請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69928完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 連豊力 | |
| dc.contributor.author | Jian-hao Huang | en |
| dc.contributor.author | 黃建豪 | zh_TW |
| dc.date.accessioned | 2021-06-17T03:34:32Z | - |
| dc.date.available | 2018-03-01 | |
| dc.date.copyright | 2018-03-01 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-02-13 | |
| dc.identifier.citation | [1: Mur-Artal et al. 2015]
Raúl Mur-Artal, J. M. M. Montiel and Juan D. Tardós, “ORB-SLAM: A Versatile and Accurate Monocular SLAM System,” IEEE Transactions on Robotics, vol. PP, No. 99, pp.1-17, 2015. [2: Davison et al. 2007] G. Klein and D. W. Murray, “Parallel tracking and mapping for small AR workspaces,” in Proceedings of the International Symposium on Mixed and Augmented Reality (ISMAR), 2007. [3: Klein & Murray 2007] A. Davison, I. Reid, N. Molton, and O. Stasse, “MonoSLAM: Real-time single camera SLAM,” Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 29, 2007. [4: Forster et al. 2014] C. Forster, M. Pizzoli, D. Scaramuzza, “SVO: Fast semi-direct monocular visual odometry,” in Proceedings of IEEE International Conference on Robotics and Automation (ICRA), pp.15-22, May 31, June 2014. [5: Mur-Artal & Tardós 2015] Raúl Mur-Artal and Juan D. Tardós, “Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM,” Robotics: Science and Systems Conference, Rome, Italy, July 2015. [6: Concha & Civera 2014] A. Concha and J. Civera, “Using superpixels in monocular SLAM,” in Proceedings of IEEE International Conference on Robotics and Automation (ICRA), HKSAR, China, pp. 365-372, May 31-June 7, 2014. [7: Ranftl et al. 2014] R. Ranftl, V. Vineet, Q. Chen, and V. Koltun, “Dense monocular depth estimation in complex dynamic scenes,” in Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [8: Valgaerts et al. 2014] L. Valgaerts, A. Bruhn, M. Mainberger, and J. Weickert, “Dense versus sparse approaches for estimating the fundamental matrix,” Journal of Computer Vision (IJCV), vol. 96, Issue. 2, pp. 212-234, 2012. [9: Engel et al. 2017] J. Engel, V. Koltun, and D. Cremers, “Direct sparse odometry,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. PP, Issue. 99, 2017. [10: Jin et al. 2013] H. Jin, P. Favaro, and S. Soatto, “A semi-direct approach to structure from motion,” The Visual Computer, vol. 19, Issue. 6, pp. 377-394, October, 2013. [11: Engel et al. 2014] J. Engel, T. Schöps, and D. Cremers, “LSD-SLAM:Large-scale Direct Monocular SLAM,” in Proceedings of the European Conference on Computer Vision (ECCV), Zürich, pp. 834-849,Sep. 6-12, 2014. [12: Concha & Civera 2015] A. Concha and J. Civera, “DPPTAM: Dense piecewise-planar tracking and mapping from a monocular sequence,” in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, pp. 5686-5693, Sept. 28-Oct. 2, 2015. [13: Pizzoli et al. 2014] M. Pizzoli, C. Forster, D. Scaramuzza, “REMODE: Probabilistic, monocular dense reconstruction in real time,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 2609-2616, May 3, June 7, 2014. [14: Newcombe et al. 2011] R. A. Newcombe, S. J. Lovegrove, and A. J. Davison, “DTAM: Dense tracking and mapping in real-time,” in Proceedings of the International Conference on Computer Vision (ICCV), 2011. [15: Engel et al. 2014] J. Engel, J. Stueckler, and D. Cremers, “Large-scale direct slam with stereo cameras,” in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, pp. 1935-1942, Sept. 28-Oct. 2, 2015. [16: