臺灣博碩士論文加值系統

由於近年來恐怖攻擊事件頻傳，已有許多國家正致力於開發影像監控系統來提高現有監控系統的人力有效性，在過去的相關文獻中，大多針對如何在場景中偵測遺留物與遺失物做相關的研究，而本研究中所發展的自動擷取事件觸發者之臉部資訊的監控系統，不僅能找出遺留物或遺失物事件的遺留物持有者與遺失物擷取者，並記錄事件發生時的關鍵性影像，同時也會擷取該事件觸發行人的較清晰臉部特徵資訊，能與監控方事先建立的危險人臉資料庫做比對，大幅提升影像監控系統的保全性。此系統使用德州儀器(Texas Instrument)之TMS320DM642 DSP為開發平台與雙攝影機架構，由場景攝影機搭配PTZ(Pan, Tilt, Zoom)攝影機，經由場景攝影機所擷取的畫面資訊，可以偵測出場景中的遺留物與遺失物，並經由座標轉換方式將PTZ攝影機引導至事件觸發者的頭部位置，擷取較清晰的臉部特徵資訊。遠端監控人員也可以隨時透過遠端監控介面，了解場景中的特徵狀況，也可以操作遠端監控介面，觀看與控制雙攝影機的場景資訊。如此便能達到智慧型自動擷取遺留物持有者與遺失物擷取者的臉部資訊之監控系統。

Due to the terrorist attacks is frequently in recent years, many countries have been developing video surveillance systems. They are working to improve the effectiveness of human resource on existing surveillance system. Over the past literatures, mostly were researched on how to detect abandoned objects and stolen objects. In this research, we develop a surveillance system to automatically capture information about the target pedestrians’ face. It’s not only to detect the owner of abandoned object and stolen object, but also record the critical event’s image. In addition, the surveillance system can capture the clear face that is who trigger off event, and compare to the dangerous face database. Let's enhance the security of the video surveillance system. Therefore, we will combine TI TMS320DM642 evaluation module with dual-camera module that can detect owner of abandoned object and stolen object. The field camera is responsible for detecting the head reference point of owner of abandoned and stolen object. Via coordinate’s transformation, the PTZ camera can be guided to the target pedestrians’ head zone and capture the facial information. Consequently, the surveillance can monitor the environment remotely via the internet transmission. They can also select for many functions in the user interface. Hence, we develop an intelligent public surveillance system can detect the ownership's face of abandoned object and stolen object.

摘 要
Abstract
誌 謝
目 錄
圖索引
表索引

第一章 序論
1.1 研究動機與目的
1.2 研究方法
1.3 論文架構

第二章 系統架構
2.1 場景行人與物件分類程序
2.2 遺留物與遺失物分類程序
2.3 遺留物持有者與遺失物擷取者偵測程序
2.4 目標行人臉部資訊擷取與辨識程序
2.5 遠端監控介面傳輸程序
2.6 硬體規格與配置

第三章 場景物件偵測與分類
3.1 前景區塊萃取
3.2 影像前置處理
3.2.1 混合式陰影濾除
3.2.2 形態學處理
3.2.3 物件標記
3.3 行人與物件分類
3.4 行人標記與追蹤
3.4.1 關聯性區域比對
3.4.2 行人追蹤之標記處理

第四章 遺留物事件與遺失物事件
4.1 遺留物與遺失物分類
4.1.1 靜態目標物偵測
4.1.2 靜態目標物實際輪廓之建立
4.1.3 邊緣輪廓色彩比對
4.1.4 重複性遺留與遺失事件偵測
4.2遺留物持有者與遺失物擷取者偵測
4.2.1 歷史影像建立與吻合率
4.2.2 遺留與遺失關鍵性
4.2.3 遺留物持有者與遺失物擷取者偵測

第五章 目標行人臉部資訊擷取
5.1 頭部參考點之建立
5.1.1區塊分割
5.1.2 頭部偵測
5.2 頭部參考點之追蹤
5.3 雙攝影機座標轉換與PTZ攝影機追蹤控制
5.4 臉部資訊之擷取
5.4.1 眼睛對偵測
5.4.2 臉部資訊擷取

