現在位置首頁 > 博碩士論文 > 詳目
  • 同意授權
論文中文名稱:風機實驗影像分析技術 [以論文名稱查詢館藏系統]
論文英文名稱:Image-based analysis technology for wind turbine experiment [以論文名稱查詢館藏系統]
院校名稱:臺北科技大學
學院名稱:工程學院
系所名稱:土木工程系土木與防災博士班
畢業學年度:103
畢業學期:第二學期
出版年度:104
中文姓名:胡祖豪
英文姓名:Tzu-Hao Hu
研究生學號:101428076
學位類別:碩士
語文別:中文
口試日期:2015/07/02
指導教授中文名:楊元森
指導教授英文名:Yuan-Sen Yang
口試委員中文名:羅俊雄;吳俊霖
中文關鍵詞:影像量測物件追蹤監測系統
英文關鍵詞:Image-based MeasurementObject TrackingCondition Monitoring System
論文中文摘要:隨著科技的進步,在工程應用中,逐漸以電腦視覺之影像量測技術取代傳統的人工辨識及接觸式感應器量測技術。雖然影像量測及分析技術理論已相當成熟,然而在實務應用中,卻存在許多以現場環境情況變化而造成之不可忽略的分析誤差。在影像量測及分析技術中,不論是以樣板比對或是特徵比對追蹤做為量測點的追蹤目標,其中具有許多會影響分析結果之因素。
本研究藉由風機振動實驗探討影像量測技術,其中主要分為三個部分。第一部份是為了幫助了解影像分析演算法之差異性,本研究採用白光LED當作追蹤識別物設計一套實驗,以現行之影像量測技術進行分析。第二部份是以本研究實作之12種追蹤演算法,並發展出一個適合本實驗影像特性的追蹤演算法,與現行之演算法進行分析,探討其中之差異。第三部分是完成了一套分析程式,處理不同影像分析模組、模組間的分析流程與資料拋轉的動作,並將多種不同之影像演算法導入期中,再將分析數據資料高度可視化,以延續本研究成果,進行未來的風機之檢測分析研究。
論文英文摘要:As technology advances, the traditional manual identification and contact measurement techniques gradually changed into computer vision-based measurement techniques in engineering applications. Although the theory of image-based analysis algorithm is a very well developed field, but there are many on-site environmental conditions caused by the change cannot be ignored analytical error in practical applications. In computer vision-based measurement techniques, there are many factors that can affect the analysis result either by template matching or feature tracking.
This paper investigations image-based measurement techniques using the wind turbine vibration experiment, which is divided into three parts. The first part is designing a experiment to understand the difference in image analysis algorithms, that using image-based measurement techniques currently with white LED as a track target. The second part is discussing the difference that the 12 kinds of tracking algorithms which this study is implemented, a customized algorithms, and the existing algorithm. The third part is to investigate which of the multiple algorithms and compare their differences. This study has developed a complete condition monitoring systems for the wind turbine analysis technology, that can handle data transfer between multiple systems, and import these algorithms which this study implemented, then use advanced data visualization platforms to analyze vibration of wind turbine.
論文目次:摘 要 i
ABSTRACT ii
誌 謝 iv
目 錄 vi
表目錄 ix
圖目錄 x
第一章 緒論 1
1.1 研究動機與目的 1
1.2 文獻回顧 2
1.3 論文架構 2
1.4 研究方法 3
第二章 影像量測分析系統理論 4
2.1 相機校正 4
2.1.1 相機幾何 4
2.1.2 被動式 9
2.1.3 主動式 12
2.2 影像處理 12
2.2.1 色彩空間 13
2.2.2 影像濾波器 15
2.2.3 模糊影像 16
2.3 移動物件辨識 17
2.3.1 光流法 17
2.3.2 連續影像相減法 18
2.3.3 背景相減法與混合高斯模型、編碼簿 19
2.3.4 樣板比對 20
2.3.5 特徵比對 22
2.4 移動物件追蹤 31
2.4.1 卡爾曼濾波器 32
2.4.2 粒子濾波器 33
2.4.3 連續適應性平均位移演算法 34
2.5 影像擷取裝置同步 35
2.5.1 硬體同步 35
2.5.2 軟體同步 36
第三章 高速移動物體之立體檢測分析系統 37
3.1 立體檢測分析系統流程及架構 37
3.2 相機校正系統 39
3.2.1 單相機校正模組 41
3.2.2 雙相機校正模組 43
3.2.3 多相機校正模組 43
3.3 移動物體追蹤系統 46
3.3.1 物件追蹤核心模組 46
3.3.2 以區域為基礎之追蹤模組 47
3.3.3 以輪廓為基礎之追蹤模組 49
3.3.4 以特徵為基礎之追蹤模組 50
3.3.5 以模型為基礎之追蹤模組 51
3.4 移動物體辨識系統 54
3.4.1 樣板比對法 54
3.4.2 區間最大值 55
3.5 座標轉換系統 56
3.6 可視化資料輸出系統 57
3.7 系統檔案架構 58
3.8 資料庫系統 64
3.9裝置管理系統 66
第四章 風機振動實驗 70
4.1 實驗目的 70
4.2 實驗配置 70
4.3 結果與分析 77
4.3.1 影像演算法 78
4.3.2 影像分析結果 80
4.3.3 影像資料與三軸加速度計 85
4.3.4 樣板比對法與區間最大值法 85
第五章 結論與未來展望 90
5.1 結論 90
5.2 未來展望 92
參考文獻 94
論文參考文獻:[1] Y. S. Yang, C. W. Huang and C. L. Wu, "A simple image-based strain measurement method for measuring the strain fields in an RC-wall experiment," Earthquake Engineering & Structural Dynamics, vol. 41, no. 1, 2012, pp. 1-17.
