跳到主要內容

臺灣博碩士論文加值系統

(216.73.217.114) 您好!臺灣時間:2026/11/17 07:14
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:董本健
研究生(外文):Ben-Jian Dong
論文名稱:基於空間順序的漸進式影像特徵點匹配
論文名稱(外文):Progressive Image Feature Matching Based on Feature Spatial Order
指導教授:賴國華、鄧進宏鄧進宏引用關係
指導教授(外文):K. Robert Lai、Chin-Hung Teng
口試委員:陸敬互
口試委員(外文):Ching-Hu Lu
口試日期:2017-1-20
學位類別:碩士
校院名稱:元智大學
系所名稱:資訊工程學系
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:2017
畢業學年度:105
語文別:中文
論文頁數:39
中文關鍵詞:影像匹配、影像X坐標、基於空間順序的漸進式匹配、特徵點匹配
外文關鍵詞:image matching、image X coordinate、spatial order-based progressive matching、feature matching
相關次數:
  • 被引用被引用:0
  • 點閱點閱:253
  • 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
影像匹配是計算機視覺,機器學習和模式識別領域內的核心基礎問題。在影像表示、影像拼接、影像分類和查找、目標識別、3D重建目標追蹤、機器定位和生物信息系統中都被大量使用。因此,如何高效正確地進行特徵點匹配是一個值得深入研究的課題。如今,有很多的學者提出了一些類似與最鄰近法和基於雜湊法的算法來進行特徵點匹配,這些算法雖然能夠極大地提高匹配的速度,但是對影像匹配的準確度而言並沒有起到很好的效果,反而與蠻力法相比準確度更下降了。基於空間順序的算法提出了從影像 坐標分析可知正確的匹配點之間不會出現交叉,因此利用特徵點匹配的空間順序性質可有效的去除不正確的匹配點,然而原始基於空間順序的算法是在影像特徵點匹配完成後才進行不正確匹配點的去除,事實上若能將空間順序的概念融入特徵點匹配的過程中應可更有效地限縮特徵點比對的範圍進而提升匹配的準確度,故本研究提出一個結合空間順序的漸進式特徵點匹配的方式,從實驗結果可知本方法確實可提升特徵點匹配的準確度。
Image matching is a very important and fundamental issue in computer vision, machine learning and pattern recognition. It is being applied widely in a large number of applications such as image representation, image stitching, image classification and retrieval, object recognition, 3D reconstruction, object tracking, robot localization and biometrics system. Therefore, how to match image features correctly and efficiently in a great quantity of feature points is a valuable subject with deeply research. Over the years, many scholars proposed some kinds of methods including Approximate Nearest Neighbor and Hashing-based algorithm to improve the speed of feature matching. Although these algorithms can speed up the matching process tremendously, their accuracy sometimes is worse than that of brute-force algorithm. The algorithm of spatial order shows that correctly matched features do not intersect when feature points are sorted according to the coordinate. Thus, spatial order can be used to remove incorrect feature matches. The original algorithm of spatial order removes incorrect matches after the matching process is completed. Actually, the concept of spatial order can be incorporated into the process of feature matching to reduce the range of feature search. In view of this, this thesis proposes a progressive matching framework that employ spatial order in feature matching. Some experiments were conducted and the results show that the proposed system can indeed improve the matching accuracy.
摘要 iii
ABSTRACT iv
誌 謝 iv
目錄 vii
表目錄 ix
圖目錄 x
第一章、緒論 1
1.1 研究背景與動機 1
1.2 研究目的 7
第二章、文獻探討 9
2.1影像匹配方法 9
2.1.1 基於最近鄰的方法 10
2.1.2 基於雜湊的方法 11
2.2 提高匹配結果準確度 11
2.2.1 圖匹配的方法 12
2.2.2 對極幾何的方法 12
2.2.2 空間順序限制的方法 13
第三章、相關技術探討 14
3.1 特徵點匹配問題的構建 14
3.2 Kendall距離 16
3.3 全重疊區域 17
3.4 部分重疊區域 18
3.5 匹配概率的計算 19
第四章、漸進式影像匹配 23
4.1 系統概述 23
4.2 傳統匹配方式 24
4.3 漸進式匹配 24
第五章、實驗過程與結果 25
5.1 實驗數據 25
5.2 統計不同影像集下的準確度 30
第六章、實驗結論與未來研究方向 33
6.1 實驗結論 33
6.2 未來研究方向 33
參考資料 34
[1] Yap, T., Jiang, X., Kot, A.C.: Two-dimensional polar harmonic transforms for invariant image representation. IEEE Trans. Pattern Anal. Mach. Intell, 2010.
