跳到主要內容

臺灣博碩士論文加值系統

(54.83.119.159) 您好!臺灣時間:2022/01/17 09:22
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:簡大淵
研究生(外文):Ta-Yuan Chien
論文名稱:內視鏡影像序列之自動校正、重構與病灶量測
論文名稱(外文):Auto-Calibration, Reconstruction and Assessment of Clinical Lesions from Endoscopic Image Sequence
指導教授:孫永年孫永年引用關係
指導教授(外文):Yung-Nien Sun
學位類別:碩士
校院名稱:國立成功大學
系所名稱:資訊工程學系碩博士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:97
中文關鍵詞:特徵點追蹤魚眼鏡頭相機自動校正影像序列重構歪曲形變校正內視鏡三維重構
外文關鍵詞:EndoscopyCamera auto calibrationFeature points trackingFish-Eye lens3D reconstructImage sequence reconstructDistortion correct
相關次數:
  • 被引用被引用:15
  • 點閱點閱:670
  • 評分評分:
  • 下載下載:178
  • 收藏至我的研究室書目清單書目收藏:0
  早在1795年就有醫學內視鏡的應用。最近三十年來,隨著光學與資訊電子技術的發展與進步,內視鏡之於內、外科醫學已成為密不可分的一部分。臨床應用的領域越來越大,到最近幾年之中,甚至已成為一個專科領域。
  相對的電腦影像分析,也提供內視鏡影像重要的臨床輔助分析工具。傳統的內視鏡影像分析,以二維影像校正及量測為重點。在本研究中,我們採用內視鏡的影像序列,將所觀察管道區域,直接以電腦視覺校正方式,做三維立體成像,並可達到即時真實貼圖呈現,以增加視覺真實感。
  在狹小的管道中,為了取得大面積的影像,內視鏡大多使用廣角度鏡頭(魚眼鏡頭)。因此所取進來的影像,皆有一定程度的變形失真。故在三維重構之前,本系統提出使用快速的廣角鏡頭變形影像校正機制,利用簡單的校正板與數學校正模型,對一組內視鏡儀器進行形變影像校正。而只需對同一台內視鏡,進行一次校正,爾後便可利用所得到的鏡頭校正參數進行重構,而不需重複校正。
  另一方面,影響重構結果的重要因素,即為影像對應點的取得與追蹤。本系統採用高通濾波器偵測特徵點,並且使用Kanade-Lucas-Tomasi (KLT)特徵追蹤演算法,作為重構影像對應點的追蹤。同時把生理組織的色彩因子,加入到KLT特徵追蹤演算法。另外,也根據內視鏡影像的縮放特性,改良KLT特徵追蹤演算法,以適應縮放型式的影像序列。並且加入廣角鏡頭所造成的形變因素考量,以增加特徵追蹤的穩定性與一致性。
  最後的三維重構部分,我們利用多重影像序列自動校正機制,計算多張影像間,特徵點的三維位置,將所觀察的管道重構出來,並貼以真實影像貼圖。對於特定病變區域,亦提供了細部重構的機制,並做真實大小校正,以提供觀測者數值上的參考。
  In the last 30 years, the progresses in optical engineering, computer science and electronic techniques have made the endoscopy an invaluable tool in both internal clinics and surgical operations. As its applications increase exponentially, it has even become a specialized division in the clinical medicine.
  The image analysis technique provides important aids to the processing of clinical endoscopic images. However, traditional image analyses emphasize the 2-D image distortion calibration and assessment for endoscopic images. In this thesis, we use the computer vision algorithm to reconstruct the 3-D model from the endoscopic image sequence, texture mapping with real images are then employed to enhance the visualization of the reconstructed tubular scene.
  For obtaining a larger field of view inside a small and narrow pipeline, the endoscope is usually equipped with wide-angle lens. Therefore, the acquired images are often with certain degrees of shape distortion. Before 3-D reconstruction, our system provides a fast mechanism for correcting the wide-angle lens distortion. Using a calibration pattern, the nonlinear distortion is corrected with a simple mathematic model for the endoscopic images. Once the endoscopic lens is calibrated, the same calibration parameters can be utilized repeatedly for the calibrated instrument.
  On the other hand, how to extract and track the correspondent features from the image sequence is one of the most important tasks in 3-D reconstruction. Our systems use the high-pass filter to extract the edge feature and the Kanade-Lucas-Tomasi (KLT) feature tracking algorithm to obtain the feature correspondences. The color information, zoom-out characteristic and distortion factor of endoscope image sequence are all taken into account for improving the feature tracking results.
