跳到主要內容

臺灣博碩士論文加值系統

(35.172.136.29) 您好!臺灣時間:2021/07/29 07:23
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

: 
twitterline
研究生:孫伊廷
研究生(外文):Sun, I-Ting
論文名稱:混合式編碼簿模型於監視系統應用
論文名稱(外文):Hybrid Codebook Model for the Surveillance System Application
指導教授:黃仲陵黃仲陵引用關係
指導教授(外文):Huang, Chung-Lin
學位類別:碩士
校院名稱:國立清華大學
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:2010
畢業學年度:99
語文別:英文
論文頁數:80
中文關鍵詞:編碼簿模型陰影去除相似性比對剪影切割
外文關鍵詞:Codebook ModelShadow RemovalCorrespondence MatchingBlob Partition
相關次數:
  • 被引用被引用:1
  • 點閱點閱:196
  • 評分評分:
  • 下載下載:14
  • 收藏至我的研究室書目清單書目收藏:0
有鑒於電腦網路的發達,影像監視系統越來越受到人們的注意,一個影像監視系統的好壞取決於很多外界以及內部的因素,除了硬體的考量之外,內部演算法的效能更是主宰偵測結果的重要因素。
在電腦視覺領域人物資訊追蹤是一個相當困難的題目,其中人物偵測在影像監視系統上為很重要的基礎,例如人員計數與徘徊偵測等等。我們將主題著重在人員計數。首先,參考幾個效果不錯的編碼簿模型,利用我們所提出的修改式的編碼簿模型,可以萃取出偵測的人物範圍以及資訊。此外,我們加上一個修改式的陰影去除法以去除光影變化所造成的干擾,勝過於傳統編碼簿模型的判別準則。相較於廣泛的追蹤演算法,我們不需假設人員進入畫面為各自獨立無遮蔽,在現實應用上面,影像監控系統常用在人群擁擠的區域,因此我們需要重視人與人間遮蔽的問題。分析人物間運動的情形,我們整理出一個廣義的狀態轉變圖,解釋了所有可能發生的狀態,我們將人物偵測分成是否可分離與合併或確定分開的狀態幾個可能發生的事件,將這些發生事件建立一個狀態迴路,藉此可以結合最佳比對的方式以五個處理方式來完成,並去統計所有畫面的估計人數,估計人數的準則可以依照前面建立好的事件流程序列來加以判別對應的處理動作,基於一些狀態的分析邏輯判別。最後在我們的實驗中,我們測試了幾個不同條件下的影片,並提出三種分析計數結果好壞的判斷數值,來證明我們所提出的方法對於不同環境下人員計數的應用上都具有一定的效用。
The human objects detection is an important basis to many applications, such as the people counting and the loitering detection. We focus on the topic of the people counting. First of all, we extract the human objects depending on our proposed modified codebook model. Besides, we add a modified shadow removal method to overcome the illumination effect. In opposition to the wide tracking algorithms, we find the best correspondence in the history to solve the matching problem. We do not need to assume that people entering the scene are individual. In reality, the surveillance system is usually set in the crowded area, and we should concentrate on the occlusion problem. We classify the object detection into different steps and accumulate total number from the estimate number of each frame. In our experiments, we test our system to different conditions and it is effective to the people counting.
