臺灣博碩士論文加值系統

本論文之「即時熱影像監測系統之研究」主題為在居家大樓或工廠廠區內架設紅外線熱影像視覺偵測系統，並發展影像自動識別技術，以針對不明入侵之異物或火災自動監測、辨識和預警，能自動辨識之入侵異物包括電器、動物和人體，而對火災之偵測，希望當火災剛在悶燒煙霧瀰漫還未蔓延開來時，能及時預警將火撲滅，達到預防火災發生效果。本論文透過統計技術，將時間和空間影像以統計方式萃取特徵值，降低影像資料處理的複雜度。這些空間影像之特徵值當作一類神經網路歸類器之輸入，此類神經網路系統可透過訓練自動調整隱藏層RBF神經元之所有參數，包括輸出權重值（Output weights）、中心值（Centers）和寬度（Widths），以加速收斂速度和降低近似誤差，且能摒除外在環境干擾擁有強健之辨識可靠度。最後我們建立一實際之熱影像監視系統，以驗證本文所提方法之有效性。

This paper develops an on-line home security system for factory or building by using infrared thermal imaging. Through recognition techniques, this home security system could automatically inspect and classify intruders, including electric equipment, human, animals, and fires, such that burglars and fires can be found early and prevented beforehand. The statistical- geometric techniques are employed to extract features of temporal and spatial images, which are used as inputs of a neural-network classificator. Training algorithms are employed to tune all parameters in the neural network, including the output weights, the widths, and the centers of hidden nodes, thereby accelerating the learning convergence and improving the approximation accuracy. Finally, a practical home security system by infrared thermal imaging will be build to show that the proposed method has high accuracy in recognition.

目錄

封面內頁
簽名頁
授權書 iii
中文摘要 v
英文摘要 vi
誌謝 vii
目錄 viii
圖目錄 x
表目錄 xiv

第一章　緒論 01
1.1 研究動機與目的 01
1.2 文獻回顧 02
1.3 研究方法 04
1.4 論文大綱 04
第二章　即時熱影像監測系統之架構 06
2.1 熱影像的介紹 06
2.2 熱影像與數位CCD攝影機之優缺點 08
2.3 熱影像視覺系統硬體架構 09
第三章　影像辨識架構 11
3.1 影像辨識流程 11
3.2 建立背景 12
3.3 影像前處理(濾波、二質化) 15
3.4 移動體的移動能量和移動史跡的介紹 21
3.5 影像型態學 26
3.6 影像Sobel 30
3.7 影像相連通 32
3.8 特徵值的擷取 36
3.8.1 求其辨識物的周長面積比(p1) 37
3.8.2 統計之幾何慣性(Moments)法則 39
3.8.3 求亂度周長比(p2) 40
3.8.4 求影像史跡圖之長寬比(p3)、影像能量圖之長寬比(p4) 44
第四章　類神經網路系統之應用 47
4.1 RBF類神經網路架構 47
4.2系統參數之訓練 49
4.2.1 遞迴式最小平方法 49
4.2.2 倒傳遞訓練法則 50
第五章　實驗與結果 52
第六章　結論與未來研究方向 67
參考文獻 68

參考文獻

[1] M. Moganti and F. Ercal, “Automatic PCB Inspection Systems”, IEEE Potentials, Vol. 14, Iss.3, pp. 6-10, 1995.
[2] M. David L. Jackson, “The Emergence of Air Force Material Command and Automatic Test Equipment (ATE) Acquisition”, IEEE AUTOTESTCON, pp. 363-367, 1991.
[3] 劉殿斌，“熱影像技術應用於偵測電子線路板上故障元件之研究”，國立成功大學工程科學系，碩士論文，八十六年度。
[4] K. Mabuchi, T. Chinzei, I. Fujimasa, S. Haeno, K. Motomura, Y. Abe and T. Yonezawa, “Evaluating Asymmetrical Thermal Distributions Through Image Processing.”, IEEE Engineering in Medicine and Biology Magazine, Vol. 17, pp. 47-55, 1998.
[5] 陳惠峰，“應用零碎維度分析皮膚真皮層微血管血液流量分佈之研究”，國立成功大學醫學工程學系，碩士論文，八十一年度。
[6] 吳俊毅，“熱分佈影像分析及其臨床應用”， 國立中興大學土木工程學系，碩士論文，八十三年度。
[7] N. Hou, “The Infrared Thermography Diagnostic Technique of High-voltage Electrical Equipments with Internal Faults”, IEEE International Conference on Power System Technology, Beijing China, 1998.
[8] S.A. Merryman and R.M. Nelms, “Diagnostic Technique for Power Systems Utilizing Infrared Thermal Imaging”, IEEE Transactions on Industrial Electronics, Vol. 42, No. 6, pp. 615-628, 1995.
[9] M. Kagesawa, S. Ueno, K. Ikeuchi, and H. Kashiwagi, “Recognizing Vehicles in Infrared Images Using IMAP Parallel Vision Board”, IEEE Transactions on Intelligent Transportation Systems, Vol. 2, No. 1, pp. 10-17, 2001.
[10] A.F. Bobick, J.W. Davis, “The Recognition of Human Movement Using Temporal Templates, “ IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 3, pp. 257-267, 2001.
[11] Y. Ricquebourg and P. Bouthemy, “Real-time Tracking of Moving Persons by Exploiting Spatio-temporal Image Slices”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 8, pp. 794-808, 2000.
[12] T. Zhao and R. Nevatia, “Tracking Multiple Humans in Complex Situations”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 9, pp. 1201-1208, 2004.
[13] R.D. Green and L. Guan, “Quantifying and Recognizing Human Movement Patterns from Monocular Video Images—part I: A New Framework for Modeling Human Motion”, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 14, No. 2, pp. 179-190, 2004.
[14] 胡晉維，“自動化影像偵測系統在人形目標物之分析”，國立交通大學機械工程研究所，碩士論文，九十一學年度。
[15] Y.S. Chung and H.V. Le, “Detection of Forest-fire Smoke Plumes by Satellite Imagery”, Atmos. Environ, Vol.18, pp. 2143-2151, 1984.
[16] T. Randriambelo, S. baldy, M. Besafi, M. Petit, and M. Despinoy, “An Improved Detection and Characterization of Active Fires and Smoke Plumes in South-eastern Africa and Madagascar”, Int. J. Remote Sensing, Vol. 19, pp. 2623-2638, 1998.
[17] D.Ebert, W. Carlson, and R. Parent, “Solid Spaces and Inverse Particle Systems for Controlling the Animation of Gases and Fluids”, The Visual Computer, Vol. 10, No. 4, pp. 179-190, 1994.
[18] B.J. Ziv, E.Y. Ran, L. Dani, and W. Michael, “ Texture Mixing and Texture Movie Synthesis Using Statistical Learning”, IEEE trans. On Visualization and Computer Graphics, Vol. 7, No. 2, pp. 120-135, 2001.
[19] B.C. Arrue, A. Ollero, and J. Ramiro, “An Intelligent System for False Alarm Reduction in Infrared Forest Fire Detection” IEEE Intelligent Systems, pp. 64-73, 2000.
[20] S.Y. Foo, “A Fuzzy Logic Approach to Tire Detection in Aircraft Dry Bays and Engine Compartment”, IEEE Transactions on Industrial Electronics Vol.47, pp. 1161-1171, 2000.
[21] 鄭光宏，“應用影像視覺於超薄型表面載式電感器之線上自動檢測”，大葉大學機電自動化研究所，碩士論文，九十二學年度。
[22] 鍾國亮 教授，2002，影像處理與電腦視覺第二版，東華書局。