[2] Y. S. Yang, C. W. Huang, B. T. Chen and C. L. Wu "Image-based surface strain field measurement of a post-tensioned RC-wall cyclic test," Eleventh East Asia-Pacific Conference on Structural Engineering & Construction (EASEC-11), Taipei, Taiwan, November, 2008.
[3] Y. S. Yang, C. W. Huang and C. L. Wu, "Image-based measurement techniques for earthquake engineering," Proceedings of the 9th Pacific Conference on Earthquake Engineering, Auckland, New Zealand, Paper No.159, 2011.
[4] A. Kumar and K. Venkata Prathyusha, "Personal authentication using hand vein triangulation and knuckle shape," IEEE TRANSACTIONS ON IMAGE PROCESSING, September, 2009, pp. 2127–2136.
[5] R. Collins, A. Lipton, H. Fujiyoshi, and T. Kanade, "Algorithms for cooperative multi-sensor surveillance," Proceedings of the IEEE, Vol. 89(10), October, 2001, pp. 1456-1477.
[6] X. Desurmont, A. Bastide, C. Chaudy, C. Parisot, J. Delaigle and B. Macq, "Image analysis architectures and techniques for intelligent surveillance systems," IEEE Proc., Vis. Image Signal Process, 152(2), 2005, pp. 224-231.
[7] Y. Hasani, E. Bodenstorfer, J. Brodersen and K. J. Mayer, "FPGA based image processing for optical surface inspection with real time constraints," Seventh International Conference on Machine Vision (ICMV 2014), Proc. SPIE 9445, February, 2015.
[8] D. Rand, E. G. Walsh, Z. Derdak, J. R. Wands and C. Rose-Petruck, "A highly sensitive x-ray imaging modality for hepatocellular carcinoma detection in vitro," Institute of Physics and Engineering in Medicine, Physics in Medicine & Biology, Vol. 60, 2015, pp. 769-784.
[9] G. F. He, S. K. Kang, W. C. Song and S. T. Jung, "Real-time Gesture Recognition using 3D Depth Camera," IEEE 2nd International Conference on Software Engineering and Service Science(ICSESS), July, 2011, pp. 187-190.
[10] A. Bakhtari, M. Naish, and M. Eskandari. "Active-vision based multi-sensor surveillance-an implementation," IEEE Transactions on Systems, Man, and Cybernetics-Part C: Applications and Reviews, 36(5), 2005, pp. 668–680.
[11] C. S. Chen, C. K. Yu, and Y. P. Hung, "New Calibration-free Approach for Augmented Reality Based on Parameterized Cuboid Structure," ICCV, 1999, pp.30-37.
[12] Roger Y. Tsai, "A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf tv camera and lenses," IEEE Journal of Robotics and Automation, 3(4), August, 1987, pp. 323-344.
[13] Z. Y. Zhang, "Camera calibration with one-dimensional objects," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, issue 7, July 2004, pp. 892–899.
[14] H. Li, H. F. Zhang, F. C. Wu and Z. Y. Hu, "A new linear camera self-calibration technique," The 5th Asian Conference on Computer Vision(ACCV), Melbourne, Australia, January, 2002.
[15] G. P. Stein, "Accurate internal camera calibration using rotation, with analysis of sources of error," Proceedings of 15th International Conference on Computer Vision(ICCV), 1995.
