在這篇論文中，我們提出了一個整合Kinect對轉盤上物體所拍得多視角RGBD影像來重建三維物體的系統，主要的問題在解決三維RGBD影像對位的問題，此論文的目的在從多張粗糙的深度圖建立出比較精細的3D 模型。此論文提出的三維重建系統主要包含下面幾個步驟：第一步驟為將我們所拍攝取得的彩色影像及深度資訊去進行物體分割，主要是利用簡單的深度資訊及空間上的資訊取得結果並取得其物體在不同的拍攝角度下的3D點雲；接者利用兩兩相鄰的影像利用SURF去計算出特徵點的對應，並且利用RANSAC 的方法對兩張相鄰的RGBD影像進行 Affine轉換的估測，進而將一些錯誤的特徵點對應刪除；然後將所有兩兩相鄰的特徵點對應去決定出從相機坐標系到世界座標系的幾何轉換關係。當中可能會有旋轉角度上的累積錯誤及一些環境變數，因此我們提出了兩步驟的最佳化程序以利用LM演算法已獲得較精細的模型。我們最後更提出了一個新的演算法結合Mean Shift去降低在重疊區的3D點雲的密度。在實驗結果中，我們應用本論文所提出的方法到真實拍攝的影像及模擬資料去重建三維物體模型，並獲得不錯的三維重建結果。

In this thesis, we present a 3D reconstruction system that integrates multi-view RGBD images acquired with Kinect for an object sitting on a turntable. In the proposed system, we first segment the object from images by using a simple background model with depth and produce the 3D point cloud from the RGBD image in a single view. Next, we compute feature correspondences between each pair of successive frames by SURF, and remove the false feature correspondences by applying RANSAC affine matching for each pair of adjacent views. Then, we use all the verified 3D feature correspondences to determine the geometric transformation that transforms the 3D coordinates from the corresponding camera coordinates to a unified world coordinate centered at the turntable. Because of the cumulative error of rotation angles and other environmental variables, we propose a two-step refinement process by using the LM Optimization. Finally, we propose a novel point set simplification algorithm to simplify the integrated point dataset that reduces the density of 3D points in the overlapped regions. Experimental results are given to demonstrate superior 3D reconstruction results by using the proposed method on both real data and simulation data.

[1] “Microsoft Kinect,” http://www.xbox.com/kinect.
[2] “ASUS Xtion,” http://tw.asus.com/Multimedia/Motion_Sensor/Xtion_PRO/.
[3] L. Cruz, D. Lucio, and L. Velho, “Kinect and rgbd images: challenges and applications,” SIBGRAPI Tutorial, 2012.
[4] A. Weiss, D. Hirshberg, and M. Black. “Home 3d body scans from noisy image and range data,” In Proc. IEEE International Conference on Computer Vision, pp. 1951–1958, 2011.
[5] J. Tong, J. Zhou, L. Liu, Z. Pan, and H. Yan. “Scanning 3d full human bodies using kinects,” IEEE Trans. Vis. Comput. Graph., 18(4):643–650, 2012
[6] M. Zollhöfer, M. Martinek, G. Greiner, M. Stamminger, and J. Süaßmuth, “Automatic reconstruction of personalized avatars from 3D face scans,” Comput. Animat. Virtual Worlds, Vol. 22, pp. 195–202, 2011.
[7] J. Hernandez, J. Choi, and G. Medioni. “Laser scan quality 3d face modeling using a low-cost depth camera,” In EUSIPCO, 2012.
[8] S. Izadi, D. Kim, O. Hilliges, D. Molyneaux, R. Newcombe, P. Kohli, J. Shotton, S. Hodges, D. Freeman, A. Davison, and A. Fitzgibbon.” Kinectfusion: real-time 3d reconstruction and interaction using a moving depth camera,” In Proc. of ACM UIST, 2011.
[9] N. Silberman and R. Fergus, “Indoor scene segmentation using a structured light sensor,” ICCV Workshop on 3D Representation and Recognition, 2011.