Kuschk & Cremers 2013] G. Kuschk and D. Cremers, “Fast and accurate large-scale stereo reconstruction using variational methods,” in Proceedings of IEEE International Conference on Computer Vision Workshops (ICCVW), Sydney, NSW, pp. 700-707, Dec. 2-8, 2013. [17: Geiger et al 2011] A. Geiger, J. Ziegler, and C. Stiller, “StereoScan: Dense 3d reconstruction in real-time,” IEEE Intelligent Vehicles Symposium (IV), Baden-Baden, pp. 963-968, June 5-9, 2011. [18: Kerl et al. 2013] C. Kerl, J. Sturm and D. Cremers, “Robust odometry estimation for RGB-D cameras,” in Proceedings of IEEE International Conference on Robotics and Automation (ICRA), Karlsruhe, pp. 3748-3754, May 6-10, 2013. [19: Whelan et al. 2015] T. Whelan, S. Leutenegger, R. S. Moreno, B. Glocker and A. Davison, “Elasticfusion: Dense SLAM without a pose graph,” in Proceedings of Robotics: Science and Systems, Rome, Italy, pp. 1-10, July 13-17, 2015. [20: Whelan et al. 2015] T. Whelan, M. Kaess, H. Johannsson, M. Fallon, J. J. Leonard and J. McDonald, “Real-time large scale dense RGB-D SLAM with volumetric fusion,” International Journal of Robotics Research, vol. 34, No. 4-5, pp. 598-626, April, 2015. [21: Taketomi et al. 2017] T. Whelan, M. Kaess, H. Johannsson, M. Fallon, J. J. Leonard and J. McDonald, “Visual slam algorithms: a survey from 2010 to 2016,” IPSJ Transactions on Computer Vision & Applications, vol. 9, No. 1, p. 16, December, 2017. [22: Strasdat et al. 2010] H. Strasdat, J. M. M. Montiel, and A. Davison, “Scale drift-aware large scale monocular SLAM,” in Proceedings of Robotics: Science and Systems (RSS), Universidad de Zaragoza, Zaragoza, Spain, June 27 - June 30, 2010. [23: Sturm et al. 2012] J. Sturm, N. Engelhard, F. Endres, W. Burgard, and D. Cremers, “A benchmark for the evaluation of rgb-d slam systems,” in Proceedings of International Conference on Intelligent Robot Systems (IROS), Oct. , 2012. [24: Engel et al. 2014] J. Engel, J. Sturm, and D. Cremers, “Scale-aware Navigation of a Low-cost Quadrocopter with a Monocular Camera,” Robotics and Autonomous Systems (RAS), vol. 62, pp. 1646-1656, 2014. [25: Mellinger et al. 2011] D. Mellinger and V. Kumar, “Minimum snap trajectory generation and control for quadrotors,” in Proceedings of IEEE International Conference on Robotics and Automation (ICRA), 2011. [26: Lindsey et al. 2011] Q. Lindsey, D. Mellinger, and V. Kumar, “Construction of cubic structures with quadrotor teams,” Autonomous Robots, vol. 33, Issue. 3, pp. 323-336, October, 2012. [27: Ritz et al. 2012] R. Ritz, M. Mueller, and R. D’Andrea, “Cooperative quadrocopter ball throwing and catching,” in Proceedings of International Conference on Intelligent Robot Systems (IROS), vol. 33, Issue. 3, pp. 323-336, October, 2012. [28: Kushleyev et al. 2012] A. Kushleyev, D. Mellinger, and V. Kumar, “Towards a swarm of agile micro quadrotors,” Autonomous Robots, vol. 35, Issue. 4, pp. 287-300, November, 2013. [29: Grzonka et al. 2012] S. Grzonka, G. Grisetti, and W. Burgard, “A Fully Autonomous Indoor Quadrotor,” IEEE Transaction on Robotics, vol. 28, No. 1, February, 2012. [30: Bristeau et al. 2011] P. Bristeau, F. Callou, D. Vissière, N. Petit, et al. , “The Navigation and Control technology inside the AR.Drone micro UAV,” in Proceedings of the 18th World Congress The International Federation of Automatic Control, vol. 44, Issue. 