浏览全部资源
扫码关注微信
收稿：2019-03-12，
修回：2019-6-5，
录用：2019-6-12，
纸质出版：2019-11-16
移动端阅览
目的
2
传统增量式运动结构恢复算法中，初始图像对选择鲁棒性差，增量求解过程效率较低，捆绑调整策略存在计算冗余，模型修正后仍存在较大误差。为解决上述问题，以基于图像序列的3维重建为基础，提出一种新的增量式运动结构恢复算法（SFM-Y）。
方法
2
首先，采用改进的自适应异常值过滤方法增强初始图像对选择的鲁棒性，得到用于初始重建的初始图像对；其次，通过增量迭代重建丰富点云模型，采用改进的EPNP（efficient perspective-
$$n$$
-point）解算方法提高增量添加过程的计算效率和精确度；最后，采用优化的捆绑调整策略进行模型修正，解决模型漂移问题，修正重投影误差。
结果
2
实验选取不同数据规模的数据集，在本文方法及传统方法间进行测试对比，以便更加全面地分析算法性能。实验结果表明，SFM-Y算法相比传统的增量式运动结构恢复算法，在计算效率和结果质量方面均有所提高，根据性能分析对比的结果所示，本文方法较传统方法在计算效率和重建精度上约有10%的提升。
结论
2
提出的增量式运动结构恢复算法能够高效准确地实现基于图像序列的3维重建优于传统方法，计算效率较高，初始重建鲁棒性强，生成模型质量较好。
Objective
2
With the fast development of virtual reality technology
determining how to establish virtual scenes rapidly and realistically becomes a bottleneck that restricts the popularization and promotion of virtual reality technology. As an important technical means to solve this problem
3D reconstruction technology has been applied in many fields
such as ancient building protection and restoration
medical treatment
and tourism. Such technology has been developing continuously in recent years
and its application scenarios have been extended greatly. The scale of data to be processed has also increased substantially
and the accuracy requirements for reconstruction results have continuously increased. In these cases
many problems existing in the traditional methods are exposed. For instance
problems such as poor robustness of initial image pair selection process
inefficient incremental solving process
redundant calculation of bundle adjustment
and errors that remain after model correction are found in the traditional incremental structure from motion algorithm. Accordingly
this study proposes a new incremental structure from motion algorithm (named SFM-Y) based on the foundation called image sequence-based 3D reconstruction.
Method
2
First
an improved adaptive outlier-filtering method is proposed to enhance the robustness of the initial image selection in this study. Next
an adaptive threshold estimation model is introduced into our algorithm
and constraints and filter conditions are added to improve the robustness of initial image selection and initial reconstruction to resolve the robustness problem caused by the threshold
which is set manually
used in the RANSAC (random sample consensus) filter process. The constraints include four-point method inspection
wide baseline constraint
and revised five-point outlier culling method. In this way
the initial image pair that is used to perform initial reconstruction is selected with strong robustness. Second
the proposed method processes incremental iterative reconstruction to enrich the point cloud model. In this process
the improved efficient perspective-$n$-point solution method is proposed to improve the computational efficiency and accuracy of the incremental addition process. The solution method combines the idea of weighted refinement and the method of how to reduce a linear system’s algebraic error. We try to give this method a rigorous derivation process to prove that it is an efficient solution to the question of how to accelerate the incremental solution process of the incremental structure from motion algorithm. Finally
an optimized bundling adjustment strategy is used to modify the model
solve the model drift
and revise the re-projection error. In this stage
the integration of graphics is checked by introducing a minimum triangulation angle and performing re-triangulation on the tracks among different projection points. Then
once or twice iterative optimization (including global bundle adjustment
filtering
and re-triangulation process) is executed to ameliorate the result of our algorithm. All the methods mentioned above that we performed or revised work together to complete a common goal
reducing solution time and improving reconstruction quality.
Result
2
Among all the experiments mentioned in this paper
we select data sets in different data scales first. A comparison and test are then performed among the methods involved in this study to comprehensively and objectively analyze the algorithm performance and acquire a convincing result. Experimental results show that the SFM-Y algorithm improves the computational efficiency and quality of results compared with the traditional incremental motion structure recovery algorithm. The performance analysis and comparison results indicate that the proposed method is more efficient than the traditional method. The reconstruction accuracy yields 10% improvement compared with that of the traditional algorithm referred to in this study.
