以OpenCV發展立體視覺線掃描攝影機平台之三維影像重建技術

Development of 3D Image Reconstruction Techniques Based on OpenCV for a Stereovision Platform Using Line Scan Cameras

10.6840/cycu201600656

謝宗浩

三維影像重建 ； 自動化光學檢測 ； 線CCD ； 立體視覺 ； 半全域區塊匹配 ； 視差估算 ； 3D image reconstruction ； automated optical inspection ； stereo vision ； linear CCD ； semi global block matching ； disparity estimation

中原大學機械工程學系學位論文

2016年

碩士

陳冠宇

繁體中文

本文使用二部線CCD、一組精密伺服馬達驅動之單軸移動平台及LED光源，發展一套具備三維影像重建功能之自動光學檢測系統。完成硬體設備後，本文比較區塊匹配、半全域區塊匹配、圖形切割三種視差深度演算法及平均平滑、高斯平滑、等兩種濾波方法的效能，以決定採用何種方法重建深度影像；其次，開發使用者圖形介面整合單軸平台運動及線CCD控制與參數調整等功能，讓使用者可藉此介面操控整套系統。根據實驗結果顯示，本文發展之系統平均只需3秒即可建立失真率約3%的待檢物之三維影像。

This paper aims to develop an automated optical inspection (AOI) system for 3D image reconstruction consisting of two line scan cameras, a single-axis motion platform driven by servo motor, and LED light sources. After completing the hardware device, in this paper, three disparity estimation algorithms such as block matching (BM), semi global block matching (SGBM), and graph cut (GC), are applied to the AOI system for comparing their performance. So we can choose the best one for the AOI system to reconstruct depth images. Next, this paper develops a graphical user interface (GUI) for users to manipulate the AOI system including control of the single-axis motion platform and line scan cameras, and parameters adjustment. Experimental results show that the proposed AOI system can reconstruct the depth image of a workpiece in just three seconds with average distortion rate 3%.