CHAPTER 1 Introduction..........................................................................................1
1.1 Motivation.......................................................................................................1
1.2 Related Works................................................................................................1
1.3 System Overview............................................................................................8
1.4 Organization of this Thesis...........................................................................9
CHAPTER 2 Human Objects Extraction................................................................10
2.1 Review the Codebook Model.......................................................................10
2.1.1 Basic Codebook Model.....................................................................10
2.1.2 Codebook Construction and Update Algorithms...........................14
2.1.3 Background Subtraction with Codewords Addition an Deletion Technologies................................................................................................16
2.2 Modify the Traditional Codebook Model..................................................18
2.2.1 Drawbacks of the Traditional Codebook Model............................18
2.2.2 Modified Decision Boundary...........................................................20
2.3 Modify the Traditional Shadow Filter.......................................................21
2.3.1 Motivation and the Traditional Shadow Filter...............................21
2.3.2 Improvements of the Shadow Filter................................................23
2.4 Hybrid Codebook Model.............................................................................28
2.4.1 Similarity Decision............................................................................28
2.4.2 Cache Codebook and Codebook Update........................................29
2.4.3 Hybrid Codebook Model..................................................................31
2.5 Silhouette Repairing and Noise Filtering...................................................36
2.5.1 Morphological Processing................................................................36
2.5.2 Pixel Neighbors Statistics.................................................................36
CHAPTER 3 Object Counting.................................................................................38
3.1 Phenomenon of the Object Counting.........................................................38
3.2 Basic Correspondence Matching System...................................................40
3.2.1 Multiple Objects Correspondence Problem...................................40
3.2.2 Feature Selection...............................................................................41
3.2.3 Feature Distance................................................................................43
3.2.4 Maximum Probability Matching Algorithm..................................44
3.3 Occlusion Issue.............................................................................................48
3.3.1 Blob Partition....................................................................................48
3.3.2 Partition Correction..........................................................................53
3.3.3 Matching Correction........................................................................53
3.3.4 Counting Correction.........................................................................55
3.3.5 Object Counting................................................................................59
CHAPTER 4 Application and Experiment..............................................................61
4.1 Input Video Pre-processing.........................................................................61
4.2 Data Introduction and Experiment Environment....................................62
4.3 Interface Introduction.................................................................................62
4.4 People Counting...........................................................................................64
4.1.1 Evaluate Performance......................................................................64
4.1.2 Side Moving Direction......................................................................65
4.1.3 Front and Reverse Direction............................................................69
4.5 Loitering Detection......................................................................................72
4.6 Combination Testing....................................................................................73
CHAPTER 5 Conclusion and Future Work............................................................77
References...................................................................................................................78
[1] D. Koller, J. Weber, T. Huang, J. Malik, G. Ogasawara, B. Rao, and S. Russell, “Toward Robust Automatic Traffic Scene Analysis in Real-Time,” In Proc. Int. Conf. Patt. Recog., pp. 126-131, 1994.
[2] C.R. Wren, A. Azarbaygaui, T. Darrel, and A.P. Pentland, “Pfinder: Real-Time Tracking of the Human Body,” In IEEE Trans. Pattern Anal. Machine Intelligence, vol. 19(7), pp. 780-785, July 1997.
[3] I. Haritaoglu, D. Harwood, and L.S. Davis, “W4: Who? When? Where? What? A Real Time System for Detecting and Tracking People,” In International Conference on Automatic Face and Gesture Recognition, Nara, Japan, 1998.
[4] S.J. McKenna, S. Jabri, Z. Duric, and H. Wechsler, “Tracking Interacting People,” In International Conference on Automatic Face and Gesture Recognition, Grenoble, France, March 2000.
[5] C. Stauffer and W.E.L. Grimson, “Learning patterns of activity using real-time tracking,” In IEEE Trans. Pattern Anal. Machine Intell., vol. 22, pp. 747-757, Aug. 2000.
[6] D. Comaniciu, V. Ramesh, and P. Meer, “Real-Time Tracking of Non-Rigid Objects Using Mean Shift,” In Proc. Conf. Comp. Vision Pattern Rec., pages II: 142-149, Hilton Head, SC, June. 2000.
[7] Y. Boykov, and M.-P. Jolly, “Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images,” In Proc. of the International Conference on Computer Vision, vol. 1, 105-112, 2001.
[8] E. Durucan and T. Ebrahimi, “Change Detection and Background Extraction by Linear Algebra,” In Proc. IEEE, vol. 89, pp. 1368-1381, Oct. 2001.
[9] L. Li, and M. K. H. Leung, “Integrating Intensity and Texture Differences fir Robust Change Detection,” In IEEE Trans. Image Process., vol. 11, pp. 105-112, Feb. 2002.
[10] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati, “Detecting Moving Objects, Ghosts and Shadows in Video Streams,” In IEEE Trans. Patt. Anal. Mach. Intell, 25(10): 1337-1342, 2003.
[11] A. Prati, I. Mikic, M.M. Trivedi, and R. Cucchiara, “Detecting Moving Shadows: Algorithms and Evaluation,” In IEEE Trans. Pattern Anal. Mach. Intell., 25(7): 918-923, 2003.
[12] K. Nummiaro, E. Koller-Meier, and L.V. Gool, “An Adaptive Color-Based Particle Filter,” In Image and Vision Computing, vol. 21, issue 1, pp. 99-110, Jan. 2003.
[13] H. Sidenbladh, “Detecting Human Motion with Support Vector Machines,” In International Conference on Pattern Recognition, Cambridge, U.K., Aug. 2004.
[14] K. Kiratiratanapruk, P. Dubey, and S. Siddhichai, “A Gradient-Based Foreground Detection Technoque for Object Tracking in a Traffic Monitoring System,” In Proc. of AVSS, pp. 377-381, Sept. 2005.
