請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41072
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 張斐章(Fi-John Chang) | |
dc.contributor.author | Chang-Han Chung | en |
dc.contributor.author | 鍾昌翰 | zh_TW |
dc.date.accessioned | 2021-06-14T17:15:13Z | - |
dc.date.available | 2010-07-30 | |
dc.date.copyright | 2008-07-30 | |
dc.date.issued | 2008 | |
dc.date.submitted | 2008-07-25 | |
dc.identifier.citation | 1. 王友俊、周瑞仁,2006,「MFA 方法應用於影像中近似橢圓物
件之分割」,農業機械學刊,15(1),PP.15-23。 2. 錢中方、林達德,2000,「應用霍氏轉換量測重疊葉片面積之 影像處理方法」,農業機械學刊,第9 卷,第四期,第47-64 頁。 3. 傅志偉,2004,「河床質調查的方法、位置與頻率-以頭前溪為 例」,國立交通大學土木工程研究所碩士論文。 4. 國立交通大學防災工程研究中心,2006,「河床質調查方法之 比較研究」專題報告書。 5. Butler, J. B., Lane, S. N., Chanfler, J. H., 2001, Automated extraction of grain-size data from gravel surfaces using digital image processing, Journal of Hydraulic Research, vol.39, pp.519-529. 6. Bunte K. and Abt, S.R., 2001, Sampling surface and subsurface particle-size distributions in wadable gravel-and-cobble-bed streams for analyses in sediment transport, hydraulics,and streambed monitoring, General Technical Report RMRS-GTR-74,Fort Collins, Colo.; U.S. Department of Agriculture,Forest Service, Rocky Mountain Research Station. 428p. 7. Eckhorn, R., Reitboeck, H. J., Dicke, M.A., 1990, Feature linking via synchoronization among distributed assemblies: simulation of results from cat corvex, Neural Computing ,vol.2, pp.293-307. 8. Gonzale, R. C. and Woods R.E., 2002, Digital Image Processing , 2nd Ed., Prentice Hall, Inc. Upper Saddle River, New Jersey. 9. Graham, D. J., Reid, I., Rice, S. P., 2005, A transferable method for the automated grain sizing of river gravels, Water Resoure.Res., 41, W07020, doi: 10.1029/2004WR003868. 10. Hey , R. D.and Thorn ,C.R.,1986,Stable channels with mobil gravel beds,Joural of Hydraulic Engineering,vol.112,pp.671-689. 11. Kinser, J. M. and Johnson, J. M., 1996, Stabilized input with a feedback pulse-coupled neural network., Opt. Eng, vol.35, no.8,pp.2158-2161. 12. Laronne, J. B. and Shlomi,Y., 2007, Depositional character and preservation potential of coarse-grained sediments deposited by flood events in hyper-arid braided channels in the Rift Valley,Arava,Israel, Sedimentary Geology, vol.195, pp.21-37. 13. Meyer, F. and Beucher, S., 1990, Morphological segmentation,Journal of Visual Communication and Image Representation,vol.1, no.1, pp.21-46. 14. Rice, S. P. and Haschenburger, J. K., 2004, A hybrid method for characterization of coarse subsurface fluvial sediments, Earth Surface Precesses and Landforms, vol.29, pp.373-389. 15. Thanos, P.and Kyle, S., 2004, Grain Size Analysis of Beach Sediment in Rich Passage Washington, A Report prepared of Pacific International Engineering. 16. Vincent, L. and Soille, P., 1991, Watersheds in digital spaces: An efficient algorithm based on immersion simulations, IEEE Trans.on Pattern Analysis and Machine Intelligence, vol.13, no.6,pp.583-598. 17. Waldemark, K., Lindblad, T., Becanovic, V., Guillen, J. L. L.,Klingner, P.L., 2000a, Patterns from the sky satellite imageanalysis using pulse coupled neural networks for pre-processing,segmentation and edge dection, Pattern recognition letters, vol.21,pp.227-237. 18. Waldemark, J., Millberg, M., Lindblad, T., Waldemark, K.,2000b, Image analysis for airborne reconnaissance and missileapplications, Patter recognition letters, vol.21, pp.239-251. 19. Xue, Y. and Yang, S., 2005, Image segmentation using watershedtransform and feed-back pulse coupled neural network, Artificial neural network: Biological Inspirations, Springer Berlin/Heidelberg. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41072 | - |
dc.description.abstract | 河床質調查最重要之目的在於暸解河床粒徑分佈資訊,ㄧ般傳統
河床質調查有體積、網格與面積法等,可依據調查目的不同,選用不同的調查方法,如表層分佈與底層分佈;目前水利界常用的為體積法,然而此法工作量龐大,費時費力,往往需要許多的人力、物力投入其中,造成許多資源的浪費;近年來照相與影像處理技術進步迅速,在辨別與量測方面皆有良好的成果,可作為量測河床粒徑分佈的有利工具;本研究以固定面積拍攝所得影像,透過製作標誌(marker)為基礎,提出四個主要步驟:(1)影像預處理,(2)標誌製作,(3)影像切割,(4)測量最大短軸;上述方式可抑制分水嶺演算法過度切割的缺點並獲得良好的分割結果;我們以台灣北部景美溪所採樣的石頭帶回實驗室隨機排列,並拍攝影像進行分析,藉由上述方法,推算其所得個數及粒徑百分比累積曲線,與實驗室篩分析所得個數及粒徑百分比累積曲線相比有良好的結果,可作為後續研究之參考及快速研判河床粒徑分佈之用。 | zh_TW |
dc.description.abstract | The measurement techniques of river materials are mainly to get surface grain-size distribution information. There are several traditional measurement techniques, such as volume, grid, and area measurement methods. Among them, the volume measurement method is the most common method used by the Hydraulics, but this method needs a huge
