簡易檢索 / 詳目顯示

研究生: 梁志中
Chih-chung Liang
論文名稱: 雙攝影機組的智慧型公共安全監控系統之設計
Design of Intelligent Public Security Surveillance System with Dual Camera Group
指導教授: 蔡超人
Chau-Ren Tsai
口試委員: 王乃堅
Nai-Jian Wang
蘇順豐
Shun-Feng Su
湯士滄
SHIH-TSANG TANG
學位類別: 碩士
Master
系所名稱: 電資學院 - 電機工程系
Department of Electrical Engineering
論文出版年: 2014
畢業學年度: 102
語文別: 中文
論文頁數: 103
中文關鍵詞: 遺留物遺失物人臉擷取DSP
外文關鍵詞: abandoned, stolen, depth distance for pedestrians, facial image
相關次數: 點閱:187下載:3
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 由於恐怖事件在世界各地持續的發生,近年來監控系統越來越被重視,但傳統的監控系統只有錄影與監控的功能,監控人員無法確切的知道場景中的可疑的物件或是發生事件時沒有發出警訊,因此本論文使用德州儀器(Texas Instrument)的數位訊號處理器TMS320DM642 DSP為開發平台,搭配雙組雙攝影機架構來組成一套智慧型公共安全監控系統。在雙攝影機架構下,其中場景攝影機主要用來偵測場景中的行人與遺留物或遺失物事件的發生,當場景中有發生事件時,PTZ (Pan/Tilt/Zoom)攝影機會擷取事件的關係人臉部影像,而本系統是使用雙組系統的架構,會利用此特性來針對場景中的事件關係人進行位置的追蹤,透過三維座標的公式可以計算出事件關係人的景深距離,如此一來就可以知道事件關係人在場景中的移動方向。最後本系統有開發一套使用者人機介面供監控人員作使用,透過使用者人機介面就可以看到雙組雙攝影機的即時影像以及發生事件時的相關影像,以實現具有遠端監控功能的雙攝影機組的智慧型公共安全監控系統。


    In recently years, monitoring system is more and more attention. Because terrorist attacks continue to occur around the world. But traditional monitoring systems only have Monitoring and video recording capabilities. Supervisors cannot accurately know a suspicious object in the scene or do not warn when an event occurs. In this paper, we use TI (Texas Instrument) digital signal processing TMS320DM642 development platform with two dual-cameras structure consisting of an intelligent public security surveillance system. In dual camera architecture, the field camera is used to detect pedestrians and abandoned or stolen events. PTZ camera will capture events related facial image when an event occurs in the scene. This system uses two dual-cameras system architecture. So we use this feature to track pedestrians in the scene. Through the three-dimensional coordinates of the formula can calculate depth distance for pedestrians. So we can know pedestrians movement direction in the scene. Finally, we have to develop a human interface for supervisors to use. Through human interface can see two dual-camera system real time image and related images when the event occurred. Thus, we achieve intelligent public security surveillance system with two dual-cameras.

    目錄 摘 要 I Abstract II 誌 謝 III 目 錄 IV 圖索引 VIII 表索引 XIV 第一章 緒論 1 1.1 研究動機與目的 1 1.2 研究方法 2 1.3 論文架構 3 第二章 系統架構 4 2.1 場景行人與物件分類程序 5 2.2 遺留物與遺失物分類程序 6 2.3 事件關係人追蹤程序 7 2.4 事件關係人臉部擷取程序 9 2.5 遠端監控使用者介面傳輸程序 10 2.6 硬體規格與環境架設 11 第三章 場景行人物件偵測與分類 17 3.1 前景區塊萃取 17 3.1.1 背景相減法 17 3.1.2 陰影濾除 20 3.1.3 雜訊濾除 22 3.2 行人區塊與物件區塊 24 3.2.1 物件標記 25 3.2.2 行人區塊與物件區塊分類 27 3.2.3 關聯性區域比對 28 3.2.4 場景行人交錯處理 29 第四章 遺留物事件與遺失物事件 39 4.1 遺留物與遺失物區塊偵測 39 4.2 遺留物與遺失物分類 41 4.2.1 偵測靜態目標物實際輪廓 41 4.2.2 比對靜態目標物輪廓色彩 43 第五章 事件關係人追蹤 46 5.1 找尋事件關係人 46 5.1.1 歷史影像建立與歷史影像吻合率 47 5.1.2 遺留物與遺失物事件關鍵影像 51 5.1.3 事件關係人偵測 52 5.2 事件關係人比對 53 5.2.1 行人位置順序編碼 54 5.2.2 傳遞行人參數 56 5.2.3 軌跡移動方向計算 57 5.2.4 確認相同事件關係人 59 5.3 事件關係人景深計算 64 第六章 事件關係人臉部擷取 67 6.1 建立頭部位置參考點 67 6.2 雙攝影機座標轉換與PTZ攝影機控制 69 6.3 擷取正面臉部影像與正臉影像正規化 .73 6.3.1 眼睛對搜尋 73 6.3.2 正規化擷取後的人臉影像 78 第七章 系統實現與效能測試 81 7.1 遠端監控使用者介面 81 7.1.1 網路傳輸架構 82 7.1.2 遠端使用者人機介面功能介紹 84 7.1.3 遠端使用者介面傳輸 85 7.2 系統實現 89 7.2.1 遺留物與遺失物事件實際運作方式 89 7.2.2 事件關係人景深位置的系統實現 91 7.3 系統效能 93 第八章 結論 96 8.1 研究成果 96 8.2 未來發展 100 參考文獻 101