[16] WIKI, “HSL and HSV”, ⟨https://en.wikipedia.org/wiki/HSL_and_HSV⟩(JUNE, 2015)
[17] WIKI, “YUV”, ⟨https://en.wikipedia.org/wiki/YUV⟩(JUNE, 2015)
[18] 橋本学, "テンプレートマッチングの魅力~物体検出・位置決めの定番技術 ~," 第19回 画像センシングシンポジウム チュートリアル講演会, June, 2013.
[19] C. Harris and M. Stephens, "A combined corner and edge detector," Proceedings of the 4th Alvey Vision Conference, 1988, pp. 147–151.
[20] J. Shi and C. Tomasi, "Good features to track," IEEE Conference on Computer Vision and Pattern Recognition(CVPR 1994), 1994, pp. 593-600.
[21] Lowe, David G., "Object recognition from local scale-invariant features," Proceedings of the International Conference on Computer Vision 2(ICCV), 1999, pp. 1150-1157.
[22] H. Bay, A. Ess, T. Tuytelaars and L. Van Gool, "SURF: Speeded up robust Features," Computer Vision and Image Understanding (CVIU), Vol. 110, No. 3, 2008, pp. 346-359.
[23] E. Rosten and T. Drummond, "Fusing points and lines for high performance tracking," IEEE International Conference on Computer Vision (ICCV). Volume 2, 2005, pp. 1508–1511.
[24] M. Calonder, V. Lepetit, C. Strecha, and P. Fua. "BRIEF: binary robust independent elementary features," Proceedings of the European Conference on Computer Vision(ECCV), 2010.
[25] E. Rublee, V. Rabaud, K. Konolige and G. Bradski "ORB: an efficient alternative to SIFT or SURF," IEEE International Conference on Computer Vision (ICCV), 2011.
[26] M. Ambai and Y. Yoshida, "CARD: compact and real-time descriptors," IEEE International Conference on Computer Vision(ICCV), November, 2011, pp. 97-104.
[27] P. F. Alcantarilla, A. Bartoli and A. J. Davison. "KAZE Features," European Conference on Computer Vision (ECCV), Fiorenze, Italy, October 2012.
[28] J. Matas, O. Chum, M. Urban, and T. Pajdla, "Robust wide baseline stereo from maximally stable extremal regions," Proc. of British Machine Vision Conference, 2002, pp. 384-396.
[29] LU YU(2013). “Feature detectors and descriptors”, ⟨ https://littlecheesecake.wordpress.com/2013/05/23/research-feature-detectors-and-descriptors/⟩(JUNE, 2015)
[30] 植田耕平,筆先追従と判別分析法を利用した筆接触画像取得型毛筆ディスプレイ,修士論文,東京,日本,2008。
[31] 李長勳,實驗影像量測之相機偏移修正與FPGA系統相機應用可行性,碩士論文,國立台北科技大學土木與防災研究所,台北,台灣,2013。
[32] 陳泓銘,翼牆與單鋼柱實驗之影像量測與嵌入式系統相機之可行性,碩士論文,國立台北科技大學土木與防災研究所,台北,台灣,2013。
[33] I. Demir and A. Sayar, "Hadoop optimization for massive image processing: case study face detection," International Journal of Computers Communications & Control, December, 2014, pp. 664-671.
[34] J. Hou, Using hadoop to cluster data in energy system, Master thesis, The College of Arts and Sciences of the University of Dayton, Dayton, Ohio, 2015.
[35] げーはな(はなげ)(2004) , “Quaternion (as Euler Parameters) ”⟨http://www.geocities.co.jp/HeartLand/8281/quateuler.html⟩(JUNE, 2015)
[36] 簡英皓,分散式水情測預報平台之研究,碩士論文,國立台北科技大學土木與防災碩士班,台北,台灣,2015。
[37] MSDN, “DirectShow Architecture (Windows Embedded CE 6.0)”, ⟨https://msdn.microsoft.com/ja-jp/library/ee494403.aspx⟩(JUNE, 2015)
[38] K. C. Lu and C. H. Loh, "Development of Wireless Sensing System for Structural Health Monitoring," Earth and Space 2010: Engineering, Science, Construction, and Operations in Challenging Environments, 2010.
[39] 黃昱婷,研究型風機葉片之使用影像量測與振動分析,碩士論文,國立台灣大學工學院土木工程學系,台北,台灣,2014。
[40] 黃祈閏,利用基因演算法設計哈特利量化表應用於醫學影像壓縮之研究,碩士論文,大葉大學資訊工程學系碩士班,彰化,台灣,2007。
論文全文使用權限:同意授權於2015-07-06起公開