臺灣博碩士論文加值系統

傳統的監視系統大部分都是人們需要坐在監控端前面盯著螢幕，監視時間一旦久了，注意力就會相對的不集中，同時會造成即使物體進入監視畫面也會不易發現的情況發生，進而造成許多的意外事故或社會案件的發生；因此本文提出一個可人臉偵測的智慧雲端監視架構的系統，希望藉由雲端的高運算能力來實現遠端監視系統人臉偵測，以降低人工監視之缺點。
在人臉偵測方面，本文使用了Apache公司所發展出來的軟體Hadoop，使用此軟體是因為Hadoop屬於分散式運算平台，其能有效的將數據量大的資料透過Map/Reduce的平行化處理方式，能比傳統的運算方式更加快速的將處理結果運算出來，對於人臉影像處理的速度有很大的幫助。
本論文主要發展一套以雲端為中心的智慧型監控系統；此雲端系統可分為三大部分，第一部分是CCD(Charge-Coupled-Device)攝影機控制端，負責傳送影像資料；第二部分為影像處理端，負責處理影像中偵測人臉的部分，處理後的人臉數據保留在伺服器中，而人臉偵測結果則透過第三部分網路應用伺服器來顯示。

Traditional surveillance systems are mostly people need to sit staring at the screen in front of monitoring terminal. Once a long time for staring at the screen, attention will be relatively non-centralized, and it will cause the situation happened that even objects into the monitor screen will be difficult to find, and then cause the emergence of a lot of contingencies or social cases. Therefore this thesis proposed a cloud-based intelligence surveillance system for face detection. In this system, the face detecting function of remote monitoring system can be achieved through the high computing ability of the cloud to reduce the shortcomings of manual monitoring.
In face detection, this research uses the Apache software developed by the company Hadoop, the reason for using this software is that Hadoop belong to a distributed computing platform,which can effectively process a large quantity of data through the Map/Reduce parallel processing mode, and the computing result is more fast than the traditional operation way, so it is very helpful for the face image processing speed.
The purpose of this thesis is to developa cloud-centric intelligent monitoring system. This cloud system can be divided into three parts. The first part is the CCD(Charge-Coupled-Device) camera control side, which is responsible for transmitting the image data. The second part is the image processing end, which is responsible for the image data computing of face detection, and the treated face data will be remained on the server. Finally, the third part is the network application server, which is used to display the face detecting results.

目錄
中文摘要----------------------------------------------------------------------------Ⅰ
英文摘要----------------------------------------------------------------------------Ⅲ
致謝----------------------------------------------------------------------------------Ⅴ
目錄----------------------------------------------------------------------------------Ⅵ
圖目錄-------------------------------------------------------------------------------Ⅷ
表目錄-------------------------------------------------------------------------------XI
第一章 緒論-----------------------------------------------------------------------01
1.1 前言-----------------------------------------------------------------------01
1.2 研究動機及目的--------------------------------------------------------02
1.3 論文架構-----------------------------------------------------------------03
第二章 人臉偵測技術概述-----------------------------------------------------04
2.1 簡介-----------------------------------------------------------------------04
2.2 影像處理技術-----------------------------------------------------------05
2.2.1 彩色影像轉灰階影像----------------------------------------05
2.2.2 影像濾波-------------------------------------------------------07
2.2.3 邊緣檢測與二值化-------------------------------------------07
2.2.4 外型影像運算-------------------------------------------------10
2.3 人臉偵測技術-----------------------------------------------------------12
2.3.1 膚色區域標定-------------------------------------------------13
2.3.2 橢圓頭部比對-------------------------------------------------17
2.3.3 人臉特徵偵測及定位----------------------------------------18
第三章 Hadoop技術概述-------------------------------------------------------25
3.1 簡介-----------------------------------------------------------------------25
3.2 Google與Hadoop-------------------------------------------------------25
3.3 Google MapReduce-----------------------------------------------------27
3.4 Google File System------------------------------------------------------28
3.4.1 BigTable--------------------------------------------------------30
3.5 Apache Hadoop----------------------------------------------------------31
3.6 Hadoop MapReduce-----------------------------------------------------32
3.6.1 JobNode與TaskNode-----------------------------------------34
3.7 Hadoop Distributed File System---------------------------------------35
3.7.1 NameNode與DataNode-------------------------------------36
3.7.2 HBase-----------------------------------------------------------37
第四章 可人臉偵測之智慧雲端監視系統實作-----------------------------39
4.1 系統架構-----------------------------------------------------------------39
4.2 CCD攝影機影像擷取端的實作--------------------------------------44
4.3 雲端影像處理的實作--------------------------------------------------49
4.4 瀏覽器觀看影像的實作-----------------------------------------------60
第五章 實驗結果-----------------------------------------------------------------63
5.1 簡介-----------------------------------------------------------------------63
5.2 軟硬體介紹--------------------------------------------------------------64
5.3 人臉偵測實驗-----------------------------------------------------------67
5.4 Hadoop運算測試結果-------------------------------------------------75
5.4.1單緒處理影像--------------------------------------------------76
5.4.2多緒處理影像-------------------------------------------------77
第六章 結論與未來展望--------------------------------------------------------79
參考文獻----------------------------------------------------------------------------81