    [1] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice-Hall, New Jersey, pp. 116-123, 2002.
    [2] J. P. Serra, Image Analysis and Mathematical Morphology, Academic Press, pp. 115-130, 1982.
    [3] B. Liu and H. Zhou, “Using Object Classification to Improve Urban Traffic Monitoring,” IEEE International Conference on Neural Networks & Signal Processing, Vol. 2, pp. 1155-1159, 2003.
    [4] P. Spagnolo, A. Caroppo, M. Leo, T. Martiriggiano and T. D’Orazio, “An Abandoned/Removed Objects Detection Algorithm and Its Evaluation on PETS Datasets,” IEEE International Conference on Video and Signal Based Surveillance, pp. 17-17, 2006.
    [5] R. L. Hsu, M. Abdel-Mottaleb and A. K. Jain, “Face Detection in Color Images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 5, pp. 696-706, 2002.
    [6] C. R. Wren, A. Azarbayejani, T. Darrell and A. Pentland. “Pfinder: Real-Time Tracking of the Human Body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp. 780-785, 1997.
    [7] I. Haritaoglu, D. Harwood and L. S. Davis, “W4: Real-Time Surveillance of People and Their Activities,”IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 8, pp. 809-830, 2000.
    [8] A. Prati, I. Mikic, M. M. Trivedi and R. Cucchiara, “Detecting Moving Shadows: Algorithms and Evaluation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 7, pp. 918-923, 2003.
    [9] S. J. McKenna, S. Jabri, Z. Duric, A. Rosenfeld and H. Wechsler, “Tracking Groups of People,” Computer Vision and Image Understanding, Vol. 80, No. 1, pp. 42-56, 2000.
    [10] 李建輝, “智慧型公共安全之遺留物體和遺失物體監控系統,” 國立台灣科技大學電機工程系碩士論文, pp. 14-68, 2009.
    [11] A. Rosenfield and M. Thurston, “Edge and Curve Detection for Visual Scene Analysis,” IEEE Transactions on Computation, Vol. 20, No. 5, pp. 562-569, 1971
    [12] 林裕超, “遠端影像監控之立體視覺目標物追蹤與量測系統,” 國立台灣科技大學電機工程系碩士論文, pp. 74-80, 2011.
    [13] Z. Jin, Z. Lou, J. Yang and Q. Sun, “Face Detection Using Template Matching and Skin-Color Information,” Neurocomputing, Vol 70, No. 4, pp. 794-800, 2007.
    [14] 陳昱宏, “智慧型公共安全之遺留物持有者和遺失物擷取者偵測,” 國立台灣科技大學電機工程系碩士論文, pp. 48-75, 2010.
    [15] F. Porikli, “Detection of Temporarily Static Regions by Processing Video at Different Frame Rates,” IEEE Conference on Video and Signal Based Surveillance, pp. 236-241, 2007.
    [16] E. Stringa and C. S. Regazzoni, “Real-Time Video Shot Detection for Scene Surveillance Applications,” IEEE Transactions on Image Processing, Vol. 9, No. 1, pp. 69-79, 2000.
    [17] M. Soriano, B. Martinkauppi, S. Huovinen and M. Laaksonen, “Adaptive Skin Color Modeling Using the Skin Locus for Selecting Training Pixels,” Pattern Recognition, Vol. 36, No. 3, pp. 681–690, 2003.

    QR CODE