跳到主要內容

臺灣博碩士論文加值系統

(3.235.120.150) 您好!臺灣時間:2021/08/06 03:18
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

我願授權國圖
: 
twitterline
研究生:吳柏逸
研究生(外文):PO-I Wu
論文名稱:基於特徵點與邊界輪廓對於應用在複雜環境達成可自動修正的影像疊合系統
論文名稱(外文):Automatically Correcting Image Stitching System Based On the Feature Points and the Edge Contour for the Complex Environment
指導教授:連豊力
口試委員:簡忠漢李後燦
口試日期:2015-04-22
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:電機工程學研究所
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:2015
畢業學年度:103
語文別:英文
論文頁數:151
中文關鍵詞:影像疊合隨機抽樣方式特徵點偵測全景影像疊合影像平面投影顏色混和邊界偵測
外文關鍵詞:Image stitchingRANSACFeature detectionPanorama stitchingImage plane projectionColor blendingEdge detection
相關次數:
  • 被引用被引用:0
  • 點閱點閱:164
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在這篇論文中提出一個針對複雜影像變化場景的自動影像疊合演算法,由於有許多硬體設備上往往會有視野狹窄的情況發生,藉由改良硬體設備去增加視野這種方法對於擴展的視野是有侷限的,然而我們論文的目標是藉由影像疊合的方式擴展硬體裝置的視野,比如在微創手術中的內視鏡往往的視野是非常狹窄的,我們可藉由影像疊合的方式去提升比原本硬體設備更多的視野提供給醫生,如此可以處理內視鏡本身視野狹窄的缺點。在影像疊合的演算法中大部分是基於影像上面的特徵點去尋找影像與影像之間共同的區域與並且假設某特定的轉換關係為前提下計算轉換矩陣用來疊合兩張影像,但是在實際應用方面硬體常以不規則的方式運動對於一般的影像疊合的方式利用特徵點與隨機抽樣演算法去計算轉換關係往往會發生無法偵測到特徵點匹配對或是計算出的轉換關係只符合區域,因此這一類的方式會產生非常不穩定的結果,針對於不規則運動的影像疊合問題在特徵點選取,特徵點估測轉換關係等步驟作一個改良,使得因為只依賴特徵點計算出的轉換誤差藉由加入輪廓訊息去調整此轉換關係使得兩影像疊合能夠更加平順以及可以在不規則的運動下找到特徵點匹配對。以往大多數的影像疊合演算法並沒有辦法知道結合之後是否還存有偏差的區域導致即使有誤差區域也無法修,因此在影像疊合有偏差的區域我們利用邊界數量與遮罩運算可以得知疊合不佳的區域在影像上的位置,而我們利用分層式特徵點匹配找出此區域的局部最佳轉換最後藉由局部與全局的轉換方式結合去處理疊合不佳的區域並且在複雜運動環境中建立二維全景影像。

In this thesis, we focus on presenting an auto image stitching system for complex environment. The primary goal is to increase visibility by using the image stitching concept for a narrow visibility device. For example, a doctor’s field of view is important in minimally invasive surgery (MIS); therefore, stitching plural narrow endoscopic images together result in a wider field of view. The wide panoramic image can help the doctor to determine positioning in an MIS environment.
The general image stitching process is based on using image feature points to find the overlapping region and estimate the projection between the two adjacent images, but the camera often moves in an irregular way in complex environment, leading to an unstable result for general stitching (random sample consensus) transformation. Therefore we focus mainly on how to improve irregular movement image stitching, feature detection, feature matching, and transformation, so that the image stitching systems can produce a wide field of view from a narrow device image


