2.2 修正粒子濾波器 44
4.3 辨識方法 46
第五章 實驗流程與結果 49
5.1 實驗平台 49
5.2 系統架構 50
5.3 實驗結果 51
5.3.1 主要特徵描述子之辨識結果 51
5.3.2 增加輔助特徵之辨識結果 55
5.3.3 增加姿勢類別之辨識結果 59
5.3.4 加入粒子濾波器之辨識結果 62
5.3.5 行為序列的姿勢辨識 65
5.4 討論 70
第六章 結論與未來研究方法 71
參考文獻 72
[1] I. Haritaoglu ,D. Harwood and L. S. Davis, “Ghost : A Human Body Part Labeling System
Using Silhouettes,” in 14th International Conf. on Pattern Recognition, Brisbane,Australia,1998
[2] S. Iwasawa , K. Ebihara , J. Ohya and S. Morishima, “Real Time Estimation of Human Body Posture from Monocular Thermal Images,” in Conf. on Computer Vision and Pattern Recognition,1997.
[3] C. Wren ,A. Azarbayejani , T. Darrell and A. Pentland, “Pfinder : Real-Time Tracking of the Human Body,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, no 7, pp. 780-785, 1997.
[4] Q. Delamarre and O. Faugeras, “3D Articulated Models and Multi-View Tracking with Silhouettes,” RobotVis Project INRIA, 2001.
[5] B. Boulay , F. Bremon , M.Thonnat ,“human posture recognition in video sequence” INRIA Sophia Antipolis, France
[6] S. Iwasawa , J. Ohya , K. Takahashi , T. Sakaguchi , S.Kawato, K. Ebihara and S. Morishima, “Real-time, 3D Estimation of Human Body Postures from Trinocular Images,’ Faculty of engineering, Seikei University, 2000.
[7] K. Takahashi ,S. Sugakawa, “Remarks on human posture classification using self-organizing map” IEEE Int’l Conf. Systems, Man and Cybernetics ,Vol. 3, pp. 2623 – 2628 ,Oct. 2004
[8] L.B.Ozer, W.Wolf, “Real-time posture and activity recognition”, in Proc. IEEE Workshop, Motion and Video Computing, pp133 – 138, Dec. 2002,
[9] L.B.Ozer, T. Lu , W. Wolf; “Design of a real-time gesture recognition system: high performance through algorithms and software” IEEE Signal Processing Magazine, Vol. 22, pp. 57-64, May 2005
[10] H. Fujiyoshi ,A. Lipton, “Real-Time Human Motion Analysis by Image Skeletonization,” in Proc. IEEE Workshop Application Computer Vision, pp. 15–21,1998
[11] R. Cucchiara, C. Grana, A. Prati, R.Vezzani,; “Probabilistic posture classification for Human-behavior analysis” IEEE Trans. Systems, Man and Cybernetics, Vol. 35,pp. 42-54, Jan. 2005
[12] D. Y. Chen, H. Y. Mark Liao, H. R. Tyan, and C. W. Lin, “Automatic Key Posture Selection for Human Behavior Analysis” IEEE International Workshop on Multimedia Signal Processing, Shanhai, China, November 2005.
[13] Y.-T. Hsu, J.-W. Hsieh, and H.-F. Kao, “Human Behavior Analysis Using Deformable Triangulations” International Workshop on Multimedia Signal Processing, Shanhai, China, 2005.
[14] L. Goldmann, M. Karaman, T. Sikora., “Human body posture recognition using MPEG-7 descriptors” SPIE - The International Society for Optical Engineering, Visual Communications and Image Processing, p 177-188, v 5308, Jan 2004.
[15] L. Goldmann, M. Karaman, T. Sikora., “Human body posture recognition using MPEG-7 descriptors” SPIE - The International Society for Optical Engineering, Visual Communications and Image Processing, p 177-188, v 5308, Jan 2004.