workload, time and energy. Image analysis techniques have been shown to work well in identifying and measuring particles, consequently they can be powerful tools for measuring the grain size distributions. In this paper we present a rapid image-processing-based procedure for the measurement of exposed fluvial gravels, defining the steps required to minimize the errors in the derived grain size distribution. The main procedure is divided into four steps: (1)image pre-processing, (2)marker making, (3)image segmenting, and (4)maximum b-axis measuring. The analyzed stones were obtained from Jingmei River and randomly disposed within a square meter grid in the laboratory and taken picture for the analysis. The measurement errors compared with sieve analyses are quite small in all the cases, consequently we can conclude that the image processing method proposed in this study can efficiently and precisely identify the grain-size distribution and can be used in the follow-up research. | en |
dc.description.provenance | Made available in DSpace on 2021-06-14T17:15:13Z (GMT). No. of bitstreams: 1 ntu-97-R95622031-1.pdf: 3183467 bytes, checksum: 698d7a4de85e5c4f2d50a17e14c60891 (MD5) Previous issue date: 2008 | en |
dc.description.tableofcontents | 目錄
摘 要................................................... I Abstract ................................................ II 目錄................................................... III 表目錄.................................................. VI 圖目錄................................................. VII 第一章 前言.............................................. 1 1.1 研究動機......................................... 1 1.2 研究目的......................................... 5 1.3 論文架構......................................... 5 第二章 文獻回顧.......................................... 6 2.1 表面採樣方法特性比較............................. 7 2.2 影像處理應用於量測方面........................... 8 2.3 影像處理應用於河床質調查......................... 8 2.4 脈衝耦合類神經網路............................... 9 第三章 理論概述......................................... 10 3.1 影像預處理...................................... 10 3.1.1 影像擷取................................... 10 3.1.2 影像校正................................... 12 3.1.3 灰階化..................................... 13 3.1.4 影像縮小................................... 14 3.1.5 梯度運算................................... 14 3.2 影像切割........................................ 16 3.2.1 分水嶺轉換(Watershed transformation) ....... 16 3.3 標誌標記........................................ 20 3.3.1 反饋式脈衝耦合類神經網路(Feedback Pulse-Coupled Neural Network, FPCNN) ............. 20 3.3.2 侵蝕(Erosion) .............................. 24 3.3.3 標記連通成分(Marker Connected Component) ... 25 3.3.4 合併規則................................... 27 3.3.5 區域填充................................... 29 3.3.6 距離轉換................................... 30 3.4 影像測量........................................ 32 3.4.1 Hotelling 轉換............................. 32 第四章 研究方法......................................... 34 4.1 採樣作業........................................ 35 4.2 實驗設計........................................ 40 4.2.1 實驗目的................................... 40 4.2.2 實驗器材................................... 40 4.2.3 實驗步驟................................... 44 4.2.4 實驗樣本................................... 48 4.3 模式的建立...................................... 51 4.3.1 FPCNN 的迭代次數........................... 51 4.3.2 規則運算修正標誌........................... 54 4.3.3 整體模式的步驟、流程....................... 58 第五章 結果與討論....................................... 62 第六章 結論與建議....................................... 75 6.1 結論............................................ 75 6.2 建議............................................ 76 參考文獻................................................ 77 | |
dc.language.iso | zh-TW | |
dc.title | 影像處理應用於河床粒徑分佈之研究 | zh_TW |
dc.title | Image Processing for Estimating River Grain-Size Distribution | en |
dc.type | Thesis | |
dc.date.schoolyear | 96-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 林達德(Ta-Te Lin),周瑞仁(Jui-Jen Chou),張麗秋(Li-Chiu Chang) | |
dc.subject.keyword | 影像處理,河床粒徑,類神經網路,分水嶺轉換, | zh_TW |
dc.subject.keyword | Image processing,River materials,Artificial neural network,Watershed transform, | en |
dc.relation.page | 78 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2008-07-28 | |
dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
dc.contributor.author-dept | 生物環境系統工程學研究所 | zh_TW |
顯示於系所單位: | 生物環境系統工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-97-1.pdf 目前未授權公開取用 | 3.11 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。