中文摘要 i
ABSTRACT iii
Contents v
List of Figures vii
List of Tables xi
Chapter 1 1
1.1 Motivation 2
1.2 Problem Formulation 4
1.3 Contribution 6
1.4 Organization of the Thesis 8
Chapter 2 9
2.1 Overlapping Detection 11
2.2 Plane Projection 12
2.3 Image Combination 13
Chapter 3 15
3.1 Feature algorithm 16
3.1.1 Scale Invariant Feature Transform (SIFT) 17
3.1.2 Affine SIFT 21
3.2 Random Sample Consensus (RANSAC) 22
3.3 Canny Edge Detection 25
3.4 K-means 28
3.5 Optimal Path 29
Chapter 4 32
4.1 Edge-Based For Estimating Transformation 34
4.1.1 Feature Detection and Feature Matching 37
4.1.2 Iterative Hierarchical Feature Matching (IFM) 41
4.1.3 Edge-Based Optimal Global Transforamtion 51
4.2 Misalignment Adjustment in Overlapping Region 66
4.2.1 Find Misalignment Region by p Index Mask 66
4.2.2 Misalignment Adjustment 71
Chapter 5 77
5.1 General Scene Stitching 77
5.1.1 Structural Regularity Indoor Environment 79
5.1.2 Structural Irregularity Outdoor Environment 82
5.2 Model of Human Internal Organs Image Stitching 85
5.2.1 Snake Tube Camera 86
5.2.2 Image Stitching Detail Process 87
5.2.3 Model of Human Internal Organs Image Stitching 108
5.2.4 Simulating Application for Operation 117
5.2.5 Comparison of Image Stitching Algorithms 121
5.2.6 Panoramic Image Stitching using EBMA Algorithm 130
Chapter 6 140
6.1 Conclusion 140
6.2 Future work 142
References 144


[1: Dasgupta & Banerjee 2006]
S. Dasgupta and A. Banerjee, "An Augmented-Reality-Based Real-Time Panoramic Vision System for Autonomous Navigation," IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, vol. 36, no. 1, pp. 154-161, Jan. 2006.
[2: Ha et al. 2008]
S.J. Ha, S.H. Lee, N.I. Cho, S.K. Kim, B.J. Son, "Embedded Panoramic Mosaic System Using Auto-Shot Interface," IEEE Transactions on Consumer Electronics, vol. 54, no. 1, pp. 16-24, Feb. 2008.
[3: Liao & Hsieh 2012]
Wei-Sheng Liao and Tung-Ju Hsieh, “GPU Parallel Computing of Spherical Panorama Video Stitching,” in Proceedings of International Conference on Parallel and Distributed Systems, Singapore, pp. 890 - 895, Dec. 17-19, 2012.
[4: Lowe 2004]
David G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, January 2004.
[5: Bay et al. 2008]
Herbert Bay, Andreas Ess, Tinne Tuytelaars, Luc Van Gool, “SURF: Speeded Up Robust Features. Computer Vision and Image Understanding (CVIU)”, Vol. 110, No. 3, pp. 346-359, 2008.
[6: Yu & Morel 2011]
Guoshen Yu and Jean-Michel Morel “ASIFT: An Algorithm for Fully Affine Invariant Comparison,” IPOL Journal Image Processing On Line, Feb. 24, 2011
[7: Puerto-Souza & Mariottini 2013]
Gustavo A. Puerto-Souza and Gian-Luca Mariottini, “A Fast and Accurate Feature-Matching Algorithm for Minimally-Invasive Endoscopic Images,” IEEE Transactions on medical imaging, vol. 32, no. 7, Jul. 2013.

