現在位置首頁 > 博碩士論文 > 詳目
論文中文名稱:基於顏色與特徵點之無標記擴增實境追蹤方法 [以論文名稱查詢館藏系統]
論文英文名稱:A Tracking Method for Markerless Augmented Reality System Based on Color and Feature Points [以論文名稱查詢館藏系統]
院校名稱:臺北科技大學
學院名稱:電資學院
系所名稱:資訊工程系研究所
畢業學年度:104
畢業學期:第二學期
出版年度:105
中文姓名:沈紹偉
英文姓名:shen shao-wei
研究生學號:103598021
學位類別:碩士
口試日期:2016/07/15
指導教授中文名:張厥煒
指導教授英文名:Chueh-Wei Chang
口試委員中文名:張厥煒;奚正寧;楊士萱
中文關鍵詞:擴增實境SURF無標記特徵追蹤
英文關鍵詞:Augment RealitySURFMarkerlessTracking
論文中文摘要:擴增實境為將三維虛擬模型結合到實際的視訊影像中之技術,近年來的應用領域日益增廣,此技術除了需要三維模型物件與視訊影像串流兩個部分,針對繪製三維虛擬模型還需要依據與參考實際視訊影像中的部分內容,稱之為目標物資訊。擴增實境系統必須在即時視訊串流下依據想要辨識的目標物資訊去呈現與運作,針對無標記目標物之擴增實境系統,在目標物的辨識與追蹤之計算量控制需額外小心,否則會造成影像中目標物追蹤延遲以及虛擬物件的放置不順等等問題。
本論文針對無標記擴增實境提供於視訊串流中偵測與追蹤目標物之方法,首先以目標物之顏色特徵做完整場景畫面中做目標物偵測,篩選出目標物可能出現之區域,接著針對該區域以SURF特徵點去做無標記之物件辨識,而非直接對整張場景影像去做特徵比對,並且於當前畫面確定存在目標物時,在下個畫面設置追蹤區域,直接在追蹤區域中比對特徵,並且進一步記錄目標物於場景中的位置,依據目標物位置的變動判斷是否需要重新計算三維空間資訊,減少串流影像處理之計算量,根據實驗結果,綜合來說整體系統與類似之方法比較,能夠減少大約60%以上之計算時間。
論文英文摘要:Augmented Reality (AR) is a technology that combine the real-time reality streaming with 3D virtual model, and has been applied to many different area. AR technology’s presentation need not only 3D virtual model information and camera streaming, but some reference information when we Render a 3D virtual model in a scene frame, which is called target information. Augment Reality system must run and be presented by recognize the target in the scene frame depend on the target information in real-time streaming, so it is important to pay attention to control the calculation which spend on target recognition and tracking, especially for markerless AR, otherwise it will lead to some issues, such as delay of the target tracking or unsmoothed when we render a 3D virtual model.
Because of the problem mentioned above, we provide a detection and tracking method which is applied to markerless augment reality system. By using color information of target image, we detect the target in the scene frame of the camera streaming, and filter the region which the target is most probably appear in, then get the feature points match of the region with target information, instead of match hole scene frame with target. Furthermore, in order to reduce calculation and improve the fluency, set the tracking region base on current target position in frame, for next frame’s match, and we make a judgement that if we have to recalculate the camera position by the difference between the target position of current frame and last frame, further reduce the calculation of overall system. According to the experiment result, compare with similar method, overall we can reduce about 60% calculation time.
論文目次:摘要 i
ABSTRACT ii
致 謝 iv
目 錄 v
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 3
1.3 論文架構 4
第二章 相關技術與文獻探討 5
2.1 現實-虛擬混和技術 5
2.2 擴增實境應用建置平台 6
2.3 尺度不變特徵與特徵索引 8
2.4 物件追蹤方法 9
2.5 無標記擴增實境系統相關文獻 12
2.5.1 Homography 19
第三章 系統架構 23
3.1 系統概要 23
3.2 系統流程 24
3.3.1 目標物與模型讀取系統流程概述 25
3.3.2 擴增實境主系統流程概述 26
第四章 目標物與模型資訊 28
4.1. 色彩空間 28
4.1.1 RGB色彩空間 29
4.1.2 HSV色彩空間 30
4.1.3 色彩分布資訊擷取 30
4.2. 尺度不變特徵擷取與索引建立 31
4.2.1 尺度不變特徵擷取 31
4.2.2 特徵索引建立 33
4.3. 三維模型物件檔資訊 33
4.3.1 素材檔讀取 35
4.3.2 模型物件資訊正規化 37
第五章 擴增實境主系統 38
5.1. 偵測目標物 39
5.1.1. 反向投影 40
5.1.2. 雜訊濾除 42
5.2. 比對區域與目標物特徵 45
5.2.1 特徵描述子之間的距離 45
5.3. 相機旋轉平移資訊計算 46
5.3.1 透視投影 46
5.3.2 攝影機成像模型 47
5.3.3 Perspective-n-point Problem 48
5.4. 三維模型繪製 54
5.5 追蹤與穩定機制 55
第六章 實驗結果 58
6.1. 實驗與系統環境 58
6.2. 實驗結果與探討 58
6.2.1. 運行時間結果比較與探討 59
6.2.2. 可能造成失敗之情況 69
6.2.3. 穩定度結果比較與探討 75
第七章 結論與未來展望 77
7.1. 結論 77
7.2. 未來展望 78
第八章 參考文獻 79
論文參考文獻:[1] M. Haller, M. Billinghurst and B. Thomas, Emerging Technologies of Augmented Reality: Interfaces and Design, United States: Idea Group Publishing, 2006, p. 262.