1, pp. 1477-1484, January, 2011. [31: Lucas et al. 2014] V. S. Lucas, S. B. Alexandre, and S. F. M´ario, “Navigation and Cooperative Control Using the AR.Drone Quadrotor,” Journal of Intelligent & Robotic System, Vol. 84, Issue. 1-4 pp. 327-350, December, 2016. [32: Engel et al. 2013] J. Engel, T. Schöps, and D. Cremers, “Semi-dense Visual Odometry for a Monocular Camera,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013. [33: Wurm et al. 2013] K. M. Wurm, A. Hornung, M. Bennewitz, C. Stachniss, and W. Burgard, “OctoMap: an efficient probabilistic 3D mapping framework based on octrees,” Autonomous Robots, vol. 34, Issue. 3, pp. 189-206, April, 2013. Website [34: ROS from OSRF, Inc] Robot Operating System. (2007, May), Open Source Robotics Foundation, Inc. Official Website. Retrieved December 11, 2017, from http://www.ros.org/ [35: Gazebo from OSRF, Inc] Gazebo. (2009), Open Source Robotics Foundation, Inc. Official Website. Retrieved December 11, 2017, from http://www.gazebosim.org/ [36: Hamer et al. 2014] M. Hamer (mikehamer), J. Engel, S. Parekh, et al. ardrone_autonomy Free Software on http://ardrone-autonomy.readthedocs.io/en/latest/index.html [37: Khandelwal 2013] P. Khandelwal (piyushk), freenect_stack (Microsoft Kinect ROS Driver) Free Software on http://wiki.ros.org/freenect_launch [38: Kinect calibration] ROS, Intrinsic calibration of the Kinect cameras Free Software on http://wiki.ros.org/openni_launch/Tutorials/IntrinsicCalibration [39: Matlab camera calibration] Matlab, Camera calibration Free Software on https://www.mathworks.com/help/vision/ref/estimatecameraparameters.html Book [40: Hartley & Zisserman 2004] R.I. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, second edition, 2004. [41: Sedgewick & Wayne 2011] R. Sedgewick and K. Wayne, Algorithms, Princeton University, Fourth edition, 2011. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69928 | - |
| dc.description.abstract | 近幾年來，機器人自主導航是一個熱門且具有挑戰的主題，這項技術可以應用在環境的探勘或是運送貨物。在機器人自主導航中環境感知是一個重要的一環，特別是在GPS信號被遮蔽區域的室內環境中，本篇利用機器人上的相機錄製的視頻透過LSD SLAM[11: Engel et al. 2014]去計算每個關鍵偵的深度資訊，將其關鍵偵的RGB影像及深度圖抽出，利用區域增長的方式將紋理梯度較低的區域抽取出來，並且基於人造的環境紋理較低的區域大部分都是平面的假設，提出一個深度填補的方法，優化每個關鍵偵的深度地圖的稠密度，提供機器人更豐富的環境資訊在自主導航應用上面，在單目SLAM遇到的尺度問題，本篇使用環境中已知的物件去計算尺度，並利用計算得到的尺度去定義深度填補中的閥值去濾除不合理的填補，
本文利用Gazebo 模擬器[35: Gazebo from OSRF, Inc] 慕尼黑官方數據集[23: Sturm et al. 2012]和實驗使用微軟Kinect傳感器針對幾種方法做了比較 比較結果顯示本篇深度填補的方法在單眼SLAM片段平面上比LSD SLAM[11: Engel et al. 2014] 和DPPTAM[12: Concha & Civera 2015]更加稠密。 | zh_TW |
| dc.description.abstract | Visual navigation of robot has been a popular and a challenge research topic in past few years. One of important part for navigation is environment sensing. Especially for previously unknown and GPS-denied environments, this thesis uses monocular camera to obtain image data and estimates the depth map information in each keyframe by LSD SLAM [11: Engel et al. 2014]. RGB image and depth map in each keyframe are extracted to detect low texture regions by region growing segmentation method. The assumption made is that image areas with low photometric gradients are mostly planar which is met in most indoors and man-made scene. This thesis proposes a depth filling method to optimize the depth map completeness in each keyframe. It can provide robot more environment information to apply on navigation. For monocular unknown scalar problem, the assigned marker in the scene is used to compute the scale. However, the estimated scale is used to define the thresholds that are used to filter out the unreasonable plane estimation in depth filling process.
