現在位置首頁 > 博碩士論文 > 詳目
  • 同意授權
論文中文名稱:光學檢測自動化之穩定性改善與系統開發 [以論文名稱查詢館藏系統]
論文英文名稱:Development and Reliability Improvement of Optical Assessment Automation [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碩士班
畢業學年度:105
畢業學期:第二學期
出版年度:106
中文姓名:黃晨暐
英文姓名:Chen-Wei Huang
研究生學號:104428083
學位類別:碩士
語文別:中文
口試日期:2017/07/24
論文頁數:53
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:楊元森;邱昱宜;林柏廷
中文關鍵詞:影像量測工業檢測自動化OpenCV
英文關鍵詞:Image MeasurementIndustrial InspectionAutomationOpenCV
論文中文摘要:隨著光學檢測設備成本逐漸降低與品質大幅提升,光學式檢測手段逐漸成為工業檢測主流工具之一。但是在光學檢測上仍然有著許多問題影響檢驗數據以及其穩定度。舉凡外在環境光源干擾、環境震動、定位誤差、光學扭曲、分析運算效能、整體系統的穩定度與一致性,都是在光學檢測實際應用上都會遭遇到的問題。然而,若沒有簡單易上手的軟工具,工程師經常得耗費許多時間處理這些技術性問題不但牽涉許多電腦視覺技術,阻礙了光學檢測的應用性。
本研究使用開源影像分析套件OpenCV,配合工業實務常用之試算表程式開發,建立一套快速而穩定的產品自動檢測系統平台。本研究整合模板匹配與光流法的混合式影像定位方法量測定位並以隨機抽樣一致(RANSAC) 演算法等方法篩選可靠資料,建立一個高效能、高可靠性的光學檢測之軟硬體雛形,並模擬其在工業檢測上的性能。
論文英文摘要:As the cost of digital cameras dramatically reduce and their imaging quality continuously improves, optical detection becomes one of the popular tools of automated optical inspection in manufacturing industry. Practical applications of optical inspection encounters problems such as optical noise induced by environment light, platform vibration, automatic positioning error, camera optical distortion, analysis time and the overall system instability and inconsistency. Handling these problems not only involves complicated computer vision techniques, but also is tedious and time consuming for engineers and developers, hindering the application of automated optical inspection.
This paper uses OpenCV, an open source computer vision library, and the spreadsheet application that commonly used in the industry, to build a fast and stable automatic inspection system platform. In this paper, a hybrid image detection method based on template match and optical flow method was used to position and measurement of ROIs, and use RANSAC (Random sample consensus) algorithm and other methods to filter out reliable data. To build a fast, high reliability of the optical inspection of the hardware and software prototype, and simulate its performance in industrial inspection.
論文目次:摘 要 i
ABSSTRACT ii
誌謝 iv
目錄 v
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1 研究動機與目的 1
1.2 文獻回顧 1
1.2.1 論文架構 2
1.2.2 研究方式 2
第二章 光學式影像量測 3
2.1 自動化檢測需求 3
2.2 影像量測與電腦視覺 3
2.3 相機參數與校正 4
2.3.1 內部參數 4
2.3.2 外部參數 6
2.3.3 鏡頭畸變 7
2.3.4 相機校正 8
2.4 影像定位方法 9
2.4.1 模板匹配(template match) 9
2.4.2 光流法(optical flow) 12
2.4.3 影像金字塔 16
2.4.4 混合式影像定位方法 16
第三章 工業檢測平台 18
3.1 檢測平台構想 18
3.2 影像型態分類 19
3.2.1 被攝物不動平台 20
3.2.2 被攝物轉動平台 21
3.2.3 檢測平台硬體規劃 22
3.2.4 檢測平台軟體規劃 24
第四章 尺寸量測方法 26
4.1 系統檔案架構 26
4.2 核心影像分析程式 28
4.2.1 比對照片與特徵點定義 29
4.2.2 特徵點搜尋定位 31
4.3 VBA於流程控制 33
第五章 測試與分析 36
5.1 量測實驗說明 36
5.2 Arduino連線穩定度測試 37
5.3 RANSAC穩定度檢驗 39
5.4 影像演算法比較 41
5.5 光源控制比較 42
5.6 高品質相機對分析增益 45
5.7 透視效果與影像扭曲校正測試 47
第六章 結論與建議 49
6.1 結論 49
6.2 後續研究方向與建議 50
參考文獻 51
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, pp. 19-21.