  Thereafter, the multiple frame auto-calibration is used to obtain the camera parameters. The 3-D coordinates of the detected feature points are then computed from the multiple images to reconstruct the 3D scene inside the tubular structure. At last, texture mapping with real endoscopic images is adopted to visualize the realistic 3D scene inside the reconstructed tubular structure of the observed organ.
中文摘要 …………………………………………………………………………. i
英文摘要 …………………..……………..………………………………… ii
誌謝 …………………..…..……….……..………………………………… iii
目錄 ………………………………………………..…………………….… iv
圖目錄 ……………………………………………….......……..……….. vii
第一章. 緒論…………………………..……………………………….….. 01
1.1 研究動機與目的 …………….……………………..…….……… 01
1.2 相關研究回顧 ………………….……………………….……… 05
1.3 論文章節概要 …………………………………………………… 08
第二章. 內視鏡影像歪曲形變之校正 …………….…..………………… 09
2.1 內視鏡廣角鏡頭之光學物理特性 ……..…………..…………… 09
2.2 相關文獻反歪曲形變校正機制概述 ………………..…..……… 10
2.3 快速自動反歪曲形變模型校正機制 ………………...…………. 13
2.3.1 校正用圖形製具之設計 …………….……………………..………….. 13
2.3.2 反歪曲形變模型與廣角鏡頭參數之關係 ………………..….……….. 13
2.3.3 廣角鏡頭參數自動校正機制 ……………………………..…………... 16
第三章. 影像序列特徵點之擷取與追蹤 ……………………..…………. 20
3.1 影像對應點之分析與萃取……………………………………….. 20
3.2 Kanade-Lucas-Tomasi (KLT) 特徵追蹤演算法 ……..………….. 21
3.3 應用於內視鏡縮放影像序列之KLT特徵追蹤演算法..…….……25
3.3.1 完整線性轉換(Affined Transform)參數之考量……………………….. 25
3.3.2 邊線特徵於KLT特徵追蹤演算法之改良………………………….... 27
3.3.3 色彩因子對於KLT特徵追蹤演算法之改良 ………………...……….. 28
3.3.4 縮放影像序列, 特徵點搜尋區域之改良 ……………..……………… 31
3.3.5 其他流程調整…………………………………………………..…….… 33
第四章. 影像序列之自動校正與三維重構………………………..………36
4.1 Epipolar Geometry 簡介………………………………………….. 36
4.2 兩張影像之Fundamental Matrix計算 ………...………………... 38
4.2.1 Fundamental Matrix簡介…………………………….………………….. 38
4.2.2 Fundamental Matrix之線性解法……………………………………….. 40
4.2.3 RANASC對應點取樣演算法……………………….………………….. 42
4.2.4 Fundamental Matrix之非線性解法………………….………………….. 45
4.2.5 Fundamental Matrix之非線性最佳化……………….………………….. 46
4.2.6 Fundamental Matrix之代數誤差最佳化…………….………………….. 47
4.2.7投影矩陣(Projection Matrix)與三維空間點計算………………………. 49
4.2.8 Fundamental Matrix之Gold Standard最佳化演算法….………………. 51
4.3影像序列之投影矩陣估算與相機參數自動校正…...……………. 55
4.3.1影像序列之投影矩陣估算……………………………..……………….. 55
4.3.2影像序列之投影矩陣Bundle Adjustment最佳化……..……………….. 57
4.3.3相機參數之自動校正與透視空間之矩陣轉換………..……………….. 60
第五章. 實驗步驟與結果 …………………………………..……………. 65
5.1實驗用人造腸道管壁之製作………………………..…………….. 65
5.2 Delaunay三角化(Triangulation)演算法…………….…………….. 67
5.3人造簡單平面管壁模擬重構實驗………………….……………... 70
5.4人造縐折管壁模擬重構實驗……………………….……………... 73
5.5人造複雜管壁模擬重構實驗……………………….……………... 76
5.6真實病患胃鏡與腸鏡重構實驗A………………….……………... 79
5.7真實病患胃鏡與腸鏡重構實驗B………………….……………... 82
第六章. 結論與後續研究 …………………………………..……………. 85
參考文獻 ………………………………………………..……………. 88
附錄-程式操作手冊 …………………………………..……………. 92
[1]James P. Helferty, Chao Zhang, Geoffrey McLennan, and William E. Higgins, “Videoendoscopic Distortion Correction and Its Application to Virtual Guidance of Endoscopy”, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 20, NO. 7, Jul. 2001.