圖目錄

圖2.1 彩色影像與灰階影像(a)彩色影像(b)灰階影像--------------------06
圖2.2 Sobel運算遮罩----------------------------------------------------------08
圖2.3 邊緣檢測結果圖(a)灰階圖(b)影像濾波圖(c)邊緣檢測圖
(d)二值化圖------------------------------------------------------------09
圖2.4 人臉偵測判斷流程圖--------------------------------------------------12
圖2.5 膚色統計範圍圖--------------------------------------------------------15
圖2.6 膚色區域標定結果-----------------------------------------------------16
圖2.7 橢圓偵測結果-----------------------------------------------------------17
圖2.8 嘴唇膚色示意圖--------------------------------------------------------19
圖2.9 嘴唇搜尋區域-----------------------------------------------------------20
圖2.10 眼睛搜尋區域-----------------------------------------------------------22
圖2.11 人臉最終判定結果圖(a)原始圖(b)人臉判定結果-----------------24
圖3.1 MapReduce流程圖------------------------------------------------------27
圖3.2 Hadoop Map/Reduce架構圖------------------------------------------33
圖3.3 JobNode與TaskNode關係圖-----------------------------------------34
圖3.4 NameNode與DataNode關係圖--------------------------------------37
圖4.1 系統架構圖--------------------------------------------------------------40
圖4.2 設定影像格式的Windows函式--------------------------------------41
圖4.3 設定影像格式的使用者介面-----------------------------------------41
圖4.4 Hadoop Image Processing流程圖------------------------------------44
圖4.5 設定callback function--------------------------------------------------44
圖4.6 callback function流程圖-----------------------------------------------45
圖4.7 callback function實作程式碼-----------------------------------------46
圖4.7 callback function實作程式碼(續)------------------------------------47
圖4.8 執行緒處理影像檔案傳輸到雲端流程圖--------------------------48
圖4.9 執行緒處理影像檔案傳輸到雲端之程式--------------------------48
圖4.9 執行緒處理影像檔案傳輸到雲端之程式(續)---------------------49
圖4.10 雲端的控制流程圖-----------------------------------------------------50
圖4.11 雲端的控制程式碼-----------------------------------------------------50
圖4.11 雲端的控制程式碼(續)------------------------------------------------51
圖4.11 雲端的控制程式碼(續)------------------------------------------------52
圖4.12 Hadoop Image Processing流程圖------------------------------------53
圖4.13 Map的程式碼------------------------------------------------------------54
圖4.14 Reduce的程式碼--------------------------------------------------------55
圖4.15 faceDetection程式碼---------------------------------------------------56
圖4.15 faceDetection程式碼(續)----------------------------------------------57
圖4.15 faceDetection程式碼(續)----------------------------------------------58
圖4.16 瀏覽器流程圖-----------------------------------------------------------60
圖4.17 時間表單的程式碼-----------------------------------------------------60
圖4.17 時間表單的程式碼(續)------------------------------------------------61
圖4.18 人臉偵測結果按鈕的程式碼-----------------------------------------61
圖4.19 網頁監視影像的選單--------------------------------------------------62
圖4.20 網頁完整畫面-----------------------------------------------------------62
圖5.1 Camera端控制模組硬體-----------------------------------------------64
圖5.2 雲端影像處理模組硬體-----------------------------------------------65
圖5.3 影像監視模組硬體-----------------------------------------------------66
 
圖5.4 設備檢視影像之畫面(a)平板影像之畫面(b)桌機影像之畫面
(c)手機影像之畫面(d)筆電影像之畫面-----------------------------66
圖5.5 純人臉偵測結果--------------------------------------------------------68
圖5.6 戴眼鏡之人臉偵測結果-----------------------------------------------70
圖5.7 戴帽子之人臉偵測結果-----------------------------------------------72
圖5.8 戴帽子之人臉偵測結果-----------------------------------------------74
圖5.9 單緒處理結果曲線圖--------------------------------------------------76
圖5.10 多緒處理結果平均曲線圖--------------------------------------------78

表目錄

表3.1 Hadoop與Google架構比較-------------------------------------------26
表4.1 索引檔案的格式--------------------------------------------------------43
表5.1 純人臉偵測實驗結果--------------------------------------------------69
表5.2 戴眼鏡之人臉偵測實驗結果-----------------------------------------71
表5.3 戴帽子之人臉偵測實驗結果-----------------------------------------73
表5.4 人臉偵測實驗結果-----------------------------------------------------75
表5.5 單緒處理結果-----------------------------------------------------------76
表5.6 多緒處理結果-----------------------------------------------------------77