1. [1] D. Marr and T. Poggio, “Cooperative computation of stereo disparity,” Science, Vol. 194, pp. 283-287, 1976.
   連結：
2. [2] S. T. Barnard and W. B. Thompson, “Disparity analysis of images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-2, No. 4, pp. 330-340, 1980.
   連結：
3. [5] R. Y. Tsai, “A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses,” IEEE Journal of Robotics and Automation, Vol. 3, No. 4, pp. 323-344, 1987.
   連結：
4. [6] A. Izaguirre, P. Pu, and J. Summers, “A new development in camera calibration: calibrating a pair of mobile cameras,” International Journal of Robotics Research, Vol. 6, No. 3, pp. 104-116, 1987.
   連結：
5. [8] W. Y. Yau and H. Wang, “Fast relative depth computation for an active stereo vision system,” Journal of Real-Time Imaging, Vol. 5, No. 3, pp. 191-204, 1999.
   連結：
6. [9] 李思漢, 基於匹配代價之非對稱立體匹配遮蔽偵測, 國立中央大學通訊工程研究所碩士論文, 2011.
   連結：
7. [10] 石家偉, 基於成本推算區域立體匹配之高解析度影像快速視差估計, 國立成功大學電腦與通信工程研究所碩士論文, 2013.
   連結：
8. [12] S. Sengupta, “Effects of unequal focal lengths in stereo imaging,” Pattern Recognition Letters, Vol. 18, pp. 395-400, 1997.
   連結：
9. [13] H. Ren and S. T. Wu, “Variable-focus liquid lens,” Optics Express, Vol. 15, No. 10, pp. 5931-5936, 2007.
   連結：
10. [14] K. Y. Chen, C. C. Chien, and C. T. Tseng, “Improving the accuracy of depth estimation in binocular vision for robotic applications,” Applied Mechanics and Materials, Vol. 284-287, pp. 1862-1866, 2013.
    連結：
11. [15] J. Qi, R. M. Leahy, S. R. Cherry, A. Chatziioannou, and T. H. Farquhar, “High-resolution 3D Bayesian image reconstruction using the microPET small-animal scanner,” Physics in Medicine and Biology, Vol. 43, No. 4, pp. 1001-1013, 1998.
    連結：
12. [18] 蘇致融, 利用雙稜鏡拍攝於3D影像重建, 國立成功大學電腦與通信工程研究所碩士論文, 2010.
    連結：
13. [19] 錢鉦津, 改良式立體視覺演算法應用於機器人視覺系統之研究, 中原大學機械工程系博士論文, 2013.
    連結：
14. [21] V. Kolmogorov, P. Monasse, and P. Tan, “Kolmogorov and Zabih’s graph cuts stereo matching algorithm,” IPOL Journal, Vol. 4, pp.220-251, 2014.
    連結：
15. [23] H. Hirschmuller, “Accurate and efficient stereo processing by semi-global matching and mutual information,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, Jun. 20-25, 2005, Vol. 2, pp. 807-814.
    連結：
16. [25] 楊儒松, 陳冠宇, 范憶華, 林俊源, “微型PCB鑽頭再研磨機台自動化光學檢測系統之發展,” 先進工程學刊, Vol. 8, No. 4, pp. 259-267, 2013.
    連結：
17. [26] D. Marr, Vision: A Computational Investigation into the Human Representation and Processing of Visual Information, New York: The MIT Press, 2010.
    連結：
18. [27] Y. S. Chen, Y. P. Hung, and C. S. FuhFast “Block Matching Algorithm Based on the Winner-Update Strategy” IEEE TRANSACTIONS ON IMAGE VOL. 10, NO. 8,PROCESSING, 2001
    連結：
19. [28] 王荷凱, 立體視覺應用於多自主行動機器人無線感測網路定位技術之研究, 中原大學機械工程學系碩士論文 2015.
    連結：
20. [3] S. T. Barnard and M. A. Fischler, “Computation stereo,” Computing Surveys, Vol. 14, pp. 553-572, 1982.
21. [4] M. Z. Brown, D. Burschka, and G. D. Hager, “Advances in computational stereo,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 8, pp. 993-1008, 2003.
22. [7] E. Grosso and M. Tistarelli, “Active/dynamic stereo vision,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 9, pp. 868-879, 1995.
23. [11] 陳家泓, 根據極幾何與視差之適應性匹配增強本體移動估測, 國立高雄大學資訊工程學系碩士論文, 2013.
24. [16] A. Geiger, J. Ziegler and C. Stiller, “StereoScan: Dense 3d reconstruction in real-time,” IEEE Intelligent Vehicles Symposium, Baden-Baden, Germany, Jun. 05-09, 2011, pp. 963-968.
25. [17] R. A. Newcombe and A. J. Davison, “Live dense reconstruction with a single moving camera,” IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, Jun. 13-18, 2010, pp. 1498-1505. 
26. [20] S. Martull, M. Peris, and K. Fukui “Realistic CG stereo image dataset with ground truth disparity maps,” The 3rd International Workshop on Benchmark Test Schemes for AR/MR Geometric Registration and Tracking Method (ICPR2012 workshop TrakMark2012), Japan, Nov. 11, 2012, pp. 40-42.
27. [22] 彭啟民,賈雲得,一種基於最小割的稠密視差圖恢復算法,北京理工大學計算機科學與技術系,2005.
28. [24] 章明, 自動化光學檢測. 桃園, 台灣: 台灣電路板協會, 2013.
29. [29] Basler racer, USER’S MANUAL FOR GigE VISION CAMERAS, Basler racer, 2015.
30. [30] 侯捷,” C++PRIMER FOURTH EDITION 中文版”,台灣培生教育出板股份有限公司pp.2-25,2015
31. [31] Basler racer, How to Set Up Several Basler racer Cameras in One Inspection Row Valid only for Basler racer GigE camera models, Basler racer, 2015.
32. [32] 阿洲, “影像平滑(blur、GaussianBlur)”, http://monkeycoding.com/?p=570, 2015.
33. [33] Handspeaker, “semi-global matching 算法總結”, http://www.cnblogs.com/hrlnw/p/4746170.html, 2015.
34. [34] 鄒宇華, “OpenCV學習筆記(18)雙目測距與三維重建的Opecv實現問題集錦(三)立體匹配視差計算”, http://blog.csdn.net/rocky_shared_image/article/details/5967291, 2010,
35. [35] Fukushima, “Point Cloud Rendering”, http://opencv.jp/opencv2-x-samples/point-cloud-rendering, 2011
36. [36] OpenCV, “Camera Calibration and 3D Reconstruction”, http://docs.opencv.org/2.4/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.html, 2013. 
37. [37] OpenCV, “Adding a Trackbar to our applications!,” http://docs.opencv.org/2.4/doc/tutorials/highgui/trackbar/trackbar.html, 2014.
38. [38] 劉瑞禎, 于仕琪, OpenCV教程─基礎篇, 北京航空航天大學出版社, 2007.