請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/73628
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 劉格非 | |
dc.contributor.author | Wei-Hsiang Huang | en |
dc.contributor.author | 黃煒翔 | zh_TW |
dc.date.accessioned | 2021-06-17T08:07:03Z | - |
dc.date.available | 2020-08-20 | |
dc.date.copyright | 2019-08-20 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-08-19 | |
dc.identifier.citation | [1] Gunnar Farneback,(2003). “Two-Frame Motion Estimation Based on Polynomial Expansion”
[2] Gunnar Farneback,(2002). “Polynomial Expansion for Orientation and Motion Estimation”, Link¨oping Studies in Science and Technology. Dissertations No. 790, [3] Lucas B and Kanade T, (1984).“An Iterative Image Registration Technique with an Application to Stereo Vision” Proc. ,Of 7th International Joint Conference on Artificial Intelligence (IJCAI) [4] Bruce David. Lucas,(1984).“Generalized Image Matching by the Method of Differences” doctoral dissertation, tech. report , Robotics Institute, Carnegie Mellon University, July [5] Chia-Ming Wangi, Kuo-Chin Fani, Cheng-Tzu Wang .(2008). “Estimating Optical Flow by Integrating Multi-Frame Information” , Journal of Information Science and Enginering 24, 1719-1731 [6] Simon Baker ,& Iain Matthews.(2004)“Lucas-Kanade 20 Years On: A Unifying Framework” ,nternational Journal of Computer Vision 56(3), 221–255, [7] J. Y. Bouguet,(1999) “Pyramidal implementation of the lLcas Kanade feature tracker description of the algorithm” ,Intel Corporation Microprocessor Research Labs [8] S. S. Beauchemin,& J. L. Barron,(1995) “The Computation of Optical Flow” , ACM Computing Surveys (CSUR) Surveys Homepage archive Volume 27 Issue 3, Sept,Pages 433-466 [9] Thomas Brox,Andrés Bruhn,Nils Papenberg,Joachim Weickert.(2004)“High Accuracy Optical Flow Estimation Based on a Theory for Warping” ,ECCV 2004: Computer Vision - ECCV pp 25-36 [10] D. Sun, S. Roth, and M. J. Black.(2010)“Secrets of optical flow estimation and their principles”. In CVPR. 6 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/73628 | - |
dc.description.abstract | 本研究建立於影像光流法之基礎上,將現實三維環境之運動場,投影至圖像二維平面,利用圖像序列中像素亮度在時間域上的變化,以及相鄰影像之間的相關性來找到上一幀跟當前幀之間存在的對應關係,從而計算出相鄰影像之間物體的運動信息的一種方法。由於光流法擁有許多不同分支,本研究主要為Farneback光流法(Farneback optical flow )進行改良及優化,主要概念為二次擬合像素點周圍之亮度趨勢分布,在時間序列上,將追蹤不同圖像有著相同趨勢分布的像素點,進而求取像素點之運動信息
為了從圖像內得到具有物體代表性之資訊,透過像素點之間的亮度梯度變化,明確找出物體邊界,試著追蹤這些邊界上的像素點,從而計算光流的變化,獲取二維圖像運動場。本研究目的為應用於土石流事件,將進行室內小型實驗,模擬土石流中有著不同粒徑顆粒情況;由於二維影像僅投影三維物體表面,故透過光流法之計算,得表面顆粒之運動信息,最後將本研究方法,真實應用於現場土石流事件,並整理與分析。 | zh_TW |
dc.description.abstract | Based on the image optical flow method, this study projects the motion field of the realistic three-dimensional environment to the two-dimensional image of the image, using the variation of the pixel brightness in the time domain of the image sequence, and the correlation between adjacent images. A method for finding the correspondence between the previous frame and the current frame to calculate the motion information of the object between adjacent images. Since the optical flow method has many different branches, this study mainly improves and optimizes the Farneback optical flow method. The main concept is the quadratic fitting of the brightness trend distribution around the pixel points. In the time series, the tracking will be different. The image has pixels with the same trend distribution, and then the motion information of the pixel is obtained.
In order to obtain the representative information of the object from the image, the boundary of the object is clearly found through the change of the brightness gradient between the pixels, and the pixel points on the boundary are tried to calculate the change of the optical flow to obtain the two-dimensional image. Like a sports field. The purpose of this study is to apply to small-scale indoor experiments to simulate the case of different particle sizes in the earth-rock flow. Since the two-dimensional image only projects the surface of the three-dimensional object, the motion information of the surface particles is obtained by the calculation of the optical flow method. Finally, the research method is applied to the on-site earth and rock flow events, and is sorted and analyzed. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T08:07:03Z (GMT). No. of bitstreams: 1 ntu-108-R06521324-1.pdf: 10061758 bytes, checksum: 75246c7aa84b024130a5688f19f94542 (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 致謝 I
摘要 II Abstract III 目錄 IV 圖目錄 VII 表目錄 X 第一章 緒論 1 1.1前言 1 1.2前人研究 2 1.2.1 光流基礎 2 1.2.2 稀疏光流法 3 1.2.3 稠密光流法 4 1.3 論文架構 6 第二章 分析方法 7 2.1基礎理論 7 2.2影像灰階化 7 2.3 空間梯度 8 2.4光流法之二次擬合 9 2.5推估角速度 15 第三章 室內實驗 17 3.1 實驗設計 17 3.2 實驗器材與配置 17 3.3 實驗流程 19 第四章 分析結果 20 4.1第一幀之前處理 20 4.1.1 影像切割 20 4.1.2 影像灰階化 22 4.1.3 空間梯度 23 4.1.4 標定追蹤點 24 4.1.5 二次擬合 27 4.2 第二幀之追蹤辨識 34 4.2.1 二次擬合追蹤 34 4.2.2 實際追蹤 41 4.2.3二次擬合與實際追蹤比較 45 4.3 第三幀之追蹤辨識 48 4.3.1 二次擬合追蹤 48 4.3.2 實際追蹤 53 4.3.3 二次擬合與實際追蹤比較 56 4.4 第四幀之追蹤辨識 59 4.4.1 二次擬合追蹤 59 4.4.2 實際追蹤 64 4.4.3 二次擬合與實際追蹤比較 67 4.5顆粒角速度 70 4.6 分析結果與比較 75 第五章 室外應用 84 5.1 室外配置 84 5.2 結果分析 86 第六章 結論與建議 99 6.1結論 99 6.2 建議 99 參考文獻 101 附錄 102 A.第二幀之二次擬合追蹤 102 B.第三幀之二次擬合追蹤 107 C.第四幀之二次擬合追蹤 112 | |
dc.language.iso | zh-TW | |
dc.title | 應用影像光流法於土石流表面顆粒之追蹤 | zh_TW |
dc.title | Image Optical Flow Applied to Trace Particle on Debris Flow Surface | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 周憲德,黃宏斌 | |
dc.subject.keyword | 影像分析,表面流速,亮度梯度,影像光流法,二次函數擬合, | zh_TW |
dc.subject.keyword | image processing,surface velocity,intensity gradient,optical flow,quadratic function fitting, | en |
dc.relation.page | 117 | |
dc.identifier.doi | 10.6342/NTU201903610 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-08-19 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
顯示於系所單位: | 土木工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf 目前未授權公開取用 | 9.83 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。