參考文獻
[1]張英傑，智慧型監視系統之多人人臉即時循序偵測及追蹤，崑山科技大學電機工程系，碩士論文，民國95年
[2]P. Goolkasian,“Processing Visual-Stimuli Inside and Outside the Focus Fattention”,Bulletin of the Psychonomic Society, vol. 29,1991,pp.510-515.
[3]蔡博智，影像追蹤方法應用在監控系統之研究，中原大學機械工程學系碩士論文，民國91年。
[4]黃敏峰，人臉追蹤法應用於監視系統之研究，成功大學電機工程學系，碩士論文，民國92年。
[5]NovQinlu He,Zhanhuai Li’Xiao Zhang, “Study on Cloud StorageSystem based on Distributed Storage Systems”, Computational andInformation Sciences( ICCIS), 17-19 Dec 2010, pp. 1332 – 1335.
[6]Kevin D.Bowers,Ari Juels, and Alina Oprea., “HAIL: A HighAvailabilityand Integrity Layer for Cloud Storage”, Computer and communicationssecurity (CCS), Nov 2009, pp. 187-198.
[7]Mingyue Luo,Gang Liu, “Distributed log information processing withMap-Reduce: A case study from raw data to final models”,Information Theory and Information Security(ICITIS), 17-19 Dec. 2010,pp.1143-1146.
[8]Afrati, Foto N. Ullman, Jeffrey D., “Optimizing Multiway Joins in aMap-Reduce Environment”, IEEE Transactions on Knowledge and DataEngineering, vol. 23, Issue. 9, Sept. 2011, pp. 1282-1298
[9]Chen Zhang ,De Sterck, H.,”CloudBATCH: A Batch Job QueuingSystem on Clouds with Hadoop and HBase”, Cloud ComputingTechnology and Science (CloudCom), Nov. 30 2010-Dec. 3 2010, pp.368-375.
[10]Jorda Polo, David Carrera, Yolanda Becerra, Malgorzata Steinder, andIan Whalley., “Performance-driven task co-scheduling for mapreduceenvironments”, Network Operations and ManagementSymposium(NOMS), 19-23 Apr 2010, pp.373 –380.
[11]Thomas Sandholm and Kevin Lai., “Dynamic proportional sharescheduling in hadoop”, Job Scheduling Stragies For Parallel Processing(JSSPP), vol. 6253, 2010, pp. 110-131.
[12]R. C. Gonzalez and R. E. Woods 原著，謬紹綱譯，”數位影像處理”，台灣培生教育出版，2004年10月初版
[13]L. G. Shapiro, G. C. Stockman, Computer Vision, pp.65-68, Prentice –Hall,NJ,2001.
[14]M. Soriano, S. Huovinen, B. Martinkauppi, M. Laaksonen,“Using the Skin Locus to Cope with Changing illumination Condition in Color-Based Face Tracking”, Proc. of IEEE Nordic Signal Processing Symposium, 2000, pp.383-386.
[15]Birchfield S., “Elliptical head tracking using intensity gradients and color histograms”,Dept. of Comput. Sci., Stanford Univ., CA, USA, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998, pp.232-237.
[16]Birchfield S., “”, Dept. of Comput. Sci., Stanford Univ., CA,USA, Conference Record of the Thirty-First Asilomar Conference on Signals Systems & Computers, 1997, pp.1710- 1714.
[17]Sulivan J., Blake A.,Isard M., MacCormick J.,“ Object Localization by Bayesian Correlation”, Dept . of Eng. Sci., Oxford Univ., UK, The Proceedings of the Seventh IEEE International Conference on Computer Vision,1999,pp.1068-1075
[18]Chiunhsiun Lin, Kuo-Chin Fan,“Human face detection using geometric triangle relationship”,Inst. of Comput. Sci. & Inf. Eng., Nat. Central Univ., Chung-Li,Taiwan, 15th International Conference on Pattern Recognition, 2000, pp.941-944.
[19]黃泰祥，具備人臉追蹤與辨識功能的一個智慧型數位監視系統，中原大學電子工程學系碩士論文，民國93年。
[20]郭玲裳，基於MapReduce的影像處理系統加入DSRF優先權排成機制，淡江大學電機工程學系碩士論文，民國101年
[21]S. Birchfield, “Elliptical Head Tracking Using Intensity Gradients and Color Histograms”, Dept. of Comput. Sci., Stanford Univ., CA, USA, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998, pp.232-237.
[22]J. Sulivan, A. Blake, M. Isard and J. MacCormick, “Object Localization by Bayesian Correlation”, Dept. of Eng. Sci., Oxford Univ., UK, The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999, pp.1068- 1075.
[23]黃建邦，彩色視覺技術於多人人臉辨識上的應用，崑山科技大學電機工程系，碩士論文，民國94年