跳到主要內容

臺灣博碩士論文加值系統

(3.235.227.117) 您好!臺灣時間:2021/07/28 03:53
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:賴柏任
研究生(外文):Po-Jen Lai
論文名稱:三維透明物體辨識系統於服務型機器人之應用
論文名稱(外文):3D Transparent Object Recognition for Service Robotics
指導教授:羅仁權羅仁權引用關係
口試委員:張帆人顏炳郎
口試日期:2015-07-30
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:78
中文關鍵詞:服務型機器人透明物體辨識姿態辨識機器人作業系統
外文關鍵詞:Service RoboticsTransparent Object RecognitionPose EstimationRobot Operating System
相關次數:
  • 被引用被引用:1
  • 點閱點閱:350
  • 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
隨著科技的進步,讓生活變得更自動化的需求是擋不住的浪潮。屆時,將有許多的服務型機器人會深入到人類的環境中進行各式各樣的任務,例如在家中幫忙倒牛奶、在餐廳中幫忙端水等等。在我們的生活中,用到了許多透明的物體,包括玻璃杯、寶特瓶、甚至是玻璃門,若機器人沒有能力辨認透明物體,將會造成許多問題,這些問題包含機器人容易毀損玻璃杯、容易撞到玻璃門或窗戶等等,不僅僅會造成機器人工作上的不便利、損壞的玻璃更可能造成人類的危險。因此,在此篇論文中,我們提出了一個透明物體的姿態辨識系統,其中我們將討論的重心放在透明物體的辨識上,輔以討論姿態辨識的模組以及抓取的模組。之所以將重心放在透明物體的辨識上,是因為姿態辨識以及抓取的功能在非透明物體上已經有相當成熟的研究。然而,辨識透明物體的研究是近十幾年來才漸漸發展起來,而且論文數量相當稀少,我們若能發展出有效的透明物體辨識演算法,將場景中透明物體所在的位置標示出來,接下來的姿態辨識和抓取的方法就可以參考適用於非透明物體的技術了。
故關於辨識透明物體,我們討論了三種方法,第一種使用RGBD感測器來感測場景、利用感測器的特性加以辨認出透明物體的所在位置。第二種及第三種方法都使用一般的相機當作感測器,分別使用Latent Dirichlet Analysis以及Deep Learning的機器學習方法來學習辨識透明物體。雖然探討了三種方法,我們主要使用第一種方法辨識到的透明物體輪廓當作姿態辨認模組的輸入。
於是,我們可以使用已經儲存在資料庫裡的透明物體3D模型,配合前述方法所找到的透明物體輪廓,可以利用配準的方式進行姿態的估計,進而得到物體姿態的估計值。


With the advancement of technology, the trend to make our lives more convenient by robot technology is unstoppable. In the future, many service robots will enter our living environments to do all kind of tasks from pouring milk for us in our home to serve water in restaurants. In our living environment, there are lots of transparent objects including cups made of glass, PET bottles and glass doors. If a robot who serve in our environment cannot recognize transparent objects, it might easily broke the transparent objects made by glass, it might not be able to open the door made of glass, it might bump into and broke glass windows and cause danger. As a result, we propose algorithms that make a robot be able to recognize and estimate the pose of transparent objects in this thesis. We emphasize on transparent object recognition because pose estimation and manipulation for non-transparent objects are relatively mature, while research on transparent object recognition just starts from a decade ago with a few papers discussing this problem. If we can develop effective algorithm for recognizing transparent object, we can take advantage of pose estimation and grasping for non-transparent object to build a complete system for grasping transparent objects.
For recognizing transparent object, we discuss three methods in this thesis. The first method which uses RGBD sensor to detect the transparent object is mainly used because the result is suitable for pose estimation.
With the stored 3D model of transparent object and the silhouettes of transparent object, we can estimate the pose by matching the model and the silhouette. Experiments show that our method can be used to detect and estimate the pose of transparent objects.


誌謝 i
中文摘要 ii
ABSTRACT iii
CONTENTS iv
LIST OF FIGURES vii
LIST OF TABLES x
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Problem statement 3
1.3 Literature Review 4
1.4 Contributions 5
1.5 Thesis Organization 6
Chapter 2 System Architecture 7
2.1 Robot Operating System (ROS) 7
2.2 Hardware Introduction 12
2.2.1 Personal Robot 2 (PR2) 12
2.2.2 Kinect 15
Chapter 3 Detection of Transparent Objects 17
3.1 Grabcut-Based Method 17
3.1.1 Overall process of Grabcut-based method 17
3.1.2 Grabcut 19
3.1.3 Transparent Object Classification 22
3.2 LDA-Based Method 24
3.2.1 Gaussian Mixture Model (GMM) 24
3.2.2 Probabilistic Latent Semantic Analysis (pLSA) & Latent Dirichlet Allocation (LDA) 26
3.2.3 LDA for transparent object detection 31
3.3 Deep Learning-Based Method 33
3.3.1 Deep Neural Network & Convolutional Neural Network 34
3.3.2 Regions with Convolutional Neural Network (R-CNN) 38
3.3.3 Selective Search 39
Chapter 4 Pose Estimation of Transparent Objects 48
4.1 Training 49
4.1.1 Model Construction 49
4.1.2 Silhouettes Generation 53
4.2 Testing 54
4.2.1 Test Silhouette Detection 54
4.2.2 Initial Pose Estimation 54
4.2.3 Pose Refinement 56
Chapter 5 Grasping 57
5.1 ROS tf for Coordinate Transform 57
5.2 PR2 manipulation pipeline 61
Chapter 6 Experiment 64
6.1 Experiment Setup 64
6.2 Detection of Transparent Objects 64
6.2.1 Grabcut-based Method 64
6.2.2 Deep Learning Based Method 67
6.3 Pose Estimation of transparent Objects 71
Chapter 7 Conclusion and Future Works 73
REFERENCE 74
Curriculum Vitae 78