[15] K. Kim, T.H. Chalidabhongse, D. Harwood, and L. Davis, “Real-Time Foreground-Background Segmentation Using Codebook Model,” Real-Time Imag. 11(3), 172-185, 2005.
[16] E. Maggio and A. Cavallaro, “Hybrid Particle Filter and Mean Shift Tracker with Adaptive Transition Model,” In Proc. of IEEE International Conf. on Acoustics, Speech, and Signal Processing, Philadelphia, 2005.
[17] J. Yao, and J.M. Odobez, “Multi-Layer Background Subtraction Based in Color and Texture,” In IEEE Conference on Computer Vision and Pattern Recognition, Washington, pp. 1-8, 2007.
[18] N. Martel-Brisson, and A. Zaccarin, “Learning and Removing Cast Shadows Through a Multidistribution Approach,” In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, pp. 1133-1146, 2007.
[19] M. Xiao, C. Han, and L. Zhang, “Moving Shadow Detection and Removal for Traffic Sequences,” In International Journal of Automation and Computing, vol. 4, no. 1, pp. 38-46, 2007.
[20] J. Wood, “Statistical Background Models with Shadow Detection for Video Based Tracking,” Linkoping University, SE-581 83 Linkoping, Sweden, March, 2007, LiTH-ISY-EX-07/3921-SE.
[21] B. Wu and R. Nevatia, “Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination Of Edgelet Based Part Detectors,” In International Journal of Computer Vision, 75(2): 247-266, 2007.
[22] A. Ilyas, M. Scuturici, and S. Miguet, “Real-Time Foreground-Background Segmentation Using a Modified Codebook Model,” In Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, pages 454-459, 2009.
[23] Z. Lin, and L.S. Davis, “Shape-Based Human Detection and Segmentation via Hierarchical Part-Template Matching,” In IEEE Trans. Pattern Anal. Mach. Intell., 32(4): 604-618, 2010.
[24] AVSS2007 Abandoned Baggage Scenario, “http://www.eecs.qmul.ac.uk/~andrea /avss2007_d.html”.
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
1. 張卿卿(2002)。〈競選媒體使用對選民競選議題知識與政治效能感的影響—以兩千年台灣總統大選為例〉,《選舉研究》,9(1): 1-39
2. 張依依、封國晨(2008)。〈從「反貪腐倒扁運動」檢視其框架策略與議題建構〉,《傳播與社會學刊》,5: 101-127。
3. 翁秀琪(1997)。〈消息來源策略研究-探討中時、聯合對婦運團體推動民法親屬編修法的報導〉,《新聞學研究》,52: 121-148。
4. 翁秀琪(1994)。〈我國婦女運動的媒介真實和「社會真實」〉。《新聞學研究》,48: 193-236。
5. 孫秀蕙(1993)。〈台灣電視新聞在政治民主化過程扮演的角色〉,《傳播文化》,2:103-109。
6. 胡幼偉、鄭麗琪(1999)。〈網路選舉資訊使用者素描:社會背景、政治參與及傳播行為的多面向觀察〉,《理論與政策》,13(3):65-87。
7. 王泰俐(2006)。〈電視新聞「感官主義」對閱聽人接收新聞的影響〉,《新聞學研究》,86期,頁91-133。
8. 劉惠卿(2009)。〈電視報導新聞議題之政黨偏差研究-以TVBS-N與SET-N報導 312 維新館事件為例〉,《傳播與管理研究》,9(1):33-64。
9. 劉念夏(2002)。〈民意調查與民意產製:一個框架理論的觀點〉,《新聞學研究》,72:173-205。
10. 臧國仁、鍾蔚文、楊怡珊(2001)。〈新聞記者的社會智能:再論記者與消息來源之互動〉。《新聞學研究》,69,55-94。
11. 臧國仁(1998)。〈新聞報導與真實建構:新聞框架理論的觀點〉,《傳播研究集刊》,3,1-102。
12. 黃惠萍(2005)。〈審議式民主的公共新聞想像:建構審議公共議題的新聞報導模式〉,《新聞學研究》,83: 39-81。
13. 黃惠萍(2003)。〈媒介框架之預設判準效應與閱聽人的政策評估-以核四案為例〉,《新聞學研究》,77: 67-105。
14. 陳憶寧、羅文輝(2010)。〈媒介使用與政治資本〉,《新聞學研究》,88: 83-134。
15. 陳憶寧(2004)。〈媒體議題與公眾議題演化過程之探討:以2002年台北市長選舉為例〉,《新聞學研究》,81: 125-162。