第六章 人臉辨識
6.1 灰階不變性
6.2 搜尋遮罩之建立
6.3 區域二元圖樣直方圖模型之建立
6.3.1 區域二元圖樣法
6.3.2 具有門檻的區域二元圖樣法
6.4 卡方距離量測
6.5 實驗結果

第七章 系統實現與效能測試
7.1 程式軟體架構
7.2 遠端監控介面
7.2.1 網路傳輸
7.2.2 遠端監控介面畫面配置
7.2.3 遠端監控介面功能介紹
7.3 系統實現
7.4 效能測試

第八章 結論
8.1 研究成果
8.2 未來發展方向

參考文獻

[1] 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, pp. 780-785, 1997.

[2] 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.

[3] A. J. Lipton, H. Fujiyoshi and R. S. Patil, “Moving Target Classification and Tracking from Real-Time Video,” Proceedings of the IEEE Workshop Applications of Computer Vision, pp. 8-14, 1998.

[4] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice-Hall, New Jersey, pp. 116-123, 2002.

[5] 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.

[6] R. Cucchiara, C. Grana, M. Piccardi and A. Prati, “Detection Moving Objects, Ghosts, and Shadows in Video Streams,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.25, No.10, pp.1337-1342, 2003.

[7] J. P. Serra, Image Analysis and Mathematical Morphology, Academic Press, pp. 115-130, 1982.

[8] Liu Bo and Zhou Heqin, “Classification To Improve Urban Traffic Monitoring using,” IEEE Int. Conf. Neural Networks & Signal Processing, December 14-17, 2003.

[9] 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.

[10] E. Stringa and C. S. Regazzoni, “Real-Time Video Shot Detection for Scene Surveillance Applications,” IEEE Transactions on Image Processing, pp. 69-79, 2000.

[11] P. Spagnolo, A. Caroppo, M. Leo, T. Martiriggiano and T. D’Orazio, “An Abandoned/Removed Objects Detection Algorithm and Its Evaluation on PETS Datasets,” Video and Signal Based Surveillance, pp. 17-17, 2006.

[12] W. Lu and Y. Tan, “A Color Histogram Based People Tracking System,” Proceedings of the IEEE International Symposium on Circuit and Systems 2, pp.137-140, 2001.

[13] S. J. McKenna, S. Jabri, Z. Duric, A. Rosenfeld and H. Wechsler, “Tracking Groups of People,” Computer Vision and Image Understanding, Vol. 80, pp. 42-56, 2000.

[14] A. Rosenfield and M. Thurston, “Edge and Curve Detection for Visual Scene Analysis,” IEEE Transactions on Computation, Vol. C-20, pp.562-569, 1971.

[15] 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， 民國九十八年六月。

[16] 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， 民國九十九年六月。

[17] S. Park and J.K. Aggarwal, “Segmentation and Tracking of Interacting Human Body Parts under Occlusion and Shadowing,” Proc. IEEE Workshop Motion and Video Computing, pp. 105-111, 2002.

[18] M. Soriano, B. Martinkauppi, S. Huovinen and M. Laaksonen, “Adaptive Skin Color Modeling Using the Skin Locus for Selecting Training Pixels,” Pattern Recogn 36, pp. 681–690, 2003.

[19] Z. Jin, Z. Lou, J. Yang and Q. Sun, “Face Detection Using Template Matching and Skin-Color Information,” Neurocomputing, Vol 70, pp. 794-800, 2007.

[20] Timo Ahonen, Abdenour Hadid and Matti Pietikainen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 28, pp. 2037-2041, 2006.

[21] T. Ojala, M. Pietikainen and T. Maenpaa, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, pp. 971-987, 2002.

[22] J.Meng, U. Gao, and X. Wang, “Face Recognition Based on Local Binary Patterns with Threshold,” IEEE International Conference on Granular Computing, pp. 352-356, 2010.

[23] Texas Instruments Inc., Reference Framework for eXpressDSP Software : RF5, An Extensive, High-Density System, April 2003.

[24] Texas Instruments Inc., Reference Framework for eXpressDSP Software : API Reference, April 2003.