跳到主要內容

臺灣博碩士論文加值系統

(35.175.191.36) 您好!臺灣時間:2021/08/01 01:00
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:Nguyen Xuan Loc
研究生(外文):Nguyen Xuan Loc
論文名稱:三維影像自動物件分割與辨識演算法之研發
論文名稱(外文):Development of Algorithms for Automatic Object Segmentation and Recognition using 3-D Point Clouds
指導教授:林世聰林世聰引用關係陳亮嘉
指導教授(外文):Shyh-Tsong LinLiang-Chia Chen
口試委員:林志平范光照蔡篤銘黃漢邦
口試委員(外文):Chih-Ping LinKuang-Chao FanDu-Ming TsaiHan-Pang Huang
口試日期:2012-07-20
學位類別:博士
校院名稱:國立臺北科技大學
系所名稱:機電科技研究所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:英文
論文頁數:113
中文關鍵詞:影像分割影像識別圖像範圍表面曲率法線向量
外文關鍵詞:object segmentationobject recognitionrange imagesurface curvaturenormal vector
相關次數:
  • 被引用被引用:0
  • 點閱點閱:589
  • 評分評分:
  • 下載下載:86
  • 收藏至我的研究室書目清單書目收藏:2
在這篇論文中,將對3-D圖像處理的物件分割和識別物體技術進行討論。隨著時代的進步,科技快速的發展,光學感測和測距裝置成為3-D影像與資訊的主要方式,3-D數據的可行性將更高。高解析的3-D物件的資訊,如人、汽車、樹木、建築物和道路的三維形貌資訊可以透過影像擷取獲得,而如何由取得的形貌資訊中進行正確的物件分割和識別將是機器視覺中具有挑戰性的研究課題。
本研究的第一個貢獻是新型的物件深度切層分割處理技術,以即時運算將三維形貌資訊中進行物件分割。物件所在的深度位置可以初步的利用深度切層分割技術來分離。為準確地定義出物件的邊緣,使用區域增長法並通過遞歸搜索過程中來找出正確的邊緣位置,以清楚地將物件分割出來。第二個貢獻是對分割物件採用新型的區域增長演算法和表面特性的分類。為了解決背景識別的問題,提出以物件表面向量分佈作為參考依據。根據這個參考依據,能將所有的點資料進行一個初步的分類。將這個分類的結果納入該表面的區域增長法的成長過程中,就能有效的對複雜的物件進行數據分割演算。為了準確地找出物件的邊界,遞迴搜尋方式的區域增長算法的過程及開發在本研究中提出。本論文的第三個貢獻,旨在識別物體。識別物體的重點主要在於界定獨特的特徵點,藉此來區分不同的3-D物體之間的相似性。在這項研究中,物體識別方式以自動搜索範圍內物件的幾何形狀和曲率變化直方圖來識別目標。以往的目標識別的都是已一個感應裝置的單一視角影像來進行辨識,其辨識效果將受到約束。因此,本研究所提出的技術可以克服這一弱點,針對物件的重要特徵採用從多個視角的影像進行分析,而得到一個完整的3-D結構的特徵值方圖分佈,藉此得到精準的目標辨識結果。


In this dissertation we discuss a variety of 3-D image processing techniques that advance the state of the art in the fields of object segmentation and object recognition. The rapid development of technology has made powerful light detection and ranging devices become available in the market and the acquisition of 3-D range data has been more feasible and popular. High-resolution 3-D profile of objects, such as people, cars, trees, buildings and roads, can be captured, providing a great help for the tasks of object segmentation and recognition which are remaining as challenging research topics in computer vision.
The first contribution of this research is the novel depth slicing technique for segmenting object with the real-time processing. The depth region containing objects can be initially segmented by employing depth slicing technique. For accurately marking object boundary, a region growing method is then applied through a recursive searching process.
The second contribution is a new method for object segmentation employing region-growing algorithm and classification of surface characteristics. In order to solve the problem of digital background identification (DBI), the method proposes a novel criterion based on the distribution of normal surface vectors. According to this criterion, range data are classified into certain types of surface as an initial stage of evaluation for addressing all the points belonging to the background. By incorporating this criterion into the region-growing process, a robust range data segmentation algorithm capable of segmenting complex objects suffering huge amount of noises in outside condition is established. To detect accurately the object boundary, a recursive search process involving the region-growing algorithm for registering homogeneous surface regions is developed.
The third contribution of this thesis aims at object recognition. The key breakthroughs for object recognition mainly lie in defining unique features that distinguish the similarity among various 3-D objects. In this research, the object recognition scheme is developed to identify targets underlining automated search in the range images using geometric constrains and curvature-based histogram. Since the accuracy of object recognition is generally limited by using a single viewpoint constraint of sensing device, the important feature of the proposed technique which can overcome this weakness is to employ a set of histograms from multiple views for representing the 3-D structure of objects.


TABLE OF CONTENTS
中文摘要 I
ABSTRACT III
ACKNOWLEDGMENTS V
TABLE OF CONTENTS VII
LIST OF TABLES IX
LIST OF FIGURES X
Chapter 1 INTRODUCTION 1
1.1 Statement of the problem 2
1.2 Research scopes 3
1.3 Contributions of the research 3
Chapter 2 LITERATURE REVIEW 6
2.1 Algorithms for 3-D object segmentation 9
2.2 Algorithms for 3-D object recognition 14
Chapter 3 OBJECT SEGMENTATION 21
3.1 Depth slicing technique 22
3.1.1 Depth distribution histogram 23
3.1.2 Butterworth low-pass filter for peak detection 25
3.1.3 Recursive search algorithm 30
3.1.4 Object tracking 37
3.2 Object segmentation employing Region-Growing Algorithm and Classification of Surface Characteristics 40
3.2.1 Classification of Surface Characteristics 41
3.2.2 Ground retrieval by least-squares plane fitting 45
3.2.3 Region growing algorithm for Digital Background Identification 49
3.2.4 Recursive search process for marking objects 52
Chapter 4 OBJECT RECOGNITION 55
4.1 K-nearest neighbor 55
4.2 Surface curvature 57
4.3 Object recognition using curvature-based histogram 60
4.3.1 Object dimension 61
4.3.2 Curvature-based histogram 63
4.3.3 Matching coefficient 68
Chapter 5 EXPERIMENTAL RESULTS 69
5.1 Object Segmentation 69
5.1.1 Depth Slicing Technique 69
5.1.2 Object segmentation employing Region-Growing Algorithm and Classification of Surface Characteristics 75
5.1.3 Discussion for object segmentation methods 83
5.2 Object Recognition 85
5.2.1 Database for object recognition 85
5.2.2 Object Recognition using curvature-based histogram 87
5.2.3 Discussion for object recognition method 95
Chapter 6 CONCLUSIONS 96
REFERENCES 99
NOMENCLATURE 109
Biography 110

[1] L. C. Chen, X. L. Nguyen and Y. S. Shu, “High Speed 3-D Surface Profilometry using HSI Color Model and Trapezoidal Phase-shifting Method,” Technisches Messen, Vol. 76, No. 7-8, pp. 347-353, 2009.
[2] L. C. Chen, Y. S. Shu and X. L. Nguyen, “High speed full-field 3-D surface profilometry using silmultaneous phase shifting principle for on-line automatic optical inspection,” The Cross Strait 6th workshop, Hongkong, Dec 21th, 2008.
[3] L. C. Chen, Y. S. Shu and X. L. Nguyen, “High Speed 3-D Surface Profilometry using HSI Color Model and Trapezoidal Phase-shifting Method,” International Conference on Precision Measurement, Technische Universität Ilmenau, German, September 08-12, 2008.
[4] L. C. Chen and X. L. Nguyen, “Dynamic 3-D surface profilometry using a novel colour pattern encoded with a multiple triangular model,” Special Issues, Measurement Science and Technology, Vol. 21, No. 5, pp. 054009, 2010.
[5] L. C. Chen and X. L. Nguyen, “Dynamic 3D surface profilometry using a novel color pattern encoded with a multiple triangular model,” The 9th International Symposium on Measurement Technology and Intelligent Instruments, Saint Petersburg, Russia, June 29 – July 2, 2009.
[6] L. C. Chen and X. L. Nguyen, “Real-time 3-D robot vision employing novel color fringe projection,” The IEEE Conference on Autonomous Robots and Agents, Wellington, New Zealand, Feb 10-12, pp. 177-181, 2009.
[7] S. Zhang and P. Huang, “High-Resolution, Real-time 3D Shape Acquisition,” Conference on Computer Vision and Pattern Recognition Workshop (CVPRW''04), Vol. 3, 2004.
[8] M. Takeda and K. Mutoh, “Fourier-transform profilometry for the automatic measurement of 3-D object shapes,” Appl. Opt., Vol. 22, pp. 3977-3982, 1983.
[9] M. Takeda and H. Yamamoto, "Fourier-transform speckle profilometry: three-dimensional shape measurements of diffuse objects with large height steps and/or spatially isolated surfaces," Appl. Opt., Vol. 33, pp.7829-7837, 1994.
