|
|
- 2017
利用三视匹配元进行多视影像批处理重建
|
Abstract:
无序多视影像的三维重建对噪声非常敏感，错误的匹配关系会影响重建的精度，甚至直接导致重建失败。提出了一种稳健的批处理重建算法，首先利用回路闭合约束剔除可能存在误匹配的三视匹配元，然后以三视匹配元中的三焦张量约束代替传统算法的核线约束来计算所有影像旋转矩阵和相机中心位置的全局最优解。重建过程中引入高效的并查集算法来提取多视匹配点，并利用迭代线性三角形算法计算空间点的三维坐标。实验结果表明，所提算法在重建效率和计算精度方面都能取得较好的结果
| [1] | ZhengShunyi, Zhang Zuxun, Zhai Ruifang. 3D Reconstruction of Complex Objects Based on Non-metric Image[J]. <em>Geomatics and Information Science of Wuhan University</em>,2008,33(5):446-449(郑顺义, 张祖勋, 翟瑞芳.基于非量测相机的复杂物体三维重建[J]. 武汉大学学报·信息科学版,2008,33(5):446-449) |
| [2] | Lourakis M I A, Argyros A A. Sba:A Software Package for Generic Sparse Bundle Adjustment[J]. <em>ACM Transactions on Mathematical Software</em>, 2009,36(1):1-30 |
| [3] | Strecha C, van Hansen W, van Gool L J, et al. On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery[C].Computer Vision and Pattern Recognition, Alaska, New York, 2008 |
| [4] | Lowe D. Distinctive Image Features from Scale-Invariant Keypoints[J]. <em>International journal of computer vision</em>, 2004, 60(2):91-110 |
| [5] | Nistér D. An Efficient Solution to the Five-Point Relative Pose Problem[J]. <em>IEEE Transactions on Pattern Analysis and Machine Intelligence</em>, 2004, 26(6):756-770 |
| [6] | Wu C. Towards Linear-Time Incremental Structure from Motion[C].3DTV-Conference, Aberdeen, 2013 |
| [7] | Sinha S, Steedly D, Szeliski R. A Multi-stage Linear Approach to Structure from Motion[M]. Berlin:Springer, 2012 |
| [8] | Moulon P, Monasse P, Marlet R. Global Fusion of Relative Motions for Robust, Accurate and Scalable Structure from Motion[C]. IEEE International Conference on Computer Vision, Sydney, 2013 |
| [9] | Galler B A, Fischer M J. An Improved Equivalence Algorithm[J]. <em>Communications of the ACM</em>, 1964, 7(5):301-303 |
| [10] | Hartley R I, Trumpf J, Dai Y, et al. Rotation Averaging[J]. <em>International Journal of Computer Vision</em>, 2013, 103(3):267-305 |
| [11] | Arie-Nachimson M, Kovalsky S Z, Kemelmacher-Shlizerman I, et al. Global Motion Estimation from Point Matches[C]. 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), Zurich, 2012 |
| [12] | Hartley R I, Zisserman A. Multiple View Geometry in Computer Vision[M]. New York:Cambridge University Press, 2003 |
| [13] | Jiang Nianjuan, Cui Zhaopeng, Tan Ping. A Global Linear Method for Camera Pose Registration[C]. IEEE International Conference on Computer Vision, Sydney, 2013 |
| [14] | Snavely, Seitz S M, Szeliski R. Modeling The World from Internet Photo Collections[J]. <em>International Journal of Computer Vision</em>, 2008, 80(2):189-210 |
| [15] | Kahl F, Hartley R I. Multiple-view Geometry under the l∞-norm[J]. <em>IEEE Transactions on Pattern Analysis and Machine Intelligence,</em>2008, 30(9):1603-1617 |
| [16] | Hartley R I, Sturm P. Triangulation[J]. <em>Computer Vision and Image Understanding</em>, 1997,68(2):146-157 |
| [17] | Fasano P, Forrest J. The COIN-OR Open Solver Interface:Technology Overview[EB/OL].https://projects.coin-or.org/Osi,2014 |
| [18] | Martinec D, Pajdla T. Robust Rotation and Translation Estimation in Multiview Reconstruction[C]. Computer Vision and Pattern Recognition, Minnesota, New York, 2007 |
| [19] | Guo Fusheng, Gao Wei. Batch Reconstruction from UAV Images with Prior Information[J]. <em>Acta Automatica Sinica</em>, 2013, 39(6):834-845(郭复胜, 高伟. 基于辅助信息的无人机图像批处理三维重建方法[J]. 自动化学报, 2013, 39(6):834-845) |
