Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
  • 搜尋 TDR
  • 授權 Q&A
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 電機資訊學院
  3. 資訊網路與多媒體研究所
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74961
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor施吉昇
dc.contributor.authorHao-Yu Chenen
dc.contributor.author陳皓宇zh_TW
dc.date.accessioned2021-06-17T09:11:20Z-
dc.date.available2019-09-03
dc.date.copyright2019-09-03
dc.date.issued2019
dc.date.submitted2019-08-29
dc.identifier.citation[1] D. Stoyanov, M. V. Scarzanella, P. Pratt, and G.-Z. Yang, “Real-time stereo reconstruction in robotically assisted minimally invasive surgery,” in International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2010, pp. 275–282.
[2] P.-L. Chang, D. Stoyanov, A. J. Davison et al., “Real-time dense stereo reconstruction using convex optimisation with a cost-volume for image-guided robotic surgery,” in International Conference on Medical Image Computing and ComputerAssisted Intervention. Springer, 2013, pp. 42–49.
[3] X. Liu, A. Sinha, M. Unberath, M. Ishii, G. D. Hager, R. H. Taylor, and A. Reiter, “Self-supervised learning for dense depth estimation in monocular endoscopy,” in OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis. Springer, 2018, pp. 128–138.
[4] A. Hosni, C. Rhemann, M. Bleyer, C. Rother, and M. Gelautz, “Fast cost-volume filteringforvisualcorrespondenceandbeyond,”IEEETransactionsonPatternAnalysis and Machine Intelligence, vol. 35, no. 2, pp. 504–511, 2012.
[5] C.Schmalz,F.Forster,A.Schick,andE.Angelopoulou,“Anendoscopic3dscanner based on structured light,” Medical image analysis, vol. 16, no. 5, pp. 1063–1072, 2012.
[6] J. Uhrig, N. Schneider, L. Schneider, U. Franke, T. Brox, and A. Geiger, “Sparsity invariant cnns,” in International Conference on 3D Vision (3DV), 2017.
[7] D. Stoyanov, A. Darzi, and G. Z. Yang, “A practical approach towards accurate dense3ddepthrecoveryforroboticlaparoscopicsurgery,”ComputerAidedSurgery, vol. 10, no. 4, pp. 199–208, 2005.
[8] Z. Zhang, “A flexible new technique for camera calibration,” IEEE Transactions on pattern analysis and machine intelligence, vol. 22, 2000.
[9] J. Jung, J.-Y. Lee, Y. Jeong, and I. S. Kweon, “Time-of-flight sensor calibration for a color and depth camera pair,” IEEE transactions on pattern analysis and machine intelligence, vol. 37, no. 7, pp. 1501–1513, 2014.
[10] P.-C. Su, J. Shen, W. Xu, S.-C. Cheung, and Y. Luo, “A fast and robust extrinsic calibration for rgb-d camera networks,” Sensors, vol. 18, no. 1, p. 235, 2018.
[11] M. Lindner, I. Schiller, A. Kolb, and R. Koch, “Time-of-flight sensor calibration for accurate range sensing,” Computer Vision and Image Understanding, vol. 114, no. 12, pp. 1318–1328, 2010.
[12] P.-C. Wu, R. Wang, K. Kin, C. Twigg, S. Han, M.-H. Yang, , and S.-Y. Chien, “Dodecapen: Accurate 6dof tracking of a passive stylus,” in ACM Symposium on User Interface Software and Technology (UIST), 2017.
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74961-
dc.description.abstract在內視鏡手術中,醫生常常只能以二維的影像資訊進行三維的手
術操作,增添了不必要的執行難度,如果能提供準確的三維資訊輔以
恰當的顯示方式,將可讓內視鏡手術操作更加容易。但現今內視鏡手
術環境下的深度預測演算法,還有許多情境是無法正確預測立體資訊
的,包含鏡像反射、變動劇烈的視差、手術器械造成的遮蔽、煙霧和
液體等。此外目前的定量評估方法也有一些限制,包含目標物體不能
形變、畫面無法有手術器械以及沒有直接的真質等。
因此,我們提出一個外部的深度相機和內視鏡鏡頭的校正方法,藉
此能提供包含影像與深度資訊的資料。之後,將能進一步以這樣的資
料進行深度預測類神經網路的訓練,以及更無限制的內視鏡情境深度
預測演算法的定量評估。
zh_TW
dc.description.abstractThis work proposes a calibration method between a narrow field of view cameraandadepthcamerainanendoscope-likescenario. Anendoscopy-like scenario has several properties including limited specular reflective surface, a camera with a narrow field of view. Instead of pushing the accuracy of the target marker with low-resolution data, we propose a solution with a loss function. The proposed loss function utilizes all of the 3 dimensions points of the checkerboard measured with the depth camera, and calculates the distance between projected 3D positions onto 2D image surface and the color image. The final re-projected error is improved to average under 1 millimeters, and further trainingand evaluation of depth estimation algorithms could be performed.en
dc.description.provenanceMade available in DSpace on 2021-06-17T09:11:20Z (GMT). No. of bitstreams: 1
ntu-108-R04944055-1.pdf: 5470332 bytes, checksum: 0edd309717a55d18e46c5345e97d3b51 (MD5)
Previous issue date: 2019
en
dc.description.tableofcontentsAcknowledgments i
摘要 ii
Abstract iii
1 Introduction 1
1.1 Motivation 1
1.2 Contribution 3
1.3 Thesis Organization 3
2 BackgroundandRelatedWork 4
2.1 Depth measurement/estimation mechanism 4
2.1.1 Stereo vision 4
2.1.2 Structure light 5
2.1.3 Time-of-flight 5
2.1.4 Depth estimation methods 5
2.2 Camera calibration 6
3 SystemArchitectureandProblemDefinition 8
3.1 System Architecture 8
3.2 Problem Definition 9
3.3 Challenges 9
3.3.1 Noisiness 9
3.3.2 Sparseness 10
3.3.3 Occlusions 11
3.3.4 Time synchronization 11
4 DesignandImplementation 12
4.1 Proposed method 12
4.2 Plane fitting 13
4.3 Two-dimensions corners matching 14
4.3.1 Color camera parameters 14
4.3.2 Color camera calibration 16
4.4 Three-dimension corners matching 17
4.5 Point-to-square optimization 18
5 PerformanceEvaluation 19
5.1 Experimental setting 19
5.2 Evaluation result 20
5.3 Quality result 24
6 Conclusion 26
Bibliography 27
dc.language.isoen
dc.title深度視覺相機與窄視野彩色相機之校正方法zh_TW
dc.titleAn Extrinsic Calibration for Depth Camera to Narrow Field of View Color Cameraen
dc.typeThesis
dc.date.schoolyear107-2
dc.description.degree碩士
dc.contributor.oralexamcommittee林忠緯,蔡欣穆
dc.subject.keyword內視鏡,深度資訊,相機校正,鏡面反射,真質,zh_TW
dc.subject.keywordendoscopy,depth,calibration,specularly re?ection,ground truth,en
dc.relation.page28
dc.identifier.doi10.6342/NTU201904109
dc.rights.note有償授權
dc.date.accepted2019-08-29
dc.contributor.author-college電機資訊學院zh_TW
dc.contributor.author-dept資訊網路與多媒體研究所zh_TW
顯示於系所單位:資訊網路與多媒體研究所

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
5.34 MBAdobe PDF
顯示文件簡單紀錄


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。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved