A 3D Reconstruction Framework from Image Sequences Based on Point and Line Features

Abstract:

A novel three dimensional reconstruction framework from wide baseline images was proposed based on point and line features. After detecting and matching features, the relations between discrete images are computed and refined according to multi-view geometric constraints, and both structure of the scene and motion of cameras are retrieved, where we employ a procedure of Euclidean reconstruction based on approximate camera internal parameters and buddle adjustments. Based on retrieved motion and correspondence of line features, a 3D line reconstruction scheme was put forward to assist us in gaining regular structure and topology of the scene. In virtue of some manual interactions, mesh models of the scene came into being, and a rectification method for perspective images was used to acquiring texture patches. Finally, an interactive modeling prototype system from multiple images is designed and implemented. Real scenes and augmented reality applications demonstrate the feasibility, correctness and accuracy of our framework.

• Periodical: Advanced Materials Research (Volumes 317-319)
• Pages: 962-967
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.317-319.962
• Online since: August 2011
• Authors: Bao Song Deng, Rong Huan Yu, Tie Qing Deng, Ling Da Wu
• Keywords: 3D Reconstruction, Augmented Reality (AR), Feature Point Matching, Line Reconstruction, Structure from Motion, Wide Baseline Images

References

[1] S. M. Seitz, B. Curless, J. Diebel, D. Scharstein, R. Szeliski: A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms. In Proceedings of International Conference on Computer Vision and Pattern Recognition, New York, June 18-20, 2006.

DOI: 10.1109/cvpr.2006.19

[2] M. Pollefeys, L. V. Gool, M. Vergauwen, F. Verbiest. Visual Modeling with a Hand-held Camera. International Journal of Computer Vision, 2004, Vol. 59, No. 3, pp.207-232.

DOI: 10.1023/b:visi.0000025798.50602.3a

[3] P. J. Narayanan, P. Rander, T. Kanade. Constructing Virtual Worlds using Dense Stereo. In Proceedings of International Conference on Computer Vision, 1998, pp.3-10.

DOI: 10.1109/iccv.1998.710694

[4] P. E. Debevec. Modeling and Rendering Architecture from Photographs. Ph.D.thesis, Computer Science Department, University of Michigan at Ann Arbor, 1996.

[5] S. N. Sinha, D. Steedly, R. Szeliski, M. Agrawala. Interactive 3D Architectural Modeling from Unordered Photo Collections. ACM Transactions on Graphics 27, 5, 159:1-159:10.

DOI: 10.1145/1409060.1409112

[6] B. Deng, Y. Gao, Y. Wei, L. Wu. Accurate Feature Point Matching for Off-line 3D Reconstruction and Augmented Reality Applications. Journal of Computational Information Systems, Vol. 2, No. 2, 2006.

[7] B. Deng, Y. Gao, Y. Wei, L. Wu. Accurate Wide Baseline Matching with Large Geometric and Illumination Deformations. Journal of Computational Information Systems, Vol. 2, No. 3, 2006.

[8] L. Wu, B. Deng, Y. Gao, Y. Wei. Accurate 3D Euclidean Reconstruction Based on Approximate Camera Internal Parameters. Journal of System Simulation, Vol.19, No.10, 2007 (In Chinese).

[9] A. W. K. Tang, T. P. Ng, Y. S. Hung. Projective Reconstruction from Line-Correspondences in Multiple Uncalibrated Images. Pattern Recognition, 2006, Vol. 39, No. 1, pp.889-896.

DOI: 10.1016/j.patcog.2005.10.019

[10] B. Deng, B. Yang, Y. Wei, L. Wu. 3D Reconstruction of Line Features Based on Multi-view Images. Journal of Computer-Aided Design & Computer Graphics, Vol.19, No.6, 2007.

[11] S. H. Park, K. M. Lee, S. U. Lee. A Line Feature Matching Technique based on an Eigenvector Approach. Computer Vision and Image Understanding, 2000, Vol. 77, No. 3, pp.263-283.

DOI: 10.1006/cviu.2000.0808

[12] X. Lu, R. Manduchi. Wide Baseline Feature Matching Using the Cross-epipolar Ordering Constraint. In Proceedings of International Conference on Computer Vision and Pattern Recognition, 2004, pp.16-23.

DOI: 10.1109/cvpr.2004.1315008