[10] K. Lai, L. Bo, X. Ren, and D. Fox. “Sparse distance learning for object recognition combining RGB and depth information,” In IEEE International Conference on Robotics and Automation, 2011.
[11] P. Henry, M. Krainin, E. Herbst, X. Ren, and D Fox. “Rgb-d mapping : Using depth cameras for dense 3d modeling of indoor environments,” In International Symposium on Experimental Robotics (ISER), 2010.
[12] M. Pollefeys, “Self-calibration and metric reconstruction inspite of varying and unknown intrinsic camera parameters,” International Journal of Computer Vision, Vol.32(1), pp. 7-25, 1999.
[13] G. Jiang, L. Quan, and H.T. Tsui, “Circular motion geometry using minimal data,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.26, pp. 721-731, 2004.
[14] G. Jiang, H.T. Tsui, L. Quan, and A. Zisserman, “Geometry of Single Axis Motions Using Conic Fitting,” IEEE Trans. Pattern Analysis Machine Intelligence, 25(10):1343-1348, 2003.
[15] H. Zhang, G. Zhang, and K.-Y.K. Wong, “Auto-calibration and motion recovery from silhouettes for turntable sequences,” In Proc. British Machine Vision Conf., pp.79-88, 2005.
[16] P.-H. Huang and S.-H. Lai, “Camera calibration from silhouette under incomplete circular motion with a constant interval angle,” In Proc. Asian Conference Computer Vision, Vol.1, pp. 106-115, 2007.
[17] C. Hernandez, F. Schmitt, and R. Cipolla, “Silhouette coherence for camera calibration under circular motion,” IEEE Trans. Pattern Analysis Machine Intelligence, Vol.29(2), pp. 343-349, 2007.
[18] H. Zhong and Y. S. Hung, “Multi-stage 3D reconstruction under circular motion,” Image and Vision Computing, 25(11): 1814-1823, 2007.
[19] “OpenNI,” http://www.openni.org.
[20] “PrimeSense Sensor Module,” http://www.primesense.com/.
[21] C. Harris and M. Stephens, “A combined corner and edge detector,” In Proceedings of the Alvey Vision Conference, pp. 147 – 151, 1988.
[22] D. Lowe, ”Distinctive image features from scale-invariant keypoints, cascade filtering approach,” International Journal of Computer Vision, Vol. 60, pp. 91 – 110, 2004.
[23] H. Bay, T. Tuytelaars, and L. V. Gool, “Surf: speeded up robust features, “In European Conference on Computer Vision (ECCV), pages 404–417, 2006
[24] D. Lowe, “Object recognition from local scale-invariant features,” International Conference on Computer Vision, 1999.
[25] “OpenSURF,” http://www.chrisevansdev.com/computer-vision-opensurf.html.
[26] M.A. Fischler and R.C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, 24(6):381–395, 1981
[27] “OpenGL,” http://www.opengl.org/.
[28] R.Fletcher, “A modified marquardt subroutine for nonlinear least squares,” Rpt. AERE-R 6799,Harwell, 1971.
[29] Y. Cheng, “Mean shift, mode seeking, and clustering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17 (8), pp. 790–799, 1995.
[30]”DAVID 3D SCANNER,” http://www.david-laserscanner.com/.
[31] P.-H. Huang, C.-M. Cheng, H.-L. Yang, S.-H. Lai, and S.-Y. Yang, “On-line 3D Modeling System Using a General Webcam and a Turntable” In CVGIP, 2009.
[32] W. Matusik, C. Buehler, R. Raskar, S. Gortler, AND L. Mcmillan, “Image-based visual hulls” In Proceedings of ACM SIGGRAPH, pp. 369–374, 2000.
[33] M. Kazhdan, M. Bolitho, and H. Hoppe, “Poisson surface reconstruction”, in Symposium on Geometry Processing, pp.61-70, Sardinia, Italy, 2006.
[34] “MeshLab,” http://meshlab.sourceforge.net/.
[35] Paul J.; N.D. McKay Besl, “A method for registration of 3-d shapes,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239–256, 1992.