跳到主要內容

臺灣博碩士論文加值系統

(18.204.48.64) 您好!臺灣時間:2021/08/03 12:33
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:王棣雲
研究生(外文):Wang, LiYun
論文名稱:一個整合式的人物偵測方法
論文名稱(外文):An Integrated Approach to Human Detection
指導教授:陳良華陳良華引用關係
指導教授(外文):Chen, LiangHua
口試委員:陳良華廖弘源許威烈
口試委員(外文):Chen, LiangHuaLiao, HongYuanHsu, WeiLieh
口試日期:2012-06-14
學位類別:碩士
校院名稱:輔仁大學
系所名稱:資訊工程學系
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:2012
畢業學年度:100
語文別:中文
論文頁數:65
中文關鍵詞:人物偵測梯度方向分佈圖傅立葉描述支持向量機
外文關鍵詞:Human DetectionHistogram of Oriented GradientFourier DescriptorsSupport Vector Machine
相關次數:
  • 被引用被引用:0
  • 點閱點閱:160
  • 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
近年來治安問題及天災人禍的事件不斷發生,政府或企業公司都會採用不同的安全系統來保護生命以及財產的安全。目前的安全系統包括了視訊監控系統、門禁管制系統、災害偵測及管理系統、特定事件偵測系統等不同的安全系統,以保護生命及財產安全。另外,因為多媒體技術、網路傳輸技術以及視訊壓縮技術的發展,數位視訊監控系統已經廣泛地被使用在我們的生活中,所以我們的方法是以視訊監控系統為主並提出一個具有高精確度及少假警報的整合式的人物偵測方法能夠自動地偵測出視訊中的人。
本論文提出了一個整合梯度方向分佈圖及傅立葉描述兩種互補的形狀特徵去判斷視訊中是否有人。梯度方向分佈圖的方法能夠有效的描述一個區域內的形狀特徵,並具有光線、視角以及姿勢的不變性,因此,梯度方向分佈圖特徵可以表示不同視角及姿勢的形狀特徵。傅立葉描述的方法能夠描述移動區域的輪廓特徵,並表示畫面中移動區域的形狀。最後,我們整合了梯度方向分佈圖方法及傅立葉描述方法的偵測值去決定視訊中是否有人。在實驗結果方面,我們的方法能夠得到很高的精確度以及很少的假警報。

Security problems have become more and more important for government and companies due to frequent natural disasters and public security problems in recent years. Current security system includes visual surveillance system, access control system, disaster detection and management system, event-specific detection system fir life and property security of, and surveillance system with monitoring function. In this research, I propose an integrated method to detect human in surveillance videos. I integrate the Histogram of Oriented Gradient feature and the Fourier Descriptors feature to determine the moving object is human or not. The advantage of the Histogram of Oriented Gradient is invariant to illuminations and viewpoints, so it can effectively represent shape features in the region. The Fourier Descriptors feature can represent the shape feature of the moving region, so it can get high recall values. Final, Support Vector Machine has been used to get classifiers of two kinds of different features. In the result, four different testing videos have been used to compare the performances between this method and other methods. The result shows this method can get higher accuracy with lower false alarm.
摘要 II
Abstract III
表目錄 VI
圖目錄 VII
第一章、研究簡介 1
1.1 研究背景 1
1.2 入侵者偵測的問題 2
1.3 論文架構 3
第二章、文獻探討 4
2.1 間接法 4
2.2 直接法 7
第三章、我們所提的方法 16
3.1 找出影像中移動區域 17
3.1.1 背景消去法 17
3.1.2 閉合運算 19
3.2 連接性分析 21
3.2.1 連通單元標記 21
3.2.2 邊界追蹤 23
3.3 特徵表示 25
3.3.1 梯度方向分佈圖 26
3.3.2 傅立葉描述 30
3.4 辨識及偵測方法 32
3.4.1 支持向量機 32
3.4.2 偵測方法 36
第四章、實驗結果 37
第五章、結論 53
5.1 總結 53
5.2 未來工作 54
Reference 55