[2] O. Enqvist, E. Ask, F. Kahl, and K. Astrom. Robust fitting for multiple view geometry. In ECCV, 2012.
[3] J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, and Y. Gong. Locality constrained linear coding for image classification. CVPR, 2010.
[4] Wang, J., Li,Y., Zhang,Y.,Wang, C.,Xie,H., Chen,G., Gao, X.:Bag-of-features based medical image retrieval via multiple assignment and visual words weighting. IEEE Trans. Med. Imaging, 2011.
[5] Andreopoulos, A., Tsotsos, J.: 50 years of object recognition: directions forward. Comput. Vis. Image Underst, 2013.
[6] Moreels, P., Perona, P.: Evaluation of features detectors and descriptors based on 3D objects. Int. J. Comput, 2007.
[7] Takacs,G., Chandrasekhar,V., Tsai, S., Chen,D., Grzeszczuk, R.,Girod, B.: Rotation-invariant fast features for large-scale recognition and real-time tracking. Sign. Process. Image Commun, 2013.
[8] Campos, F.M., Correia, L., Calado, J.M.F.: Robot visual localization through local feature fusion: an evaluation of multiple classifiers combination approaches. J. Intell. Rob. Syst, 2015.
[9] Mian, A., Bennamoun, M., Owens, R.: Keypoint detection and local feature matching for textured 3D face recognition. Int. J. Comput, 2008.
[10] Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput, 2001.
[11] Bianco, S., Mazzini, D., Pau, D., Schettini, R.: Local detectors and compact descriptors for visual search: a quantitative comparison. Digital Signal Process, 2015.
[12] Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: a survey. Found. Trends Comput, 2007.
[13] Lindeberg, T.: Feature detection with automatic scale selection. Int. J. Comput, 1998.
[14] Ali Ismail A., Mahmoud H.: Image Feature Detectors and Descriptors: Foundations and Applications. Springer,Switzerland (2016).
[15] Moravec, H.P.: Towards automatic visual obstacle avoidance. In: 5th International Joint Conference on Artificial Intelligence, 1977.
[16] Harris, C., Stephens, M.: A combined corner and edge detector. In: The Fourth Alvey Vision Conference, Manchester, UK, 1988.
[17] Smith, S.M., Brady, J.M.: A new approach to low level image processing. Int. J. Comput, 1997.
[18] Rosten, E., Drummond, T.:Machine learning for high speed corner detection. In: 9th European Conference on Computer Vision (ECCV’06), May 2006.
[19] Lakemond, R., Sridharan, S., Fookes, C.: Hessian-based affine adaptation of salient local image features. J. Math. Imaging Vis, 2012.
[20] Lindeberg, T.: Feature detection with automatic scale selection. Int. J. Comput, 1998.
[21] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, 2004.
[22] Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. Int. J. Comput, 2004.
[23] H. Baya, A. Essa, T. Tuytelaarsb, and L. Van Gool, “Speeded-up robust features (SURF),” Computer Vision and Image Understanding, 2008.
[24] Yussof, W., Hitam, M.: Invariant Gabor-based interest points detector under geometric transformation. Digital Signal Process, 2014.
[25] Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable extremal regions. ImageVis. Comput, 2004.
[26] Rosten, E., Drummond, T.:Machine learning for high-speed corner detection. In: Proceedings of European Conference on Computer Vision, 2006.
[27] Agrawal, M., Konolige, K., Blas, M.: CenSurE: center surround extremas for realtime feature detection and matching. In: Proceedings of European Conference on Computer Vision, 2008.
[28] Calonder, M., Lepetit,V., Strecha, C., Fua, P.: BRIEF: binary robust independent elementary features. In: Proceedings of the European Conference on Computer Vision, 2010.
[29] Leutenegger, S., Chli, M., Siegwart, R.: BRISK: binary robust invariant scalable keypoints. In: Proceedings of IEEE International Conference on Computer Vision, 2011.
[30] Rublee, E.,Rabaud,V.,Konolige, K.,Bradski,G.:ORB:an efficient alternative to SIFT or SURF. In: Proceedings of IEEE International Conference on Computer Vision, 2011.
[31] Alahi, A., Ortiz, R., Vandergheynst, P.: Freak: Fast retina keypoint. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2012.
[32] D. Mukherjee, Q. M. J. Wu, and G. Wang, “A comparative experimental study of image feature detectors and descriptors,” Machine Vision and Applications, 2015.
