3D Motion Parameters Estimation Using MRF and Neural Network

Wen Qing Huang; Wen Jie Li; Hai Yan Hu; Ya Ming Wang; Ming Feng Jiang

doi:10.4028/www.scientific.net/AMR.490-495.1605

Paper Titles

The Study of the SVPWM Realization Method Based on DSPIC30F6010A
p.1584

Tool Wear Prediction Based on Fuzzy Cluster Analysis
p.1589

Research on Thermal Characteristic and Thermal Compensation Technology of Spindle System of CNC Machine Tool
p.1595

Research on Goniometer Fault Detection of a Certain Missile Based on Wavelet Analysis
p.1600

3D Motion Parameters Estimation Using MRF and Neural Network
p.1605

The Grey Relational Analysis of Driving Forces for Water Consumed Structure
p.1612

Research and Application of Reverse System Based on Bluetooth Technology
p.1617

Study on the Application of Segmentation Algorithm Based on Medical Image Fusion
p.1622

The Statistic Definition and Research of the One Class Similar Special Curve
p.1627

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 490-4953D Motion Parameters Estimation Using MRF and...

3D Motion Parameters Estimation Using MRF and Neural Network

Abstract:

In this paper we use the method of MRF and neural network to solve the problem of parameters estimation in non-rigid 3D movement. Firstly, the method of MRF is used for modeling the local motion correlation of each feature point, and the 3D coordinates of each feature point are obtained. Then the method of neural network is used for clustering the feature points according to their motion situation. When the neural network reaches stabilization, we can get the motion parameters of each feature point. Finally, we correct the neighborhoods of each feature point according to motion parameters. The experimental results show that our algorithm can correctly estimate the non-rigid motion parameters.

You might also be interested in these eBooks

Mechatronics and Intelligent Materials II

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 490-495)

Pages:

1605-1611

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.490-495.1605

Citation:

Cite this paper

Online since:

March 2012

Authors:

Wen Qing Huang, Wen Jie Li, Hai Yan Hu, Ya Ming Wang, Ming Feng Jiang

Keywords:

3D Movement, MRF, Neural Network (NN), Parameters Estimation

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] WANG Ya-ming, HUANG Wen-qing, LI Wei, WANG Yuan-mei. Local 3D Non-Rigid Motion Estimation from Monocular Image Sequence Based on Regularization [J], Journal of Circuits and Systems, Vol. 9, No. 2, pp: 142-145, Apr. (2004).

DOI: 10.1109/icmlc.2004.1384544

Google Scholar

[2] Liu Huai-hui. Research in The Algorithm of Finite Element Riangle Mesh Generation in Planar Area[D]. Shandong: Shandong university, 2008. 4. 24.

Google Scholar

[3] Cheng Hong-wei. 3D Movement Analysis of Connection Body and Elastomer Based on Image Sequence [D]. Zhejiang: Zhejiang Sci-Tech University, 2007. 3. 30.

Google Scholar

[4] Zhang Peng. The Application Research of Markov stochastic field in The Image Processing [D]. Hubei: Huazhong University of Science And Technology, 2005. 5. 12.

Google Scholar

[5] Rajala, Miika, Ritala, Risto. A Method to Estimate the Graph Structure for A Large MRF Model[J]. 17th International Conference on Artificial Neural Networks, ICANN, 2007, 4669: 836-849.

DOI: 10.1007/978-3-540-74695-9_86

Google Scholar

[6] Li Xing-lin. 3D Movement Analysis [M]. China science and technology university press, pp: 2-4, (1994).

Google Scholar

[7] Ting Chen, Wei-Chung Lin. Artificial Neural Networks for 3-D Motion Analysis-Part II: Nonrigid Motion [J]. IEEE Trans Neural Networks, 1995, 6(6): 1394-1401.

DOI: 10.1109/72.471368

Google Scholar

[8] Schindler, Konrad. Spatially consistent 3D motion segmentation[J]. Proceedings- International Conference on Image Processing, ICIP, 2005, 3: 409-412.

DOI: 10.1109/icip.2005.1530415

Google Scholar