[2]Christian Stern, “Non-Invasive Virtual Endo- and Exoscopic Screening for Arterial and Colonic Disease Based on Ultrafast 3D MRI”, The Institute of Diagnostic Radiology of the Zurich University Hospital, Multi-Media Laboratory. http://www.ifi.unizh.ch/mml/people/stern/stern.html

[3]“Multislice CT Colonography”
TOSHIBA VISIONS Magazine No 2 · Volume 2 · 2002.
http://www.toshiba-europe.com/medical/medicallr.asp?PageID=3

[4]Huaibin Zhao; Aggarwal, J.K. “3D reconstruction of an urban scene from synthetic fish-eye images”, Image Analysis and Interpretation, 2000. Proceedings. 4th IEEE Southwest Symposium , 2000 Page(s): 219 -223

[5]Warren E. Smith,Nimish Vakil, and Seth A. Maislin, “Correction of Distortion in Endoscope Images”, IEEE TRANSACTION ON MEDICAL IMAGING, VOL.11, NO. 1, Mar. 1992.

[6]Hideaki Haneishi, Yutaka Yagihashi, and Yoichi Miyake, “ A New Method for Distortion Correction of Electronic Endoscope Images”, IEEE TRANSACTION ON MEDICAL IMAGING, VOL.14, NO. 3, Sep. 1995.

[7]K. Vijayan Asari, Sanjiv Kumar, and D. Radhakrishnan, “A New Approach for Nonlinear Distortion Correction in Endoscopic Images Based on Least Squares Estimation”, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL.18, NO. 4, Apr. 1999.

[8]Bruce D. Lucas and Takeo Kanade., “An Iterative Image Registration Technique with an Application to Stereo Vision”, International Joint Conference on Artificial Intelligence, pages 674-679, 1981.

[9]Carlo Tomasi and Takeo Kanade., “Detection and Tracking of Point Features.”, Carnegie Mellon University Technical Report CMU-CS-91-132, April 1991.

[10]Jianbo Shi and Carlo Tomasi., “Good Features to Track.”, IEEE Conference on Computer Vision and Pattern Recognition, pages 593-600, 1994.

[11]Stan Birchfield., ”Derivation of Kanade-Lucas-Tomasi Tracking Equation.”, Unpublished, May 1996.

[12]Tommasini, T.; Fusiello, A.; Trucco, E.; Roberto, V., “Making good features track better”, Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on , 1998. Page(s): 178 –183

[13]Reinhard Klette, Karsten Schluns, Andreas Koschan, “Computer Vision , Three-Dimensional Data from Images”, Springer Publishing , P148~149.

[14]P. Montesinosa,*, V. Goueta, R. Dericheb, D. Pele´ c , “Matching color uncalibrated images using differential invariants”, ELSEVIER Image and Vision Computing 18 (2000) 659–671.

[15]P. Montesinos, V. Gouet, R. Deriche, D. Pelé, “Differential Invariants for Color Images”, Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on , Volume: 1 , 1998, Page(s): 838 -840 vol.1

[16]Gouet, V.; Montesinos, P.; Pelc, D., “Stereo matching of color images using differential invariants”, Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on , Volume: 2 , 1998. Page(s): 152 -156 vol.2

[17]Richard Hartley, Andrew Zisserman, “Multiple View Geometry in Computer Vision”, CAMBRIDGE UNIVERSITY PRESS Publishing, Page(s):217-241

[18]M. A. Fischler and R. C. Bolles. “Random sample consensus: A paradigm for model fitting with application to image anaysis and automated cartography.”, Comm. Assoc. Comp. Mach., 24(6):381-395, 1981

[19]Richard Hartley, Andrew Zisserman, “Multiple View Geometry in Computer Vision”, Publisher CAMBRIDGE UNIVERSITY PRESS, Page(s):568-582

[20]Pollefeys, M.; Koch, R.; Van Gool, L., “Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters”, Computer Vision, 1998. Sixth International Conference on , 1998 , Page(s): 90 –95

[21]R. A. Dwyer. A Faster “Divide-and-Conquer Algorithm for Constructing Delaunay Triangulations.” Algorithmica, 2:137-151,1987.

[22]F. Dehne and R. Klein. “A Sweepcircle Algorithm for Voronoi Diagrams.” Proceedings of Graph-Theoretical Concepts in Computer Science, published as Lecture Notes in Computer Science Page(s) 59-69, Springer-Verlag, 1987.

[23]Milan Sonka, Vaclav Hlavac, Roger Boyle., “Image Processing Analysis, and Machine Vision”, Second Edition, PWS Publishing, 1999

[24]Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing”, Addison Wesley Publishing, 1992.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