[1] S. Ferrando, G. Gera and C. Regazzoni, “Classification of Unattended and Stolen Objects in Video Surveillance System”, IEEE International Conference on Advanced Video and SignalBased Surveillance (AVSS), pages 21, 2006.
[2] F. Li, M.K. Leung, M. Mangalvedhekar and M. Balakrishnan, ‘‘Automated video surveillance and alarm system’’, International Conference on Machine Learning and Cybernetics, Volume 2, pages 1156 - 1161 , 2008.
[3] K. Lee, C.Y. Choo, H.Q. See, Z.J. Tan and Y. Lee, ‘‘Human detection using Histogram of oriented gradients and Human body ratio estimation’’, IEEE International Conference on Computer Science and Information Technology (ICCSIT), Volume 4, pages 18 - 22, 2010.
[4] M.S. Chowdhury, Y.C. Kuang and M.P. Ooi, ‘‘Fast and accurate human detection for video applications using edgelets’’, International Conference on Computer Applications and Industrial Electronics (ICCAIE), pages 74 - 79, 2010.
[5] N. Dalal and B. Triggs, ‘‘Histogram of Oriented Gradients for Human Detection’’, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Volume 1, pages 886 - 893, 2005.
[6] N. Dalal, B. Triggs and C.Schmid, ‘‘Human Detection Using Oriented Histograms of Flow and Appearance’’, European Conference on Computer Vision, pages 428 - 441, 2006.
[7] L. Meng, L. Li, S. Mei and W. Wu, ‘‘Directional Entropy Feature for Human Detection’’, International Conference on Pattern Recognition (ICPR), pages 1 – 4, 2008.
[8] C.H. Chuang, S.S. Huang, L.C. Fu and P.Y. Hsiao, ‘‘Monocular Multi-Human Detection Using Augmented Histograms of Oriented Gradients’’, International Conference on Pattern Recognition (ICPR), pages 1 – 4, 2008.
[9] S. Walk, N. Majer, K. Schindler and B. Schiele, “New Features and Insights for Pedestrian Detection”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1030 – 1037, 2010.
[10] T. Watanabe, S. Ito and K. Yokoi, “Co-occurrence Histograms of Oriented Gradients for Human Detection”, Information and Media Technologies, Volume 5, No. 2, pages 659 - 667, 2010.
[11] N. Buch and S.A. Velastin, ‘‘Human Intrusion Detection using Texture Classification in Real-Time’’, Tracking Humans for the Evaluation of their Motion in Image Sequences, THEMIS 2008, pages 1 - 6, 2008.
[12] S.T. An, J.J. Kim, J.W. Lee and J.J. Lee, ‘‘Fast Human Detection Using Gaussian Particle Swarm Optimization’’, IEEE International Conference on Digital Ecosystems and Technologies Conference (DEST), pages 143 - 146, 2011.
[13] R. Fisher, S. Perkins, A. Walker and E.Wolfart, “Connected Component Labeling”, http://homepages.inf.ed.ac.uk/rbf/HIPR2/label.htm.
[14] E. Persoon and K.S. Fu, “Shape Discrimination using Fourier descriptions”, IEEE Transactions on System Man and Cybernetics, volume 7(3), pages 170 - 179, 1977.
[15] V.N. Vapnik, ‘‘Statistical Learning Theory’’, Wiley, New York, 1998.
[16] INRIA person dataset, http://pascal.inrialpes.fr/data/human/.
[17] MIT pedestrian dataset, http://cbcl.mit.edu/software-datasets/PedestrianData.html.
[18] LEMS Vision group dataset, http://www.lems.brown.edu/~dmc/.
[19] MPEG-7 dataset, http://www.cis.temple.edu/~latecki/TestData/mpeg7shapeB.tar.gz
[20] CAIVAR video dataset, http://homepages.inf.ed.ac.uk/rbf/CAVIARDATA1/.
[21] PETS2000 video dataset, http://ftp.pets.rdg.ac.uk/PETS2000/.
[22] C.W. Hsu, C.C. Chang and C.J. Lin, “A practical guide to support vector classification”, Technical report, Department of Computer Science, National Taiwan University, Taipei, Taiwan, 2003.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top