Motion estimation for 3d rigid object shapes based on 3d-2d color-consistency in multi-view

Authors:
Xiuxiu Li;Jiangbin Zheng;Huan Xu
Affiliations:
Northwestern Polytechnical University, Xi'an, China;Northwestern Polytechnical University, Xi'an, China;Northwestern Polytechnical University, Xi'an, China
Venue:
IScIDE'11 Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2011

Citing 5
Cited 0

Salient geometric features for partial shape matching and similarity

ACM Transactions on Graphics (TOG)
Reconstruction of deforming geometry from time-varying point clouds

SGP '07 Proceedings of the fifth Eurographics symposium on Geometry processing
A dense point-to-point alignment method for realistic 3D face morphing and animation

International Journal of Computer Games Technology - Special issue on cyber games and interactive entertainment
An extension of the ICP algorithm for modeling nonrigid objects with mobile robots

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
A Game-Theoretic Approach to Robust Selection of Multi-view Point Correspondence

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

A motion estimation algorithm for 3D rigid object in multi-view is proposed in this paper. In the algorithm, firstly, calculate the color difference between the shape of the 3D object and the silhouettes from multi-view to get the 3D-2D color-consistency; secondly, define an object function about the 3D- 2D color-consistency; lastly, minimize the object function with Levenberg- Marquard algorithm to obtain the 3D motion parameters. It is obvious that the algorithm could not be affected by the distribution and positioning accuracy of features owing to the usage of the whole color information. Some experiments show that the algorithm for the 3D shape motion estimation in multi-view videos is effective.