[2] R. T. Azuma, "A Survey of Augmented Reality," In Presence: Teleoperators and Virtual Environments, vol. 6, 1997, pp. 355-385.
[3] IKEA Taiwan 宜家家具(2013,07,29)。IKEA型錄擴增實境功能影片。取自https://www.youtube.com/watch?v=haRLBwJ3Tx8
[4] J. Ackerman. (2000,06,15). UNC Ultrasound/Medical Augmented Reality Research. Retrieved from http://www.cs.unc.edu/Research/us/
[5] H. Kato and M. Billinghurst, "Marker Tracking and HMD Calibration for a Video-Based Augmented Reality Conferencing System," 2nd IEEE and ACM International Workshop on, San Francisco, CA, 1999, pp. 85-94.
[6] S. Jackson. (2012,07,25). 3 Augmented Reality Frameworks for Windows Phone. Retrieved from https://dzone.com/articles/windows-phone-augmented-reality
-comparison
[7] EPFL. (2014,05,26). Camera Calibration using BazAR. Retrieved from http://cvlab.epfl.ch/software/bazar/calib.php
[8] P. Milgram, H. Takemura, A. Utsumi and F. Kishino, "Augmented Reality: A Class of Displays on the Reality-Virtuality Continuum," Telemanipulator and Telepresence Technologies, vol. 2351, 1994, pp. 282-292.
[9] V. Gaikar. (2012,5,21). Google Glass Brings Augmented Reality Into The Mainstream. Retrieved from http://www.tricksmachine.com/2012/05/google
-glass-brings-augmented-reality.html
[10] K. Carbotte. (2016,04,05). The HTC Vive Review. Retrieved from http://www.tomshardware.com/reviews/htc-vive-virtual-reality-hmd,4519.html
[11] M. Mozuch. (2016,03,18). Sonys PlayStation VR is Pretender, Not Contender for VR King at GDC 2016. Retrieved from http://www.idigitaltimes.com/
sonys-playstation-vr-pretender-not-contender-vr-king-gdc-2016-520456
[12] S. Sarkar. (2016,01,06). Oculus Rift Price Set at $599, Shipping in March. Retrieved from http://www.polygon.com/2016/1/6/10723218/oculus-rift-price-
release-date-pre-orders
[13] Microsoft. (2016). Microsoft HoloLens. Retrieved from https://www.microsoft
.com/microsoft-hololens/en-us
[14] Magicleap. (2016). Magicleap. Retrieved from https://www.magicleap.com/
#/home
[15] D. Bohn. (2015,01,21). Up Close with the HoloLens, Microsofts most Intriguing Product in Years. Retrieved from http://www.theverge.com/2015/1/21/7868251/
microsoft-hololens-hologram-hands-on-experience
[16] Philip Lamb. (2003). Retrieved from https://www.hitl.washington.edu/artoolkit/
[17] Vuforia. (2016). Retrieved from http://www.vuforia.com/
[18] Inglobe. (2011,05,25). ARToolKit Professional for Android. Retrieved from http://arblog.inglobetechnologies.com/?p=421
[19] ARToolKit. (2016,02,15). Natural Feature Tracking with Fiducial Markers. Retrieved from http://artoolkit.org/documentation/doku.php?id=3_Marker
_Training:marker_nft_fiducial_markers
[20] Unity. Retrieved from http://unity3d.com/cn/
[21] Vuforia Developer. (2016). Retrieved from https://developer.vuforia.com
[22] D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," International Journal of Computer Vision, vol. 60, 2004, pp. 91-110.
[23] Y. Ke and R. Sukthankar, "PAC-SIFT: a More Distinctive Representation for Local Image Descriptors," Computer Vision and Pattern Recognition, Proceedings of the 2004 IEEE Computer Society Conference on, vol2, 2004, pp. 511-517.
[24] H. Bay, T. Tuytelaars and L. Van Gool, "SURF: Speeded up Robust Features," Computer Vision and Image Understanding, vol. 110, 2006, pp. 346-359.
[25] L. Juan and O. Gwun, "A Comparison of SIFT, PCA-SIFT and SURF," Interational Journal of Image Processing, vol. 3, 2009, pp. 143-152.
[26] NTNU. k-Dimensional Tree. Retrieved from http://www.csie.ntnu.edu.tw/
~u91029/Position.html
[27] W. Hu, T. Tan, L. Wang and S. Maybank, "A Survey on Visual Surveillance of Object Motion and Behaviors," IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews, vol. 34, 2004, pp. 334-352.