[1]M. Osadchy, D. Jacobs, and R. Ramamoorthi, "Using specularities for recognition," in Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, 2003, pp. 1512-1519.
[2]K. McHenry, J. Ponce, and D. Forsyth, "Finding glass," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005, pp. 973-979.
[3]M. Fritz, G. Bradski, S. Karayev, T. Darrell, and M. J. Black, "An additive latent feature model for transparent object recognition," in Advances in Neural Information Processing Systems, 2009, pp. 558-566.
[4]C. J. Phillips, K. G. Derpanis, and K. Daniilidis, "A novel stereoscopic cue for figure-ground segregation of semi-transparent objects," in Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on, 2011, pp. 1100-1107.
[5]I. Lysenkov, V. Eruhimov, and G. Bradski, "Recognition and pose estimation of rigid transparent objects with a kinect sensor," Robotics, p. 273, 2013.
[6]I. Lysenkov and V. Rabaud, "Pose estimation of rigid transparent objects in transparent clutter," in Robotics and Automation (ICRA), 2013 IEEE International Conference on, 2013, pp. 162-169.
[7]ROS.org, http://www.ros.org/ [Online; accessed 30-July-2015].
[8]Understanding ROS Topics,
http://wiki.ros.org/action/fullsearch/ROS/Tutorials/UnderstandingTopics [Online; accessed 30-July-2015].
[9]Understanding ROS Services and Parameters,
http://wiki.ros.org/ROS/Tutorials/UnderstandingServicesParams[Online; accessed 30-July-2015].
[10]Smisek, Jan, Michal Jancosek, and Tomas Pajdla. "3D with Kinect." Consumer Depth Cameras for Computer Vision. Springer London, 2013. 3-25.
[11]Meshlab, http://meshlab.sourceforge.net/ [Online; accessed 30-July-2015].
[12]B. Tuong-Phong, "Illumination for computer-generated images," University of Utah, pp. 29-51, 1973.
[13]Rother, Carsten, Vladimir Kolmogorov, and Andrew Blake. "Grabcut: Interactive foreground extraction using iterated graph cuts." ACM Transactions on Graphics (TOG) 23.3 (2004): 309-314.
[14]Boykov, Yuri, Olga Veksler, and Ramin Zabih. "Fast approximate energy minimization via graph cuts." Pattern Analysis and Machine Intelligence, IEEE Transactions on 23.11 (2001): 1222-1239.
[15]Goldberg, Andrew V., and Robert E. Tarjan. "A new approach to the maximum-flow problem." Journal of the ACM (JACM) 35.4 (1988): 921-940.
[16]Y. Raja, S. McKenna, and S. Gong, ``Segmentation and tracking using color mixture models,'' in Asian Conference on Computer Vision, Hong Kong, January 1998.
[17]S. McKenna, Y. Raja, and S. Gong, ``Object tracking using adaptive color mixture models,'' in Advances in Color Machine Vision, ACCV Spec. Sess., Hong Kong, January 1998.
[18]C. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, 1995.
[19]G. J. McLachlan and K. E. Basford, Mixture Models: Inference and Applications to Clustering, Marcel Dekker Inc., New York, 1988.
[20]C. E. Priebe, ``Adaptive mixtures,'' J. Amer. Stat. Assoc., vol. 89, no. 427, pp. 796-806, 1994.
[21]C. E. Priebe and D. J. Marchette, ``Adaptive mixtures: Recursive nonparametric pattern recognition,'' Pattern Recognition, vol. 24, no. 12, pp. 1197-1209, 1991.
[22]C. E. Priebe and D. J. Marchette, ``Adaptive mixture density estimation,'' Pattern Recognition, vol. 26, no. 5, pp. 771-785, 1993.
[23]D. M. Titterington, A. F. M. Smith, and U. E. Makov, Statistical Analysis of Finite Mixture Distributions, John Wiley, New York, 1985.
[24]G. Borgefors, "Hierarchical chamfer matching: A parametric edge matching algorithm," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 10, pp. 849-865, 1988.
[25]I. L. Dryden and K. V. Mardia, Statistical shape analysis vol. 4: Wiley Chichester, 1998.
[26]P. J. Besl and N. D. McKay, "Method for registration of 3-D shapes," in Robotics-DL tentative, 1992, pp. 586-606.
[27]R. Hartley and A. Zisserman, Multiple view geometry in computer vision: Cambridge university press, 2003.
[28]A. W. Fitzgibbon, "Robust registration of 2D and 3D point sets," Image and Vision Computing, vol. 21, pp. 1145-1153, 2003.
[29]Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. IEEE, 2014.
[30]C. Gu, J. J. Lim, P. Arbelaez, and J. Malik. Recognition using regions. In CVPR, 2009.
[31]J. Uijlings, K. van de Sande, T. Gevers, and A. Smeulders. Selective search for object recognition. IJCV, 2013.
[32]J. Carreira and C. Sminchisescu. CPMC: Automatic object segmentation using constrained parametric min-cuts. TPAMI, 2012.
[33]Y. Jia. Caffe: An open source convolutional architecture for fast feature embedding. http://caffe.berkeleyvision.org/, 2013.
[34]A. Krizhevsky, I. Sutskever, and G. Hinton. ImageNet classification with deep convolutional neural networks. In NIPS, 2012.
[35]ROS Object manipulator, http://wiki.ros.org/object_manipulator [Online; accessed 30-July-2015].


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
無相關期刊
 
無相關點閱論文