Conclusion
2
After a series of analyses
arguments
and experiments
the following conclusions are drawn. Experiments in many databases show that the new incremental motion structure restoration algorithm (SFM-Y) proposed in this study can efficiently and accurately achieve the goal of 3D reconstruction based on image sequences. This algorithm provides a new way of thinking in the field of incremental structure from motion algorithm
which certainly has a positive promoting effect on the development of 3D reconstruction research and has great meaning for the following research and exploration. The proposed algorithm is better than traditional methods and has the advantages of high computational efficiency
strong initial reconstruction robustness
and high quality of the generated model.
Zhao Q P. Over view of virtual reality[J]. Science in China:Information Science, 2009, 39(1):2-46.
赵沁平.虚拟现实综述[J].中国科学F辑:信息科学, 2009, 39(1):2-46. [DOI:10.1360/zf2009-39-1-2]
Forsyth D A, Ponce J. Computer Vision O: amodern Approach[M]. Beijing: Electronic Industry Press, 2012: 110.Forsyth D A, Ponce J.
计算机视觉——一种现代方法[M].北京: 电子工业出版社, 2012: 110.
Lyu L, Yao T Z, Song J T, et al. Design andimplementation of 3D reconstruction systembased on monocular vision[J]. Computer Engineering, 2018, 44(12):233-239.
吕立, 姚拓中, 宋加涛, 等.基于单目视觉三维重建系统的设计与实现[J].计算机工程, 2018, 44(12):233-239. [DOI:10.19678/j.issn.1000-3428.0047936]
Moulon P, Monasse P, Marlet R. Global fusion of relative motions for robust, accurateand scalable structure from motion[C]//Proceedings of 2013 IEEE International Conference on Computer Vision. Sydney, Australia: IEEE, 2013: 3248-3255.[ DOI: 10.1109/ICCV.2013.403 http://dx.doi.org/10.1109/ICCV.2013.403 ]
Skilling J, Gull S F. Algorithms and Applications[M]//Smith C R, Grandy W T. Maximum Entropy and Bayesian Methods in Inverse Problems. Dordrecht: Reidel Publishing Company, 1985: 83-132.
Yao T Z, Zuo W H, An P, et al. Wide-baseline 3D reconstruction with semantic prior fusion and progressive depth optimization[J]. Journal of Image and Graphics, 2019, 24(4):603-614.
姚拓中, 左文辉, 安鹏, 等.融合语义先验和渐进式深度优化的宽基线3维场景重建[J].中国图象图形学报, 2019, 24(4):603-614. [DOI:10.11834/jig.180477]
Anand A, Koppula H S, Joachims T, et al. Contextually guided semantic labeling and search for three-dimensional point clouds[J]. The International Journal of Robotics Research, 2013, 32(1):19-34.[DOI:10.1177/0278364912461538]
Tong S, Xu X G, Yi C T, et al. Overview on vision-based 3D reconstruction[J]. Application Research of Computers, 2011, 28(7):2411-2417.
佟帅, 徐晓刚, 易成涛, 等.基于视觉的三维重建技术综述[J].计算机应用研究, 2011, 28(7):2411-2417. [DOI:10.3969/j.issn.1001-3695.2011.07.003]
Snavely N, Seitz S M, Szeliski R. Photo tourism:exploring photo collections in 3D[J].ACM Transactions on Graphics,2006, 25(3):835-846.[DOI:10.1145/1141911.1141964]
Snavely N, Seitz S M, Szeliski R. Modeling the world from internet photo collections[J]. International Journal of Computer Vision, 2008, 80(2):189-210.[DOI:10.1007/s11263-007-0107-3]
Shah R, Deshpande A, Narayanan P J. Multistage SFM: revisiting incremental structure from motion[C]//Proceedings of the 2nd International Conference on 3D Vision. Tokyo, Japan: IEEE, 2014, 1: 417-424.[ DOI: 10.1109/3DV.2014.95 http://dx.doi.org/10.1109/3DV.2014.95 ]
Schönberger J L, Frahm J M. Structure-from-motion revisited[C]//Proceedings of 2016 IEEE Computer Vision and Pattern Recognition.Las Vegas, NV, USA: IEEE, 2016: 4104-4113.[ DOI: 10.1109/CVPR.2016.445 http://dx.doi.org/10.1109/CVPR.2016.445 ]
