No Access

Analysis of wavelet basis selection in optimal trajectory space finding for 3D non-rigid structure from motion

Yaming Wang

School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, P. R. China

Search for more papers by this author

Jianmin Cheng

School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, P. R. China

Search for more papers by this author

Junbao Zheng

School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, P. R. China

Corresponding author.

Search for more papers by this author

Yingli Xiong

School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, P. R. China

Search for more papers by this author

, and

Huaxiong Zhang

School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, P. R. China

Search for more papers by this author

https://doi.org/10.1142/S0219691314500234Cited by:3 (Source: Crossref)

Abstract

Trajectory representation model has been proposed to describe non-rigid deformation. An optimal trajectory space finding algorithm for 3D non-rigid structure from motion (OTSF-NRSFM) based on this model also has been proposed. However, the influence of the wavelet basis selection on the OTSF-NRSFM algorithm has still not been studied. To help OTSF-NRSFM researchers select wavelet basis properly, we investigated the influences of wavelet basis selection. Two typical wavelet bases, DCT basis and WHT basis, are discussed in this paper. The spectrum properties of wavelet basis and feature point trajectory, trajectory representation results on synthetic shark data, OTSF-NRSFM reconstruction results on synthetic data and real data are analyzed. The results show that the wavelet selection has much influence on OTSF-NRSFM reconstruction results of some non-rigid feature points, which have complicated trajectory. This paper gives researchers some inspiration about wavelet basis selection in OTSF-NRSFM algorithm.

Keywords:

AMSC: 22E46, 53C35, 57S20

References

I. Akhter, Y. Sheikh and S. Khan, In defense of orthonormality constraints for nonrigid structure from motion, Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR' 09) (IEEE, 2009) pp. 1534–1541. Google Scholar
I. Akhteret al., Nonrigid structure from motion in trajectory space, 22nd Annual Conf. on Neural Information Processing Systems (NIPS' 08) (Curran Associates Inc., USA, 2008) pp. 42–48. Google Scholar
I. Akhteret al., IEEE Trans. Pattern Anal. Mach. Intell. 33(7), 1442 (2011), DOI: 10.1109/TPAMI.2010.201. Crossref, Web of Science, Google Scholar
C. Bregler, A. Hertzmann and H. Biermann, Recovering non-rigid 3D shape from image streams, Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR' 2000) (IEEE, 2000) pp. 690–696. Google Scholar
M. Burenius, J. Sullivan and S. Carlsson, Motion capture from dynamic orthographic cameras, 1st IEEE Workshop on Dynamic Shape Capture and Analysis (IEEE, 2011) pp. 1634–1641. Google Scholar
F. Daiet al., Comparison of image-based and time-of-flight-based technologies for 3D reconstruction infrastructure, Proc. Construction Research Congress (ASCE, 2012) pp. 929–939. Google Scholar
A. Del Bue, F. Smeraldi and L. Agapito, Image Vis. Comput. 25(3), 297 (2007), DOI: 10.1016/j.imavis.2005.10.004. Crossref, Web of Science, Google Scholar
J. Johnson and M. Puschel, In search of the optimal Walsh–Hadamard transform, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (IEEE, 2000) pp. 3347–3350. Google Scholar
O. Khatib, IEEE J. Robot. Autom. RA 3(1), 43 (1987), DOI: 10.1109/JRA.1987.1087068. Crossref, Web of Science, Google Scholar
S. A. Khayam , The Discrete Cosine Transform (DCT): Theory and Application, ECE 802-602: Information Theory and Coding ( Michigan University , 2003 ) . Google Scholar
T. Kim, S. Lee and J. Paik, IET Image Process. 5(1), 87 (2011), DOI: 10.1049/iet-ipr.2009.0276. Crossref, Web of Science, Google Scholar
H. C. Longuet-Higgins, Nature 293(10), 133 (1981), DOI: 10.1038/293133a0. Crossref, Web of Science, Google Scholar
M. Paladini, A. Bartoli and L. Agapito, Sequential non-rigid structure-from-motion with the 3d-implicit low-rank shape model, European Conf. on Computer Vision (ECCV, 2010) (Springer-Verlag, 2010) pp. 15–28. Google Scholar
M. Paladiniet al., Factorization for non-rigid and articulated structure using metric projections, Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR, 2009) (IEEE, 2009) pp. 2898–2905. Google Scholar
H. Parket al., 3D surface reconstruction of terrestrial laser scanner data for forestry, Proc. IEEE Int. Ceoscience and Remote Sensing Symposium (IGARSS' 2010) (IEEE, 2010) pp. 4366–4369. Google Scholar
H. S. Parket al., 3D reconstruction of a moving point from a series of 2D projections, European Conf. on Computer Vision (ECCV, 2010) (2010) pp. 158–171. Google Scholar
K. R. Rao and P. Yip , Discrete Cosine Transform: Algorithms, Advantages, Applications ( Academic Press , Boston , 1990 ) . Crossref, Google Scholar
G. Strang, SIAM Rev. 41(1), 135 (1999), DOI: 10.1137/S0036144598336745. Crossref, Web of Science, Google Scholar
Y. Y. Tang and X. G. You, IEEE Trans. Pattern Anal. Mach. Intell. 25(9), 1118 (2003). Crossref, Web of Science, Google Scholar
C. Tomasi and T. Kanade, Int. J. Comput. Vis. 9(2), 137 (1992), DOI: 10.1007/BF00129684. Crossref, Web of Science, Google Scholar
L. Torresani , A. Hertzmann and C. Bregler , Learning non-rigid 3D shape from 2D motion , 17th Annual Conf. on Neural Information Processing Systems (NIPS' 03) ( Curran Associates Inc. , USA , 2003 ) . Google Scholar
O. Trabocchi and C. Gomez-Reino, J. Opt. Soc. Am. A, Opt. Image Sci. Vis. 21(3), 388 (2004), DOI: 10.1364/JOSAA.21.000388. Crossref, Web of Science, Google Scholar
J. Valmadre and S. Lucey, Deterministic 3d human pose estimation using rigid structure, European Conf. on Computer Vision (ECCV, 2010) (2010) pp. 467–480. Google Scholar
M. Venkadesan and F. J. Valero-Cuevas, J. Neurosci. 28(6), 1366 (2008), DOI: 10.1523/JNEUROSCI.4993-07.2008. Crossref, Web of Science, Google Scholar
J. Xiao, J. Chai and T. Kanade, Int. J. Comput. Vis. 67(2), 233 (2006), DOI: 10.1007/s11263-005-3962-9. Crossref, Web of Science, Google Scholar
R. Q. Yan and R. X. Gao, Int. J. avelets, Multiresolut. Inf. Process. 7(4), 411 (2009), DOI: 10.1142/S0219691309002994. Link, Web of Science, Google Scholar
X. G. You and Y. Y. Tang, IEEE Trans. Image Process. 16(5), 1220 (2007), DOI: 10.1109/TIP.2007.891800. Crossref, Web of Science, Google Scholar
X. H. Yu, The relationship between wavelet bases and image compression, Proc. 3rd Int. Conf. Wavelet Analysis and Its Applications (2003) pp. 53–60. Google Scholar
Y. Y. Zhu, M. Cox and S. Lucey, 3D motion reconstruction for real-world camera motion, Proc. IEEE Comput. Soc. Conf. Computer Vision and Pattern Recognition (CVPR' 2011) (IEEE, 2011) pp. 1–8. Google Scholar