[16] Y. Avrithis ; Y. Xirouhakis; S. Kollias, “Affine invariant representation and classification of object contours for image and video retrieval” Computational Intelligence and Applications, p 342-347, 1999
[17] A. Folkers ; H. Samet, “Content-based image retrieval using Fourier descriptors on a logo database” IEEE, Pattern Recognition, p521 – 524, v3, Aug. 2002.
[18] V. Kellokumpu , M. Pietikäinen and J. Heikkilä “Human activity recognition using sequences of postures” IAPR Conference on Machine Vision Applications, Tsukuba Science City, Japan, p 570-573,2005
[19] V. Kwatra, A. Bobick, A. Johnson, “Temporal integration of multiple silhouette-based body-part hypotheses” IEEE Computer Society Conference on Computer Vision and Pattern Recognition. p 758-764 , v 2, Dec 2001.
[20] C.D. Liu , P.C. Chung , Y.N. Chung “Human home behavior interpretation from video streams” Networking, Sensing and Control, IEEE International Conference , p 192 - 197 Vol.1 , March 2004
[21] 鄭士奇,「以高斯混合模型為基礎並使用陰影濾除之動態背景影像模型建立」,國立交通大學,碩士論文,民國94年
[22] C.Stauffer and W.Eric, L. Grimson,“Learning patterns of activity using real-time tracking”, IEEE Trans. on PAMI,22(8):747-757,Aug 2000.
[23] H. Stark,J W. Woods, Probability and Random Processes with Applications to Signal Processing, 3th Edition , 2002
[24] J. Canny, “A Computational Approach to Edge Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-8, No.6, 1986.
[25] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes – Active Contour Models,” International Journal of Computer Vision, Vol. 1, No.4, 321-331, 1987.
[26] C. Xu and J. L. Prince, “Gradient Vector Flow: A New External Force for Snakes,” IEEE Conference on Computer Vision and Pattern Recognition, 66-71, 1997.
[27] K. S. Ntalianis, N. D. Doulamis, A. D. Doulamis, and S. D. Kollias, “Multiresolution gradient vector flow field: a fast implementation towards video object plane segmentation,” Proc. IEEE Int. Conf. Multimedia and Expo, pp. 1~4, 2001.
[28] 林群棋,「使用基於相似度的外觀圖解法於三維物體之形狀記憶與辨識」,國立交通大學,碩士論文,民國94年
[29] 王志浩,「以形狀為基礎建立在影像序列上之影像查詢方法」,私立元智大學,碩士論文,民國89年
[30] C. C.Chang ,P.C. Mou “ Gesture recognition approach for sign language using curvature scale space and hidden Markov model” IEEE International Conference on Multimedia and Expo (ICME), v 2, p 1187-1190 2004
[31] D. Zhang, G. Lu, “A comparative study of curvature scale space and Fourier descriptors for shape-based image retrieval” Journal of Visual Communication and Image Representation, p 41-60 , v 14, March 2003
[32] F. Mokhtarian, S. Abbasi , J. Kittler , 1996. ”Efficient and robust retrieval by shape content through curvature scale space” International workshop on Image Databases and multimedia search, pp. 53-42 1996
[33] F. Mokhtarian, S. Abbasi , J. Kittler , “Enhancing CSS-based shape retrieval for objects with shallow concavities” Image and Vision Computing, v 18, n 3, p 199-211,Feb, 2000
[34] C. M. Cyr and B. Kimia, “A Similarity-Based Aspect-Graph Approach to 3D Object Recognition,” in International Journal of Computer Vision, 57(1):5–22, 2004.
[35] M. Isard , A. Blake, “CONDENSATION - Conditional density propagation for visual tracking” International Journal of Computer Vision, p 5-28, v 29, August 1998
[36] M. Isard , A. Blake, “A Mixed-state CONDENSATION tracker with automatic model-switching” Journal of Engineering and Applied Science, IEEE 6th International Conference on Computer Vision, p 107-112, Jan 1998.
[37] 吳家豪, “印刷電路板圓孔檢測方法之研究,” 私立元智大學,碩士論文, 民國91年
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top