[10] J. Yi and S. Huang, "Modified Fourier Transform Profilometry for the Measurement of 3-D Steep Shapes," 0pfic.and Laser Engineering, Vol. 27, pp. 493-505, 1997.
[11] J. Lin and X. Su, "Two-dimensional Fourier transform profilometry for the automatic measurement of three dimensional object shapes," Optical Engineering, Vol. 34, pp. 3297-3302, 1995.
[12] L. C. Chen, W. S. Dai and X. L. Nguyen, “Development of a new compact 3-D vision system for in-situ robots,” CACS International Automatic Control Conference, Taipei, Taiwan, Nov. 27-29, 2009.
[13] L. C. Chen, X. L. Nguyen and W. S. Dai, “3-D image acquisition using FTP with adaptive fringe evaluation for accurate phase retrieval,” International Conference on 3D systems and applications, Tokyo, Japan, May 19-21, 2010.
[14] L. C. Chen, X. L. Nguyen and W. S. Dai, “Real-time Fourier Transform Profilometry with Reference Reconstruction for 3-D Robot Vision,” The 6th International Conference on Ubiquitous Robots and Ambient Intelligence, Kwangju, Korea, Oct. 28-31, 2009.
[15] M. A. Herraez, D. R. Burton and M. J. Lalor, "Accelerating fast Fourier transform and filtering operations in Fourier fringe analysis for accurate measurement of three-dimensional surfaces," Optics and Lasers in Engineering, Vol. 31, pp. 135-145, 1999.
[16] L. C. Chen, X. L. Nguyen and H. W. Ho, “High-speed 3-D Machine Vision Employing Fourier Transform Profilometry with Digital Tilting-Fringe Projection,” ARSO’08, IEEE Conference on Advanced Robotics and its Social Impacts, Taipei, Taiwan, 2008.
[17] L. C. Chen, C. H. Cho and X. L. Nguyen, “One-shot three-dimensional surface profilometry using DMD-based two-frequency moire and fourier transform technique,” International Journal on Smart and Intelligent Systems, Vol. 2, No. 3, pp. 345-380, 2009.
[18] L. C. Chen, X. L. Nguyen, F. H. Zhang and T. Y. Lin, “High-speed Fourier transform profilometry for reconstructing objects having arbitrary surface colours,” Journal of Optics, Vol. 12, p. 095502, 2010.
[19] W. Chen, X. Su, Y. Cao, L. Xiang and Q. Zhang, "Fourier transform profilometry based on a fringe pattern with two frequency components," Proc. of SPIE Vol. 6027, pp. 60271I1-60271I9, 2006.
[20] L. C. Chen, H. W. Ho and X. L. Nguyen, “Fourier transform profilometry (FTP) using an innovative bandpass filter for accurate 3-D surface reconstruction,” Journal of Optics and Laser in Engineering, Vol. 48, pp. 182–190, 2010.
[21] L. C. Chen, F. H. Zhuang and X. L. Nguyen, “3-D Vision for Inspection Robot using Fourier Transform Profi-lometry with color encoded fringe pattern robots,” CACS International Automatic Control Conference, Taipei, Taiwan, Nov. 27-29, 2009.
[22] CSEM: The SwissRanger, Manual V1.02. CSEM SA, 8048 Zurich, Switzerland 2006.
[23] R. Lange and P. Seitz, “Solid-state time-of-flight range camera,” IEEE Journal of Quantum Electronics, Vol. 37, pp. 390–397, 2001.
[24]J. Poppinga and A. Birk. “A Novel Approach to Efficient Error Correction for the SwissRanger Time-of-Flight 3D Camera,” In Proceedings of RoboCup, pp.247-258, 2008.
[25] Q. Wang, Q. Li, Z. Chen , J. Sun and R. Yao, “Range image noise suppression in laser imaging system,” Optics & Laser Technology, vol. 41, pp.140-147, 2009.
[26] K. M. Lee, P. Meer and R.-H. Park, “Robust Adaptive Segmentation of Range Images,” IEEE Trans. Pattern Anal. Machine Intell., vol. 20, pp. 200-205, Feb. 1998.
[27] L. C. Chen, X. L. Nguyen and C. W. Liang, “Object segmentation method using depth slicing and region growing algorithm,” International Conference on 3D Systems and Applications General, Tokyo, Japan, May. 2010.
[28] H. Gharavi and S. Gao, “3-D Segmentation and Motion Estimation of Range Data for Crash Prevention,” IEEE Intelligent Vehicles Symposium, Istanbul, Turkey, June 13-15, 2007.
[29] Fengliang Xu, Kikuo Fujimura, “Human Detection Using Depth and Gray Images,” Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS’03) 2003.