This thesis compares the depth filling method against several alternatives using Gazebo simulation [35: Gazebo from OSRF, Inc], public Tum dataset [23: Sturm et al. 2012], and experiment with a Microsoft Kinect sensor. The comparison demonstrate that our depth filling method for piecewise planar monocular SLAM is denser than LSD SLAM [11: Engel et al. 2014] and DPPTAM [12: Concha & Civera 2015]. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T03:34:32Z (GMT). No. of bitstreams: 1 ntu-107-R03921062-1.pdf: 7591250 bytes, checksum: 9ec2ebc2aec48aadc1ab3cd562746fae (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 摘要 ii
ABSTRACT iv CONTENTS vi LIST OF FIGURES viii LIST OF TABLES xi Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Problem Formulation 2 1.3 Contributions 4 1.4 Organization of the Thesis 4 Chapter 2 Background and Literature Survey 5 Chapter 3 Related Algorithms 9 3.1 Camera Pin-hole Model 9 3.2 Convex Hull 12 3.3 K-Means Clustering 13 3.4 Disjoint-set data structure 16 Chapter 4 Dense Piecewise Plane Mapping from a Monocular Image Sequence 18 4.1 Introduction of Input Data 20 4.2 Plane Segmentation and Extraction 22 4.2.1 Gradient Estimation 22 4.2.2 Region Growing Segmentation 25 4.3 Scale Estimation for Monocular SLAM 28 4.4 Plane Fitting at Lower Texture Region 31 4.4.1 Sparse Filter 33 4.4.2 Direct Least Square for Plane Estimation 37 4.4.3 K-Means Down Sample 37 4.4.4 Non-Dense Filter 38 4.4.5 Vote and Remove Outlier of Depth Point 41 4.5 Project Fitting Plane to Depth Map 44 Chapter 5 Experimental Results and Analysis 49 5.1 Environments Setting 49 5.1.1 Robot Operating System 49 5.1.2 Gazebo 50 5.1.3 RGB-D Sensor 51 5.1.4 Two Wheel Robot 53 5.2 Depth Filling Simulations 54 5.2.1 Manhattan Corridor 56 5.2.2 National Taiwan University Ming-Da Hall 6F 66 5.3 Depth Filling on TUM Dataset 75 5.3.1 fr3_nonstructure_texture 78 5.3.2 fr3_structure_texture 83 5.4 Experiment 89 5.4.1 Kinect Camera Parameters 90 5.4.2 Accuracy of Kinect Sensor 91 5.4.3 NTU Ming-Da Hall sixth floor east south corridor 94 5.5 Comparison of Direct Mapping Alternatives 103 5.5.1 LSD SLAM vs. LSD SLAM + Depth Filling 104 5.5.2 LSD SLAM + Depth Filling vs. DPPTAM 105 5.6 Large-Scale Experiments 107 5.6.1 NTU Ming-Da Hall first floor 107 5.6.2 NTU Ming-Da Hall fifth floor 113 Chapter 6 Conclusions and Future Works 121 6.1 Conclusions 121 6.2 Future Works 122 6.2.1 Plane Estimation in Depth Filling 122 6.2.2 Scale Estimation with Measurements 124 REFERENCES 125 | |
| dc.language.iso | en | |
| dc.title | 基於單眼視頻低梯度區域深度估計之稠密片段平面地圖重建 | zh_TW |
| dc.title | Dense Piecewise Planar Reconstruction based on Low Gradient Region Depth Estimation from a Monocular Image Sequence | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 黃正民,李後燦,簡忠漢 | |
| dc.subject.keyword | 單眼視覺同步定位與地圖構建,相機定位,半稠密地圖重建,深度填補,機器人導航, | zh_TW |
| dc.subject.keyword | Visual SLAM,camera localization,semi-dense map reconstruction,depth filling,robot navigation, | en |
| dc.relation.page | 129 | |
| dc.identifier.doi | 10.6342/NTU201800355 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2018-02-13 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-107-1.pdf 目前未授權公開取用 | 7.41 MB | Adobe PDF |
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。