跳到主要內容

臺灣博碩士論文加值系統

(44.200.86.95) 您好!臺灣時間:2024/05/20 07:54
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:黃柏諭
研究生(外文):Huang, Bo-Yu
論文名稱:可應用於電腦輔助影像監控系統之人臉偵測與興趣區間探索軟體實作
論文名稱(外文):Face Detection and Discovery of Interval of Interest—Implementation of a Software Subsystem for Computer-Assisted Video Surveillance
指導教授:呂紹偉
指導教授(外文):Leu, Shao-Wei
口試委員:張順雄詹景裕黃培華呂紹偉
口試委員(外文):Chang, Shung-HyungEu, JanGeneHuang, Pei-HwaLeu, Shao-Wei
口試日期:2015-07-23
學位類別:碩士
校院名稱:國立臺灣海洋大學
系所名稱:電機工程學系
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:2015
畢業學年度:103
語文別:中文
論文頁數:37
中文關鍵詞:動態偵測人臉偵測興趣區間擷取電腦輔助影像監控
外文關鍵詞:motion detectionface detectionextraction of interval of interestcomputer-assisted video surveillance
相關次數:
  • 被引用被引用:2
  • 點閱點閱:132
  • 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
本論文實作一影像監控之輔助系統,其特色除了具有動態偵測能力,還具備人臉偵測之功能,透過結合這兩項功能,在調閱監視影像時,能夠快速的找到關鍵的影像區段及時間點。一般家庭或無管理人員之公寓可利用此系統協助保存重要影像資訊,並且能夠進一步的結合網路傳輸,在可疑活動發生之後適時提供遠端監控之協助。
本系統由影像資訊擷取與使用者介面二個子系統組成,其中影像資訊擷取子系統負責擷取感興趣區間搜尋以及人臉影像偵測,我們透過高斯混合模型建立一背景模型,再基於背景模型取得動態物件範圍,此範圍分別經由信號處理與影像處理程序,即可取得監控影像資訊。系統的另一部分為使用者介面,當需要查閱影像內容時,只要透過介面選擇欲觀看的監控影像,即可將先前擷取的區間資訊與人臉資訊顯示於在螢幕上,若使用者點選清單內容或人臉影像即可快速得知事件的起始時刻。
實驗結果顯示此系統能有效搜尋興趣區間及偵測人臉,並能將搜尋及偵測結果妥善儲存與顯示。此系統對於一般數位化影像監控系統功能的提升將有實質的助益。

This thesis implements a software subsystem capable of both motion and face detection. These two capabilities are very useful to computer-assisted video surveillance systems, now considered essential to many home owners and community administrators. Video surveillance systems equipped with these functionalities can help investigators quickly go through days or even weeks of video recording and extract the most relevant video intervals for evidence gathering or for further analyses. These capabilities can also be integrated with Internet-ready cameras to trigger remote monitoring of dubious events.
Our software subsystem is composed of two separate modules: one for extracting the intervals of interest (IOI) as well as for face detection and the other for user interface. We use a Gaussian mixture model to build the background model, which is then used to obtain the pixels of the moving objects. After a series of image and signal processing steps, video intervals containing moving objects are extracted and saved for review. Viewing of these intervals of interest is done through the user interface. A simple click on the IOI list or any of the face images appearing on the user interface can take the viewer directly to the video interval in the recording.
Experimental results have shown that our software subsystem extracts the IOI and detects human faces with satisfactory accuracy and efficiency. Integration of this subsystem to a computer assisted video surveillance system is both feasible and desirable.

致謝 I
摘要 II
Abstract III
目錄 IV
圖目錄 VI
第一章 緒論 1
1.1 研究動機 1
1.2 監控系統 1
1.3 相關工作 3
1.3.1 相關產品、系統 3
1.3.2 動態偵測技術 4
1.3.3 人臉偵測技術 5
1.4 實作架構 5
1.5 小結 6
第二章 物件擷取 7
2.1 灰階影像 7
2.2 降解析度 8
2.3 建立背景模型 9
2.3.1 高斯混合模型 10
2.3.2 最大期望法 11
2.4 背景與物件切割 13
2.5 膨脹 13
2.6 物件連通 14
2.7物件範圍擷取 17
第三章 興趣區間探索 18
3.1 時間軸投影 18
3.2 區間擷取 19
第四章 人臉偵測 21
4.1影像特徵 21
4.2 分類器訓練 22
4.3 強分類器串聯 24
4.4 人臉偵測 25
4.5 人臉篩選 25
4.6 人臉比對 26
第五章 實驗結果與結論 28
5.1 實驗環境 28
5.2 實驗設備 28
5.3 實驗結果 28
5.3.1 資訊擷取 28
5.3.2 使用者介面 31
第六章 結論與展望 34
參考文獻 35