[8: Xiong & Pulli et al. 2010]
Yingen Xiong and Kari Pulli, "Color Matching for High-Quality Panoramic Images on Mobile Phones," IEEE Transactions on Consumer Electronics, vol. 56, no. 4, pp. 2592-2600, Nov. 2010
[9: Zhuang et al. 2009]
Yi Zhuang, Xinrong Hu, and Jianchun Wang,“The Implement of an Image Stitching Algorithm based on Feature Extraction ,”in Proceedings of Second International Conference on Education Technology and Training, Sanya, pp. 327-330, Dec. 13-14, 2009.
[10: Jia & Tang 2008]
Jiaya Jia and Chi-Keung Tang, “Image Stitching Using Structure Deformation,” IEEE Transactions on Patten Analysis and Machine Intelligence, vol. 30, no. 4, pp. 617-631, Apr. 2008
[11: Xiong & Pulli 2009]
Yingen Xiong and Kari Pulli, “Sequential Image Stitching for Mobile Panoramas,” IEEE International Conference on Information, Communications and Signal Processing, Macau, pp. 1-5, Dec. 8-10, 2009.
[12: Liu & Zhou 2004]
Y. Liu and X. Zhou, “Automatic texture segmentation for texture-based image retrieval,” in Proceedings of 10th International Conference on Multimedia Modelling, pp. 285-290, Jan. 2004
[13: Rebi`ere. 2008]
Nad`ege Rebi`ere, “Image Mosaicing using Local Optical Flow Registration,” in Proceedings on 19th International Conference on Pattern Recognition, Tampa, FL, pp. 1-5, Dec. 8-11, 2008.
[14: Kim et al. 2011]
S. Kim, C. Coffin, and T. Hollerer, "Robust Relocalization and Its Evaluation for Online Environment Map Construction," IEEE Transactions on Visualization and Computer Graphics, vol. 17, no. 7, pp. 875-887, Jul. 2011
[15: Kim et al. 2009]
S. Kim, C. Coffin, and T. Hollerer, "Relocalization Using Virtual Keyframes for Online Environment Map Construction," in Proceedings of 16th ACM Symp. Virtual Reality Software and Technology, Kyoto, Japan, pp. 127-134, Nov. 18-20, 2009
[16: Rav-Acha et al. 2007]
A. Rav-Acha, Y. Pritch, D. Lischinski, and S. Peleg, "Dynamosaicing: Mosaicing of Dynamic Scenes," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 10, pp. 1789-1801, Oct. 2007
[17: Lin et al. 2011]
Wen-Yan Lin, Siying Liu1, and Tian-Tsong Ng, “Smoothly varying affine stitching,” in Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , Rhode Island, Providence, pp. 345-352, Jun. 20-25, 2011.
[18: Koo et al. 2009]
Hyung Il Koo, Beom Su Kim, and Nam Ik Cho, “A New Method To Find An Optimal Warring Function In Image Stitching,” in Proceedings of IEEE International conference on acoustics speech and signal processing, Taipei, pp. 1289-1292, Apr.19-24, 2009.
[19: Salembier & Oliveras 1998]
Philippe Salembier and Albert Oliveras, “Antiextensive Connected Operators for Image and Sequence Processing,” IEEE Transactions in Image Processing, vol. 7, no. 4, Apr. 1998.
[20: Hua et al. 2010]
Zhen Hua, Yewei Li, and Jinjiang Li, “Image Stitch Algorithm Based on SIFT and MVSC,” in Proceedings of IEEE International Conference on Fuzzy Systems and Knowledge Discovery, Yantai, Shandong, pp. 2628-2632, Aug.10-12, 2010.
[21: Fang 2011]
Xianyong Fang, “Feature Based Stitching of a Clear/Blurred Image Pair,” in Proceedings of IEEE International Conference on Multimedia and Signal Processing, Guilin, pp. 146-150, May 14-15, 2011.
[22: Chen 2012]
Jyun-Hong Chen, “Image stitching on the unmanned air vehicle in the indoor environment,” in Proceedings of SICE Annual Conference (SICE), Akita, pp. 402-406, Aug. 20-23, 2012.
[23: Gu & Yu 2009]
Hua Gu and Yue Yu, “A new optimal seam selection method for airborne image stitching,” in Proceedings of IEEE International Workshop on Imaging Systems and Techniques, Shenzhen, pp. 159-163, May 11-12, 2009.
[24: Senarathne et al. 2011]
Chaminda Namal Senarathne, Shanaka Ransiri,and Pushpika Arangala, “A faster image registration and stitching algorithm,” in Proceedings of International Conference on Industrial and Information Systems, Kandy ,Aug. 16-19, 2011,
[25: Li et al. 2008]
Yanfang Li, Yaming Wang, and Wenqing Huang “Automatic Image Stitching Using SIFT,” in Proceedings of International Conference on audio language and image processing, Shenzhen, pp. 568-571, Jul. 7-9, 2008.
[26: Cheng et al. 2010]
Yan Cheng, Shu Yang, and Shi-feng Li “Image Encryption of Multiple Keys Method Based on Chaotic Maps,” International Conference on Pervasive Computing Signal Processing and Applications (PCSPA), Harbin, pp. 891-894, Sep. 17-19, 2010.
[27: Juan & Gwun 2010]
Luo Juan and Oubong Gwun “SURF applied in panorama image stitching,” in Proceedings of international conference on image processing theory tools and applications, Paris, pp. 495-499, Jul. 7-10, 2010.
[28: Barron et al. 1992]
J.L. Barron, D.J. Fleet, and S.S. Beauchemin “Performance of Optical Flow Techniques,” in Proceedings of Computer Society Conference on Computer Vision and Pattern Recognition, Champaign, pp. 236-242, Jun. 15-18, 1992.