Farenzena M,Fusiello A, Gherardi R. Structure-and-motion pipeline on a hierarchical cluster tree[C]//Proceedings of the 12th International Conference on Computer Vision Workshops.Kyoto, Japan: IEEE, 2009: 1489-1496.[ DOI: 10.1109/ICCVW.2009.5457435 http://dx.doi.org/10.1109/ICCVW.2009.5457435 ]
Agudo A, Moreno-Noguer F, Calvo B, et al.Sequential non-rigid structure from motion using physical priors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(5):979-994.[DOI:10.1109/TPAMI.2015.2469293]
Cui H N, Shen S H, Hu Z Y. Global fusionof generalized camera model for efficient large-scale structure from motion[J]. Science China Information Sciences, 2017, 60(3):038101.[DOI:10.1007/s11432-015-0792-1]
Lee M, Cho J, Choi C H, et al. Procrustean normal distribution for non-rigid structure from motion[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland: IEEE, 2013: 1280-1287.[ DOI: 10.1109/CVPR.2013.169 http://dx.doi.org/10.1109/CVPR.2013.169 ]
Ludovic M, Del Bue A. Revisiting projective structure for motion:a robust and efficient incremental solution[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018.[DOI:10.1109/TPAMI.2018.2849973]
Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.[DOI:10.1023/b:visi.0000029664.99615.94]
Jia D, Zhu N D, Yang N H, et al. Image matching methods[J]. Journal of Image and Graphics, 2019, 24(5):677-699.
贾迪, 朱宁丹, 杨宁华, 等.图像匹配方法研究综述[J].中国图象图形学报, 2019, 24(5):677-699. [DOI:10.11834/jig.180501]
Wu C C. Towards linear-time incremental structure from motion[C]//Proceedings of 2013 International Conference on 3DV-Conference. Seattle, WA, USA: IEEE, 2013: 127-134[[ DOI: 10.1109/3DV.2013.25 http://dx.doi.org/10.1109/3DV.2013.25 ]
Hartley R, Eisserman A. Multiple View Geometry in Computer Vision[M]. USA:Cambridge University Press, 2003.
Lepetit V, Moreno-Noguer F, Fua P. EPnP:an accurate O(n) solution to the PnP problem[J]. International Journal of Computer Vision, 2009, 81(2):155-166.[DOI:10.1007/s11263-008-0152-6]
Moulon P, Monasse P, Marlet R. Adaptive structure from motion with a contrario model estimation[C]//Proceedings of Asian Conference on Computer Vision. Daejeon, Korea: Springer, 2012: 257-270.[ DOI: 10.1007/978-3-642-37447-0_20 http://dx.doi.org/10.1007/978-3-642-37447-0_20 ]
Zhang F, Xu Z H, Shi L M, et al. Automatic reconstruction of distant scenes from wide baseline images[J]. Journal of Computer-Aided Design&Computer Graphics, 2010, 22(2):256-263.
张峰, 许振辉, 史利民, 等.基于宽基线图像远距离场景的自动三维重建[J].计算机辅助设计与图形学学报, 2010, 22(2):256-263.
Yang S, Wu F C. Weighted linear methods for the camera pose estimation[J]. Journal of Software, 2011, 22(10):2476-2487.
杨森, 吴福朝.摄像机位姿的加权线性算法[J].软件学报, 2011, 22(10):2476-2487. [DOI:10.3724/SP.J.1001.2011.03916]
Ferraz L, Binefa X, Moreno-Noguer F. Very fast solution to the PnP problem with algebraic outlier rejection[C]//Proceedings of 2014 Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA: IEEE, 2014: 501-508.[ DOI: 10.1109/CVPR.2014.71 http://dx.doi.org/10.1109/CVPR.2014.71 ]
Cui H N, Gao X, Shen S H, et al. HSfM: hybrid structure-from-motion[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 1212-1221.[ DOI: 10.1109/CVPR.2017.257 http://dx.doi.org/10.1109/CVPR.2017.257 ]
Wilson K, Snavely N. Robust global translations with 1DSfM[C]//European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014: 61-75.[ DOI: 10.1007/978-3-319-10578-9_5 http://dx.doi.org/10.1007/978-3-319-10578-9_5 ]
相关作者
相关机构
京公网安备11010802024621