[33] Arandjelovi, A., Zisserman, A.: Three things everyone should know to improve object retrieval. Conf. Comput, Vis. Pattern Recogn, 2011.
[34] M. Muja and D. G. Lowe, “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration,” in VISAPP, 2009.
[35] C. Silpa-Anan and R. Hartley. Optimised kd-trees for fast image descriptor matching. In Computer Vision and Pattern 5721 Recognition, 2008. CVPR 2008.
[36] M. Muja and D. G. Lowe. Fast approximate nearest neighbors with automatic algorithm configuration. VISAPP International Conference on Computer Vision Theory and Applications, 2009.
[37] A. Andoni and P. Indyk. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. In Foundations of Computer Science, 2006.
[38] X. Zhang, Z. Li, L. Zhang, W.-Y. Ma, and H.-Y. Shum. Ef- ficient indexing for large scale visual search. In Computer Vision, 2009 IEEE 12th International Conference on, 2009.
[39] M. A. Fischler and R. C. Bolles, “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,” Commun. ACM, 1981.
[40] R. Shah, V. Srivastava, and P. J. Narayanan, “Geometry-Aware Feature Matching for Structure from Motion Applications,” in IEEE Winter Conference on Applications of Computer Vision (WACV), January 2015.
[41] W. Aguilar, Y. Frauel, F. Escolano, M. E. Martinez-Perez,A. Espinosa-Romero, and M. A. Lozano, “A robust graph transformation matching for non-rigid registration,” Image Vis. Comput, 2009.
[42] L. Talker, Y. Moses, and I, Shimshoni. Using Spatial Order to Boost the Elimination of Incorrect Feature Matches, In CVPR, 2016.
[43] Zhou, F., De la Torre, F.: Deformable graph matching. In: CVPR (2013).
[44] Duchenne, O., Bach, F.R., Kweon, I.S., Ponce, J.: A tensor-based algorithm forhigh-order graph matching. In: CVPR, 2009.
[45] Torresani, L., Kolmogorov, V., Rother, C.: Feature correspondence via graph matching: Models and global optimization. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008.
[46] Salzmann, M., Fua, P.: Reconstructing sharply folding surfaces: A convex formulation. In: CVPR ,2009.
[47] Pilet, J., Lepetit, V., Fua, P.: Fast non-rigid surface detection, registration and realistic augmentation. IJCV ,2008.
[48] Tran, Q.-H., Chin, T.-J., Carneiro, G., Brown, M.S., Suter, D.: In defence of ransac for outlier rejection in deformable registration. In: Fitzgibbon, A., Lazebnik, S.,Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012.
[49] Ostlund, J., Varol, A., Ngo, D.T., Fua, P.: Laplacian meshes for monocular 3D shape recovery. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C.(eds.) ECCV 2012.
[50] Pizarro, D., Bartoli, A.: Feature-based deformable surface detection with self occlusion reasoning. IJCV ,2012.
[51] Leordeanu, M., Hebert,M.: A spectral technique for correspondence problems using pairwise constraints. In: ICCV ,2005.
[52] Toby, C., Adrien, B.: Using Isometry to Classify Correct/Incorrect 3D-2D Correspondences. ECCV, 2014.
[53] M. Muja and D. G. Lowe, “Fast approximate nearest neighbors with automatic algorithm configuration,” in VISAPP International Conference on Computer Vision Theory and Applications, 2009.
[54] C. Strecha, A. M. Bronstein, M. M. Bronstein, and P. Fua, “Ldahash: Improved matching with smaller descriptors,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012.
[55] J. Chen, C. Leng, J. Wu, and H. Lu, “Fast and accurate image matching with cascade hashing for 3D reconstruction, “ in Proceedings of 2014 International Conference on Computer Vision and Pattern Recognition, CVPR 2014.
[56] M. Cho, J. Lee, and K. M. Lee. Reweighted random walks for graph matching. In ECCV, 2010.
[57] Q.-T. Luong, Matrice fondamentale et calibration visuelle sur l’environnement. Vers une plus grande autonomie des syst`emes robotiques, PhD thesis, Universit´e Paris Sud-Paris XI, 1992.
[58] Z. Liu, J. An, and Y. Jing, “A simple and robust feature point matching algorithm based on restricted spatial order constraints for aerial image registration,” IEEE Trans. Geosci. Remote Sens., 2012.
[59] M. G. Kendall. A new measure of rank correlation. Biometrika, 1938.
[60] K. Mikolajczyk and C. Schmid. “A performance evaluation of local descriptors,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005.
電子全文 電子全文(本篇電子全文限研究生所屬學校校內系統及IP範圍內開放)
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