[29: Bay et al. 2008]
Herbert Bay, Andreas Ess, and Tinne Tuytelaars “Speeded-Up Robust Features (SURF),” Computer Vision and Image Understanding, New York, vol. 110, pp. 346-39, Jun. 2008.
[30: Milgram 1975]
D. L. Milgram, “Computer methods for creating photo mosaics,” IEEE Transactions on Computers, vol. 24, no. 11, pp. 1113–1119, 1975.
[31: Chew & Lian 2012]
Vencedor Chew and Feng-Li Lian , “Panorama stitching using overlap area weighted image plane projection and dynamic programming for visual localization,” in Proceedings of IEEE International Conference on Advanced Intelligent Mechatronics (AIM), Kaohsiung, Taiwan, pp. 250-255, July 11-14, 2012.
[32: Gracias et al. 2009]
Nuno Gracias, Mohammad Mahoor, Shahriar Negahdaripour, and ArthurGleason, “Fast Image Blending using Watersheds and Graph Cuts,” ImageVision Comput., vol. 27, no. 5, pp. 597–607, 2009.
[33: Pan & Lyu 2010]
Xunyu Pan and Siwei Lyu, “Region Duplication Detection Using Image Feature Matching,” IEEE Transactions on Information Forensics and Security, vol. 5, no. 4, Dec. 2010.
[34: Agarwala et al. 2004]
AInm Agarwala, Mira Dontcheva, Maneesh Agrawala, and Steven Drucker,Alex Colburn, “Interactive digital photomontage,” ACM Transactions on Graphics (TOG), vol. 23, pp. 294–302, Aug. 2004.
[35: Uyttendaele et al. 2001]
M. Uyttendaele, A. Eden, and R. Szeliski, “Eliminating ghosting and exposure artifacts in image mosaics,” in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition vol. 2, pp. 509–516, 2001.
[36: P´erez et al. 2003]
Patrick P´erez, Michel Gangnet, and Andrew Blake, “Poisson image editing,” ACM Transactions on Graphics (TOG), vol. 22, no. 3, pp. 313–318, 2003.
[37: KANG 2010]
Guang-Quan KANG, “Image stitching based on motion estimation,” 2010 Third International Conference on Information and Computing, Jiang Su, Wuxi, pp. 82-85, Jun. 4-6, 2010.
[38: John 1986]
Canny John, “A Computational Approach to Edge Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, pp. 679–698, Nov. 2004.
[39: Kanungo & Mount 2002]
Tapas Kanungo and David M. Mount “An Efficient k-Means Clustering Algorithm: Analysis and Implementation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 881–892, Jul. 2002.
[40: Fischler & Bolles 1981]
Martin A. Fischler and Robert C. Bolles “Random Sample Consensus: A Paradigm for Model Fitting with Apphcatlons to Image Analysis and Automated Cartography,” Communications of the ACM, vol. 24, pp. 381–395, Jun. 1981.
[41: Teodoro & Kurc 2012]
George Teodoro and Tahsin M. Kurc “Accelerating Large Scale Image Analyses on Parallel, CPU-GPU Equipped Systems,” Parallel & Distributed Processing Symposium (IPDPS), Shanghai, pp. 1093–1104, May 2012.
[42: Zhu et al. 2002]
Ce Zhu, Xiao Lin, and Lap-Pui Chau “Hexagon-Based Search Pattern for Fast Block Motion Estimation,” IEEE Transactions on circuits and systems for video technology, vol. 12, no. 5, may 2002.

