Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/96082
標題: 3D電腦視覺變位觀測系統用於集水井之變形觀測
3D Displacement Monitoring System Using Computer Vision Technology for Drainage Well's Deformation
作者: Han-Lun Chen
陳漢倫
關鍵字: 電腦視覺
OpenCV
全時段趨勢圖
日平均趨勢圖
集水井變位
Computer Vision
OpenCV
Full Time Trend
Daily Average Trend
引用: [1]何春蓀 (1986)「台灣地質概論—台灣地質圖說明書,第二版」,經濟部中央地質調查所,共164頁。 [2]杜小宇 (2008)「數位近景攝影測量系統精度分析和控制」,南京航空航天大學碩士論文。 [3]廖彥舒 (2004)「非量測型數位相機應用於近景攝影測量之研究-使用三∼六百萬畫素相機」,逢甲大學土地管理學系碩士在職專班碩士論文。 [4]鄒芳諭 (2009)「以非量測性相機進行近景攝影測量探討」,國立交通大學土木工程學系碩士論文。 [5]黃偉哲、柳文成 (2011)「應用攝影測量量測山坡地崩塌量之研究-苗栗火炎山為例」,農業工程學報,57 (4):1-13。 [6]鍾婉婷 (2011)「應用無人工佈標之近景攝影測量建立災害邊坡數值地形模型」,國立臺北科技大學土木與防災研究所碩士論文。 [7]曾匹佑 (2011)「使用地面攝影測量技術對遠距離崩塌地三維建模與應用之研究」,國立高雄應用科技大學土木工程與防災科技研究所碩士論文。 [8]宋周燕 (2006)「攝影測量和透地雷達在數位典藏上之應用」-以台灣府城垣小東門段為例,國立成功大學土木工程學系碩士論文。 [9]吳笛豪 (2008)「應用近景攝影與地面雷射掃描於地物量測精度及三維建模之研究」,國立高雄應用科技大學土木工程與防災科技研究所碩士論文。 [10]黃聿? (2002)「三維空間多攝影機視覺監控系統」,國立交通大學資訊工程系碩士論文。 [11]洪博冠 (2014)「應用近景攝影測量技術於集水井變形量量測之可行性研究」,碩士論文,國立中興大學土木工程所。 [12]台灣WiKi,http://www.twwiki.com/wiki%5E%9C%96%E5%83%8F%E7%90%86%E8%A7%A3 [13]黃明正 (2014) 「數位影像處理概論」。 [14]OpenCV 中文網站,http://www.opencv.org.cn,2009/10/24 [15]繆紹綱 (2003)「數位影像處理」,普林斯頓國際有限公司。 [16]王紹義 (2015)「影像處理輔助無人搬運車走行輪磨耗量測研究」,碩士論文,國立中興大學機械工程所。 [17]曾佩婷 (2005)「在特定車道行駛之大型車偵測與追蹤」,國立中央大學資訊工程研究所碩士論文。 [18]莊仁輝 (2002)「家用機器人之電腦視覺系統研發」,行政院國家科學委員會專題研究計劃其中進度報告。 [19]陳守信 (1997)「即時影像處理於自走車避障之設計與實現」,逢甲大學 自動控制工程學系畢業專題。 [20]Luhmann, T., Robson, S., Kyle, S. and Harley, I. (2011) Close Range Photogrammetry:Principles, Techniques and Applications, Scotland: Whittles Publishing. [21]Z. Y. Zhang, 'A flexible new technique for camera calibration,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume. 22, page 1330-1334, Nov 2000. [22]A. Agarwala, K.C. Zheng, C. Pal, M. Agrawala, M. Cohen, B. Curless, D. Salesin and R.Szeliski, 'Panoramic Video Textures,' In Proc. SIGGRAPG'05, Volume. 24, no.3, page 821-827, August, 2005. [23] E. Rosten and T. Drummond, 'Machine learning for high-speed corner detection,' in Proceedings of the 9th European conference on Computer Vision, pages 430-443, 2006. [24]P. Perez, M. Gangnet and A.Blake, 'Poisson Image Editing,' in ACM Transactions on Graphics, Volume. 22(3), Jul., 2003. [25]M.D.Levine,Vision in Man and Machine, McGraw-Hill Book Company, New York, 1985. [26]N. Otsu, 'A threshold selection method from gray level histogram,' IEEE transactions on System, Man, and Cybernetics, SMC-8, 1978, p.62-66. [27]J. N. Kapur, P. K. Sahoo, and A. K. C. Wong, 'A new method for gray-level picture thresholding using the entropy of the histogram,' Computer Vision Graphics,and Image Processing, 29(3), p.273-285, 1985. [28]K. L. Chung and W. Y. Chen, 'Fast adaptive PNN-based thresholding algorithms,' Pattern Recognition, 36(12), p.2793-2804, 2003. [29]Moravec,H.P,(1977).Towards automatic visual obstacle avoidance.Proceedings of 5th Intrenational Joint Conference on Artificial Intelligence,Cambridge,Massachusetts,USA,pp.584. [30]Martinez-Fonte,L.,S Gautama,and W.Philips,(2004).An Empirical Study of Corner Detection to Extract Buildings in very High Resolution Satellite Images.Proceedings if ProRISC,pp.288-293. [31]K. H. Chang,'A study on the economic polarized light stereoscopic projection system,'Master Thesis, National Central University, Department of Optics and Photonics, p.7-14, 2007.
摘要: 梨山地區為國內重要治理地滑地重要指標之一,為了要排除區域內較深層的地下水,在梨山多處設置集水井。集水井往往設置於地滑區,因其可有效降低地下水位,增加邊坡之穩定性,若發生土體滑動之情形則集水井可能發生變形之情況,因此集水井的變形觀測可有效反應出土體之地滑狀況。 本研究於梨山編號W6集水井架設了四台Raspberry Pi且利用OpenCV判讀位於集水井內部之覘標,其集水井內部總共分為四層,每一組儀器分別對應一個覘標,編號分別為Pw6-B1、Pw6-B2、Pw6-B3及Pw6-B4,經由了室內試驗以及現地試驗讓本研究在長期監測下成功得到了穩定的數據,再進一步經由數據分析加以探討。 從全時段趨勢圖與日平均趨勢圖曲線之變化,判斷出集水井變化之情形,集水井電腦視覺變位觀測系統未來將可成為梨山地滑預警之依據。
Lishan is one important observation area to prevent the occurrences of landslides in Taiwan. In order to expel deeper underground water inside the area, various drainage well's were established in Lishan. Drainage well's is often set up in landslide area to reduce underground water accumulation more efficiently, so as to enhance the stability of slope land. On the other hand, the occurrence of earth slide may also cause the deformation of drainage well's. Hence, the observation on the shape of drainage well's is also an effective measure to determine whether there are earth slides in the area. This study installed four Raspberry Pi around one of the drainage well's, drainage well's No.W6, in Lisan and utilized OpenCV to interpret the signals inside the drainage well's. There were four levels in this drainage well's. The four Raspberry Pi were assigned with different serial number, Pw6-B1, Pw6-B2, Pw6-P3, and Pw6-B4, and were sent to different level to monitor the signals at each level respectively. Through both lab testing and on-site testing, the study observed the signals for a long period and obtained stable statistics, which was further discussed after conducting data analysis. From observing the changes in full-time trend and daily average trend, the study was able to determine the changes of this drainage well's. The drainage well's displacement observation system by computer vision in the future may become an early warning reference for landslides in Lishan area.
URI: http://hdl.handle.net/11455/96082
文章公開時間: 2017-07-04
Appears in Collections:土木工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.