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, 2011, pp. 14-16.
4. 胡祖豪,風機實驗影像分析技術,碩士論文,國立臺北科技大學土木與防災研究所,臺北,2015。
5. C. Domínguez, J. Heras, and V. Pascual, “IJ-OpenCV: Combining ImageJ and OpenCV for processing images in biomedicine,” Computers in Biology and Medicine, vol. 84,
no. 1, 2017, pp. 189-194.
6. J. K. Oh, G. Jang, S. Oh, J. H. Lee, B. J. Yi, Y. S. Moon, J. S. Lee, and Y. Choi,
“Bridge inspection robot system with machine vision,” Automation in Construction,
vol. 18, no. 7, 2009, pp 929-941.
7. 劉建宏,光學影像檢測模組之開發與應用,碩士論文,國立臺灣科技大學機械工程學系,臺北,2002。
8. G. Bradski and A. Kaehler, Learning OpenCV: Computer vision with the OpenCV library. OReilly Media, 2008.
9. A. D. H. Thomas, M. G. Rodd, J. D. Holt, and C. J. Neill, “Real-time industrial visual inspection: A review,” Real-Time Imaging, vol. 1, no. 2, 1995, pp. 139-158.
10. D. M. Hitchner, (2017), Perform Serial Port Communication from VB,
取自: http://www.thescarms.com/vbasic/CommIO.aspx (July 18th, 2017).
11. OpenCV.org, (2016), OpenCV 3 docs - OpenCV:OpenCV modules,
取自: http://docs.opencv.org/3.2.0/ (2017, July 18).
12. Microsoft, (2017), Office VBA Reference,
取自: https://msdn.microsoft.com/vba/office-vba-reference (July 18th, 2017).
13. S. Baker, D. Scharstein, J. P. Lewis, S. Roth, M. J. Black and R. Szeliski,
“A database and evaluation methodology for optical flow,” International Journal of Computer Vision, vol. 92, no. 1, 2011, pp. 1-31.
14. R. T. Chen and C. A. Harlow, “Automated visual inspection: A survey,”
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 4, no. 6, 1982,
pp. 557-573.
15. A. K. Jain, Y. Zhong, and S. Lakshmanan, “Object matching using deformable templates,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 3, 1996, pp. 267-278.
16. C. Steger, M. Ulrich, and C. Wiedemann, Machine vision algorithms and applications, WILEY-VCH Verlag GmbH and Co. KGaA, 2008.
17. 林綉莉,智慧型影像量測與分析之研究與應用於自動化光學檢測,碩士論文,聖約翰科技大學電機工程系碩士班,臺北,2009。
18. 陳明煌,塑膠射出成型機模具之自動化光學檢測,碩士論文,南臺科技大學電資工程學系,臺南,2015。
19. 蘇榮智,自動化光學檢測之研究,碩士論文,國立台灣科技大學機械工程學系,臺北,2006。
20. L. Xu, X. He, X. Li, and M. Pan, “A machine-vision inspection system for conveying attitudes of columnar objects in packing processes,” Measurement,
vol. 87, 2016, pp. 255-273.
21. J. Y. Bouguet, (2015), Camera Calibration Toolbox for Matlab,
取自:http://www.vision.caltech.edu/bouguetj/calib_doc/ (August 11th, 2017).
論文全文使用權限:同意授權於2018-08-21起公開