[30] M. Roggero, “Object segmentation with region growing and principal component analysis,” In: International Archives of Photogrammetry and Remote Sensing, Graz, Austria, Vol. XXXIV, Part 3A, 289–294, 2002.
[31] C. R. Muller, F. Peyrin, Y. Carrillon and C. Oldet, “Automated 3D region growing algorithm based on an assessment function,” Pattern Recognition Letters, vol. 23, pp. 137-150, 2002.
[32] K. Pulli and M. Pietikäinen, “Range Image Segmentation Based on Decomposition of Surface Normals,” Scandinavian Conference on Image Analysis (SCIA), Norway, 1993.
[33] B. Heisele and W. Ritter, “Segmentation of Range and Intensity Image Sequences by Clustering,” Proceedings of the International Conference on Information Intelligence and Systems, 1999.
[34] I. S. Chang and R. H. Park, “Segmentation based on fusion of range and intensity images using robust trimmed methods,” Pattern Recognition, vol. 34, pp. 1951-1962, Oct. 2001.
[35] J. Neira, J. D. Tardos, J. Horn and G. Schmidt, “Fusing Range and Intensity Images for Mobile Robot Localization,” IEEE Transaction on Robotics and Automation, vol. 15, no. 1, Feb. 1999.
[36] A. Golovinskiy, T. Funkhouser, “Min-Cut Based Segmentation of Point Clouds,” IEEE Workshop on Search in 3D and Video (S3DV) at ICCV, 2009.
[37] K. Klasing, D. Wollherr, and M. Buss, “A clustering method for efficient segmentation of 3D laser data,” in Proceedings IEEE ICRA, 2008.
[38] K. Klasing, D. Wollherr, M. Buss, “Realtime Segmentation of Range Data Using Continuous Nearest Neighbors,” Proceedings of the 2009 IEEE International Conference on Robotics and Automation (ICRA), Kobe, Japan, 2009.
[39] F. Moosmann, O. Pink and C. Stiller, “Segmentation of 3D Lidar Data in non-flat Urban Environments using a Local Convexity Criterion,” In IEEE Intelligent Vehicles Symposium, Xi''an, China, June 2009.
[40] X. Jiang, “An Adaptive Contour Closure Algorithm and Its Experimental Evaluation,” IEEE Trans. Pattern Anal. Machine Intell., vol. 22, pp. 1252-1265, Nov. 2000.
[41] L. Silva, O. R. P. Bellon, and P. F. U. Gotardo, “Edge-Based Image Segmentation using Curvature Sign Maps from Reflectance and Range Images,” Proceeding of ICIP, pp. 730-733, 2001.
[42] S. Stiene, K. Lingemann, A. Nuchter and J. Hertzberg, “Contour-based Object Detection in Range Images,” Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT''06), 2006.
[43] C. Zhang, T. Chen,“Efficient feature extraction for 2D/3D objects in mesh representation,” IEEE International Conference on Image Processing, 2001.
[44] E. Paquet, A. Murching, T. Naveen, A. Tabatabai, M. Rioux,“Description of shape information for 2-D and 3-D objects,”Signal Processing: Image Communication, Vol. 16, pp. 103-122, 2000.
[45] J. Corney, H. Rea, D. Clark, J. Pritchard, M. Breaks, R. Macleod,“Coarse filters for shape matching,” IEEE Computer Graphics and Applications, Vol. 22(3), pp. 65–74, 2002.
[46] M. Elad, A. Tal and S. Ar, “Content based retrieval of VRML objects - an iterative and interactive approach,” Proceedings of the sixth Eurographics workshop on Multimedia, pp. 97–108, 2001.
[47] L. C. Chen, X. L. Nguyen and Shy-Tsong Lin, “Automatic object detection employing viewing angle histogram for range images,” The 2012 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Kaohsiung, Taiwan, July 11-14, 2012.
[48] R. Osada, T. Funkhouser, B. Chazelle and D. Dobkin, “Shape distributions,” ACM Trans Graph, Vol. 21(4), pp. 807–832, 2002.
[49] H. Y. Shum, M. Hebert and K. Ikeuchi, “On 3D shape similarity,” Proc. IEEE Computer Vision and Pattern Recognition, pp. 526–531, 1996.
[50] J. Koendering, “Solid shape,” The MIT Press, 1990.
[51] S. J. Chua and R. Jarvis, “Point signatures: a new representation for 3D object recognition,”International Journal of Computer Vision, Vol. 25(1), pp. 63–65, 1997.
[52] A. E. Johnson and M. Hebert, “Using spin images for efficient object recognition in cluttered 3D scenes,”IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21(5), pp. 635–651, 1999.