Websites
[43: SIFT Keypoint Detector from David Lowe 2013]
SIFT Keypoint Detector. (2005, July). In David Lowe Personal Page. Retrieved Jun. 2, 2014, from http://www.cs.ubc.ca/~lowe/keypoints/
[44: Laparoscopic surgery image 2013]
Fig.1 Laparoscopic surgery, from is3tin3a.cgu.edu.tw
[45: VLFeat SIFT Stitching 2013]
VLFeat SIFT stitching algorithm. The matches based on RANSAC and produces a mosaic, from http://www.vlfeat.org/applications/apps.html
[46: Panorama Stitching from Tobias Weyand 2014]
Panorama Stitching algorithm in Matlab. In Tobias Weyand Page.Form
http://tobw.net/index.php?cat_id=2&project=Panorama+Stitching+Demo+in+Matlab
[47: HSL and HSV from wiki 2013]
HSL and HSV. (2013, June 6). In Wikipedia. Retrieved June 20, 2014, from http://en.wikipedia.org/wiki/HSL_and_HSV
[48: Random Sample Consensus from wiki 2013]
RANSAC. (2013, May 13). In Wikipedia. Retrieved June 23, 2014, from http://en.wikipedia.org/wiki/RANSAC
[49: Optical Flow software 2010]
Optical Flow Matlab&C Code. (2010, Jun.). In Brown University Retrieved June 23, 2014, from http://cs.brown.edu/people/black/code.html
[50: Hausdorff-Based Image Comparison 1994]
Hausdorff-Based Image Comparison Code. (1998). In Computational Geometry McGill University Retrieved June 22, 2014
, from http://www.cs.cornell.edu/vision/hausdorff/hausmatch.html
[51: Interpolation from wiki 2013]
Interpolation. (2013, May 31). In Wikipedia. Retrieved June 31, 2014, from http://en.wikipedia.org/wiki/Interpolation
[52: SIFT from Electronic Thesis and Dissertation Collection 2011]
The Scale-Invariant Feature Transform on a Parallel pipeline. (2011, May). In Electronic Thesis and Dissertation Collection. Retrieved June 31, 2014, from http://etd.lsu.edu/docs/available/etd-04272011-105721/
[53: Rigid body from wiki 2013]
Rigid body. (2013, June 27). In Wikipedia. Retrieved June 27, 2014, from http://en.wikipedia.org/wiki/Rigid_body
[54: On line SURF/SIFT/ASIFT 2014]
On Line Demo Analysis of the SURF/SIFT/ASIFT method (2014). In IPOL Journal Image Processing On line. Retrieved June 27, 2014, from http://www.ipol.im.
[55: Edge detection code]
Edge detection method. In Matlab platform. Retrieved June 26, 2014, from http://www.mathworks.com/products/image/
[56 : Control Point Selection Tool]
The function enables you to select control points in two related images. In Matlab platform. Retrieved June 1, 2015, from http://www.mathworks.com/help/images/ref/cpselect.html
Books:
[57: Szeliski 2010]
Richard Szeliski, Computer Vision: Algorithms and Applications, November 24, 2010.
[58: Gonzalez & Woods 2008]
R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd adapted ed., Editor: S. G. Miaou, Taiwan: Pearson, June 2008.
[59: Mehta & Bhirud 2011]
Jalpa D. Mehta and S. G. Bhirud, Image stitching techniques, Editor: S. J. Pise, pp 74-80, 2011.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top