[1] Z. Ji and H. Qin, “A Vehicle Surveillance System for Face Detection,” IEEE International Conference on Vehicular Electronics and Safety, Bielefeld, Germany, Dec. 2007.
[2] A. Ezzahout and R. O. H. Thami, “Conception and Development of a Video Surveillance System for Detecting, Tracking and Profile Analysis of a Person,” International Symposium ISKO-Maghreb, Morocco, Nov. 2013.
[3] S. Zhang, S. C. Chan, R. D. Qin, K. T. Ng, Y. S. Hung, and W. Lu, “On the Design and Implementation of a High Definition Multiview Intelligent Video Surveillance System,” IEEE International Conference on Signal Processing, pp. 353–357, Beijing, China, Aug. 2012.
[4] B. Song, Y. Tian, and B. Zhou, “Design and Evaluation of Remote Video Surveillance System on Private Cloud,” International Symposium on Biometrics and Security Technologies, pp. 256–262, Kuala Lumpur, Malaysia, Aug. 2014.
[5] AtHome Camera, 2015, Brief_Athome Camera. <http://www.ichano.com/index.jsp>, June 2015.
[6] SpotCam, 2013, My SpotCam-雲端監控領導品牌<http://www.myspotcam.com/welcome/feature/?lang=tw>, June 2015.
[7] iSpy, 2014, Open Source Camera Security Software. , June 2015.
[8] QNAP, 2015, 威聯通科技股份有限公司(QNAP System, Inc.)-網路儲存設備<https://www.qnap.com/i/cht/>, June 2015.
[9] Synology, 2015, 群輝科技Network Attached Storage (NAS) <https://www.synology.com/zh-tw/>, June 2015.
[10] T. Bouwmans, F. Porikli, B. Hoferlin, and A. Vacavant, Background Modeling and Foreground Detection for Video Surveillance. Boca Raton, Florida, USA: CRC Press, 2015.
[11] P. KaewTraKulPong and R. Bowden, “An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection,” Computer Vision and Distributed Processing, 2001.
[12] Z. Zivkovic, “Improved Adaptive Gaussian Mixture Model for Background Subtraction,” International Conference on Pattern Recognition, Cambridge, UK, vol. 2, pp. 28–31, Aug. 2004.
[13] T. Charoenpong, A. Supasuteekul, and C. Nuthong, “Adaptive Background Modeling from an Image Sequence by Using K-Means Clustering,” Int’l Conf. on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, Chiang Mai, Thailand, pp. 880–883, May 2010.
[14] A. N. Kumar and C. Sureshkumar, “Background Subtraction Based on Threshold Detection using Modified K-Means Algorithm,” International Conference on Pattern Recognition, Informatics and Mobile Engineering, Tamilnadu Salem, India, pp. 378–382, Feb. 2013.
[15] B. Han and L. S. Davis, “Density-Based Multifeature Background Subtraction with Support Vector Machine,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 5, pp. 1017–1023, Dec. 2012.
[16] L. Maddalena and A. Petrosino, “A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications,” IEEE Transactions on Image Processing, vol. 17, no. 7, pp. 1168–1177, May 2008.
[17] D. M. Rashed, M. S. Sayed, and M. I. Abdalla, “Improved Moving Object Detection Algorithm Based on Adaptive Background Subtraction,” International Conference on Electronics, Communications and Computers, Puebla, Mexico, pp. 29–33, Dec. 2013.
[18] J. Scott, M. A. Pusateri, and D. Cornish, “Kalman Filter Based Video Background Estimation,” IEEE Applied Imagery Pattern Recognition Workshop, Washington, D.C., pp. 1–7, Oct. 2009.
[19] K. A. Ahmad, Z. Saad, N. Abdullah, Z. Hussain, and M. H. Mohd Noor, “Moving Vehicle Segmentation in a Dynamic Background using Self-adaptive Kalman Background Method,” IEEE International Colloquium on Signal Processing and its Applications, Penang, Malaysia, pp. 439–442, March 2011.
[20] S. Kherchaoui and A. Houacine, “Face Detection Based on a Model of the Skin Color with Constraints and Template Matching,” International Conference on Machine and Web Intelligence, pp. 469–472, Oct. 2010.
[21] M. Mahadevi and C. P. Sumathi, “Face Detection based on Skin Color Model and Connected Component with Template Matching,” International Conference on Information Communication and Embedded Systems, Chennai, India, pp. 1–4, Feb. 2014.
[22] M. J. Seow, D. Valaparla, and V. K. Asari, “Neural Network Based Skin Color Model for Face Detection,” Applied Imagery Pattern Recognition Workshop, Washington, D.C., pp. 141–145, Oct. 2003.
[23] A. Sagheer and S. Aly, “An Effective Face Detection Algorithm based on Skin Color Information,” Eighth International Conference on Signal Image Technology and Internet Based Systems, Sorrento, Italy pp. 90–96, Nov. 2012.
[24] P. Viola and M. J. Jones, “Robust Real-Time Face Detection,” International Journal of Computer Vision, vol. 57, no. 2, pp. 137–154, May 2004.
[25] L. Zhang and Y. Liang, “A Fast Method of Face Detection in Video Images,” International Conference on Advanced Computer Control, Liaoning, China pp. 490–494, March 2010.
[26] Z. Li, L. Xue, and F. Tan, “Face Detection in Complex Background Based on Skin Color Features and Improved AdaBoost Algorithms,” IEEE International Conference on Progress in Informatics and Computing, Shanghai, China, vol. 2, pp. 723–727, Dec. 2010.
[27] C. M. Bishop, Pattern Recognition and Machine Learning. New York, USA, Springer, 2006.
[28] R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. Michigen, USA: Wiley, 2001.
[29] E. Alpaydin (2010), Introduction to Machine Learning, 2nd ed. Cambridge, MA, USA: MIT Press.
[30] R. C. Gonzales and R. E. Woods (2007), Digital Image Processing, 2nd ed. New Jersey, USA: Prentice Hall, 2007.
[31] A. McAndrew, J. H. Wang, and C. S. Tseng, Introduction to Digital Image Processing with Matlab, Taipei, Taiwan: Cengage, 2010.
[32] Connected Component Labeling Algorithm – CodeProject, 2014. <http://www.codeproject.com/Articles/336915/Connected-Component-Labeling-Algorithm>, June 2015.
[33] C. Garcia and G. Tziritas, “Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis,” IEEE Transactions on Multimedia, vol. 1, no. 3, pp. 264–277, Sep. 1999.
[34] C. K. Chow and T. Kaneko, “Automatic Boundary Detection of the Left Ventricle from Cineangiograms,” Computers and Biomedical Research, vol. 5, no. 4, pp. 388–410, Aug. 1972.

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