Recovery of 3D Non-Rigid Structure from Images Based on Trajectories

Abstract:

In this paper, we address the problem of recovering the 3D structure of a non-rigid object based on trajectories throughout an image sequence. We formulate the 3D non-rigid shape as a linear combination of basis trajectories and compute the rectification matrix using generic algorithm with orthogonal constrains. In order to improve the reconstruction ability, trajectory filters are introduced to eliminate the need for choosing basis size. Experimental results from a human motion image sequences show that the proposed approach is more efficient for recovery of 3D non-rigid structure. Furthermore, the adjustment of basis size is avoided through the success use of trajectory filters.

• Periodical: Applied Mechanics and Materials (Volumes 651-653)
• Pages: 2081-2085
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.651-653.2081
• Online since: September 2014
• Authors: Ya Ming Wang*, Z. Zhang, Jun Bao Zheng, L.L. Tong
• Keywords: Genetic Algorithm (GA), Non-Rigid Structure from Motion, Trajectory Filters

References

[1] C. Tomasi and T. Kanade. Shape and motion from image streams under orthography: A factorization method. International Journal of Computer Vision, Vol. 9(2) (1992) pp.137-154.

DOI: 10.1007/bf00129684

[2] C. Bregler, A. Hertzmann and H. Biermann. Recovering non-rigid 3D shape from image streams. IEEE Conference on Computer Vision and Pattern Recognition (CVPR2000), Vol. 2 (2000), pp.690-696.

DOI: 10.1109/cvpr.2000.854941

[3] I. Akhter, Y. Sheikh, S. Khan and T. Kanade. Nonrigid structure from motion in trajectory space. In Advances in neural information processing systems(NIPS), (2008), pp.41-48.

[4] J. Valmadre, S. Lucey. General Trajectory Prior for Non-Rigid Reconstruction. IEEE Conference on Computer Vision and Pattern Recognition (CVPR2012), (2012), pp.1394-1401.

DOI: 10.1109/cvpr.2012.6247826

[5] F. Xiang, L. Junzhou, W. Jieyi, G. Guanqun. QoS routing based on genetic algorithm. Computer Communications. Vol. 22(15-16) (1999), pp.1392-1399.

DOI: 10.1016/s0140-3664(99)00113-9

[6] Y. Yun, C. Moon and D. Kim. Hybrid genetic algorithm with adaptive local search scheme for solving multistage-based supply chain problems. Computers & Industrial Engineering, Vol. 56(3), (2009), pp.821-838.

DOI: 10.1016/j.cie.2008.09.016

[7] H. S. Park, T. Shiratori, et al. 3D Reconstruction of a Moving Point from a Series of 2D Projections. Computer Vision–ECCV. Springer Berlin Heidelberg, Vol. 6313, (2010), pp.158-171.

DOI: 10.1007/978-3-642-15558-1_12

[8] S. A. Martucci. Symmetric convolution and the discrete sine and cosine transforms. IEEE Transactions on Signal Processing, Vol. 42(5) (1994), pp.1038-1051.

DOI: 10.1109/78.295213

[9] Information on http: /mocap. cs. cmu. edu.