[53] H. Q. Dinh and S. Kropac, “Multi-Resolution Spin-Images,” Computer Vision and Pattern Recognition (CVPR), June 2006.
[54] A. S. Mian, M. Bennamoun and R. A. Owens, “Matching Tensors for Automatic Correspondence and Registration,” ECCV, part 2, pp. 495-505, 2004.
[55] A. S. Mian, M. Bennamoun and R. A. Owens, “Performance Analysis of an Improved Tensor Based Correspondence Algorithm for Automatic 3D Modeling,” IEEE ICIP, October, 2004.
[56] A.S. Mian, M. Bennamoun, and R.A. Owens, "A novel algorithm for automatic 3D model-based free-form object recognition", in Proc. SMC (7), pp.6348-6353, 2004.
[57] M. Körtgen, G. J. Park, M. Novotni and R. Klein,“3D shape matching with 3D shape contexts,” Proc. 7th Central European Seminar on Computer Graphics, April 2003.
[58] A. Frome, D. Huber, R. Kolluri, T. Bulow, J. Malik, “Recognizing objects in range data using regional point descriptors,” In: Proc. European Conference on Computer Vision, vol. 3, pp. 224–237, 2004.
[59] H. Chen and B. Bhanu, “3D free-form object recognition in range images using local surface patches,” Pattern Recognition Letters, Vol. 28, pp. 1252–1262, 2007.
[60] H. Chen and B. Bhanu, “3D free-form object recognition in range images using local surface patches”. Proc. Internat. Conf. Pattern Recognition 3, 136–139, 2004.
[61] D. G. Lowe, “Distinctive Image Features from Scale- Invariant Keypoints,” International Journal of Computer Vision, vol.60, pp. 91-110, 2004.
[62] T. R. Lo and J. P. Siebert, “Local feature extraction and matching on range images: 2.5D SIFT,” Computer Vision and Image Understanding, Vol. 113, pp. 1235-1250, 2009.
[63] A. E. Johnson, M. Hebert, “Using spin images for efficient object recognition in cluttered 3D scenes,” IEEE Trans Pattern Anal Mach Intell, Vol. 21, pp. 635–651, 1999.
[64] O. Carmichael, D. Huber, M. Hebert, “Large data sets and confusing scenes in 3-d surface matching and recognition,” Second International Conference on 3-D Digital Imaging and Modeling, Ottawa, Ont., Canada, pp. 258–367, 1999.
[65] D. Huber, M. Hebert, “A new approach to 3-d terrain mapping,” International Conference on Intelligent Robotics and Systems, pp. 1121–1127, 1999.
[66] H. Quynh Dinh, S. Kropac, "Multi-Resolution Spin-Images," IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR''06), vol. 1, pp.863-870, 2006.
[67] Gonzalez, R.C., Woods, R.E. “Digital Image Processing”, Addison Wesley, 1992.
[68] Gui, V., Lacrămă, D., Pescaru, D. “Prelucrarea Imaginilor”, Editura Politehnica, Timişoara, 1999.
[69] A Recursive Approach to Identify the Objects in a 2D Image - Cezar Popescu (2005).
[70] R. Cutler and L.S. Davis, “Robust real-time periodic motion detection, analysis and applications”, IEEE Trans on Pattern Analysis and Machine Intelligence 22, (8) 2000.
[71] I. Haritaoglu, D. Harwood, and L. Davis, “W4: A real-time system for detection and tracking of people and monitoring their activities”, IEEE Trans. on Pattern Analysis and Machine Intelligence 22 (8), 809-830, August 2000.
[72] T. Darrell, G. Gordon, M. Harville, and J. Woodfill, “Integrated person tracking using stereo, color, and pattern detection”, Proc. Computer Vision and Pattern Classification, 601-608, Santa Barbara, CA, 1998.
[73] S. J. McKenna, S. Jabri, Z Duric, and H. Wechsler, “Tracking interacting people”, Int. Conf on Automatic Face and Gesture Classification, 572-578, Grenoble, France, March, 2000.
[74] D. M. Mount, ANN Programming Manual, Version 1.0, 2005.
[75] M. Donias, P. Baylou and N. Keskes, “Curvature Of Oriented Patterns: 2-D and 3-D Estimation from Differential Geometry,” ICIP 98. Proceedings. International Conference on Image Processing, 1998.
[76] T. Surazhsky, E. Magid snd O. Soldea O, “A comparison of gaussian and mean curvatures estimation methods on triangular meshes”, In Proceedings of the 2003 IEEE International Conference on Robotics and Automation, Taipei, 2003.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top