[28] Q. Zang and R. Klette, "Object Classification and Tracking in Video Surveillance," Computer Analysis of Images and Patterns, vol. 2756, 2003, pp. 198-205.
[29] C. R. Wren, A. Azarbayejani, T. Darrell and A. P. Pentland, "Pfinder: Real-time Tracking of the Human Body," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, 1997, pp. 780-785.
[30] H. Fujiyoshi and A. J. Lipton, "Real-time Human Motion Analysis by Image Skeletonization," 4th IEEE Workshop on Applications of Computer Vision (WACV98), Princeton, NJ, 1998, pp. 15-21.
[31] D. S. Jang and H. I. Choi, "Moving Object Tracking using Active Models," ICIP 98. 1998 International Conference on, Chicago, IL, 1998, pp. 648-652.
[32] D. Comaniciu, V. Ramesh and P. Meer, "Kernel-based Object Tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, 2003, pp. 564-577.
[33] M. J. Lucena, "An Optical Flow Probabilistic Observation Model for Tracking," ICIP 2003. 2003 International Conference on, vol. 2, 2003, pp. 957-967.
[34] L. Z. Husz, M. A. Wallace and R. P. Green, "Tracking with a Hierarchical Partitioned Particle Filter and Movement Modelling," IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics, vol. 41, 2011, pp. 1571-1584.
[35] J. Purnama, D. Andrew and M. Galinium, "Geometry Learning Tool for Elementary School using Augmented Reality," Industrial Automation, Information and Communications Technology (IAICT), Bali, 2014, pp. 145-148.
[36] M. Hincapié, A. Caponio, H. Rios and E. G. Mendívil, "An Introduction to Augmented Reality with Applications in Aeronautical Maintenance," International Conference on Transparent Optical Networks, Stockholm, 2011, pp. 1-4.
[37] 陳頡 ,以環場視覺及擴增實境技術作室內停車之自動導引,碩士論文,國立交通大學,新竹,2014。
[38] T. Lee and T. Hollerer, "Multithreaded Hybrid Feature Tracking for Markerless Augmented Reality," IEEE Transactions on Visualization and Computer Graphics, vol. 15, 2009, pp. 355-368.
[39] T. S. Yee, H. Arshad and A. Abdullah, "Development of a PC-based Markerless Augmented Reality," Electrical Engineering and Informatics (ICEEI), Denpasar, 2015, pp. 49-53.
[40] L. Daniel and M. David, Mastering OpenCV with Practical Computer Vision Projects, Birmingham: Packt Publishing, 2012, pp. 95-122.
[41] M. Hamidia, "Markerless Tracking using Interest Window for Augmented Reality Applications," Multimedia Computing and Systems (ICMCS) International Conference on, Marrakech, 2014, pp. 20-25.
[42] Elan Dubrofsky, Homography Estmation, Master, The University of British Columbia, Vancouver, 2007.
[43] E. Rublee, V. Rabaud, K. Konolige and R. G. Bradski, "ORB: An Efficient Alternative to SIFT or SURF," IEEE International Conference on Computer Vision (ICCV), Barcelona, 2011, pp. 2564-2571.
[44] R. Hartley and A. Zisserman, Multiple View Geomerty in Computer Vision, New York: Cambridge University Press, 2003, pp. 87-127.
[45] R. Collins. Planar Homographies. Retrieved from http://www.cse.psu.edu/
~rtc12/CSE486/lecture16.pdf
[46] H. E. Burdick. (2004) Color Spaces. Retrieved from http://www.viz.tamu.edu
/faculty/parke/ends375f04/notes/sec1_4.html
[47] Mevislab. (2013,02,08). Color Model Converter. Retrieved from http://mevislabdownloads.mevis.de/docs/2.4/MeVisLab/Standard/Documentation/Publish/ModuleReference/ColorModelConverter.html
[48] S. Boulos. Appendix B1. Object Files. Retrieved from http://www.cs.utah.edu
/~boulos/cs3505/obj_spec.pdf
[49] BRender Tutorial. (2012,07,11). Guide:1 Setting the Scene:Scene Description. Retrieved from http://rr2000.toshiba-3.com/R4/BRENDER/UGBK_6.HTM
[50] OpenCV. (2015,12,18). Real Time Pose Estimation of a Textured Object. Retrieved from http://docs.opencv.org/3.1.0/dc/d2c/tutorial_real_time_pose.html
#gsc.tab=0
[51] X. S. Gao, X. R. Hou, J. Teng and H. F. Cheng, "Complete Solution Classification for the Perspective-Three-Point Problem," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, 2003, pp. 930-943.
[52] Iplimage. (2012,05,28). The P3P (Perspective-Three-Point) Principle. Retrieved from http://iplimage.com/blog/p3p-perspective-point-overview/
[53] W. T. Wu, "Basic Principles of Mechanical Theorem Proving in Elementary Geometries," Journal of Automated Reasoning, vol. 2, 1986, pp. 221-252.
[54] N. Ho. (2013,05,10). Finding Optimal Rotation and Translation between Corresponding 3D Points. Retrieved from http://nghiaho.com/?page_id=671
論文全文使用權限:同意授權於2019-08-18起公開