Abstract
Template-based deformable surface shape recovery is a well-known challenging problem for its compatible local minima and high degree of freedom. The gradient-based optimization method often converges to the local minimum, the premature convergence also occurs even using the evolution strategies which are highly effective in locating a single global minimum. Meanwhile, exploration in a high dimensional space is often time exhausted. To avoid these difficulties, a two-step method was proposed. The projections of vertices of a mesh were estimated firstly. Then the 3D positions of the vertices were estimated via estimating the depth along the sightlines calculated according to the given projections. While the depth of vertices was estimated, the problem was regarded as a multimodal optimization. A DE-based niching algorithm was used to solve it, and the partial reinitialization was used to keep the diversity of the population. The effectiveness of our method was demonstrated on both synthetic data and real images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Salzmann, M., Pilet, J., Ilic, S., Fua, P.: Surface Deformation Models for Nonrigid 3d Shape Recovery. IEEE Transaction on Pattern Analysis and Machine Intelligence 29(8) (2007)
Salzmann, M., Fua, P.: Linear Local Models forMonocular Reconstruction of Deformable Surfaces. IEEE Transaction on Pattern Analysis and Machine Intelligence 33(5) (2011)
Varol, A., Salzmann, M., Fua, P., Urtasun, R.: A Constrained Latent Variable Model. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)
Moreno Noguer, F., Fua, P.: Stochastic Exploration ofAmbiguities for Non-Rigid Shape Recovery. IEEE Transaction on Pattern Analysis and Machine Intelligence 35(2) (2013)
Bartoli, A., Gerard, Y., Chadebecq, F., Collins, T.: on Template-Based Reconstruction From A Single View: Analytical Solutions And Proofs ofWell-Posedness forDevelopable, Isometric And Conformal Surfaces. In: IEEE Conference on Computer Vision And Pattern Recognition (2012)
Das, S., Suganthan, P.N.: Differential Evolution: A Survey ofThe State-Of-The-Art. IEEE Transaction on Evolutionary Computation 15(1) (2011)
Qu, B.Y., Suganthan, P.N., Liang, J.J.: Differential Evolution With Neighborhood Mutation forMultimodal Optimization. IEEE Transaction on Evolutionary Computation 16(5) (2012)
Storn, R., Whigham, P.: Differential Evolution: A Simple And Efficient Heuristic forGlobal Optimization Over Continuous Spaces. J. Global Optimization 11(4) (1995)
Qin, V.K., Huang, V.L., Suganthan, P.N.: Differential Evolution Algorithm With Strategy Adaption forGlobal Numerical Optimization. IEEE Transaction on Evolutionary Computation 13(2) (2009)
Qu, B.Y., Suganthan, P.N.: Multiobjectives And Diversified Selection. Information Science 180(17) (2010)
Thomsen, R.: Multimodal Optimization Using Crowding-Based Differential Evolution. IEEE Congress on Evolutionary Computation (2004)
Rumpler, J., Moore, F.: Automatic Selection ofSubpopulations And Minimal Spanning Distances forImproved Numerical Optimization. IEEE Congress on Evolutionary Computation (2001)
Rigling, B., Moore, F.: Exploitation of Subpopulation In Evolutionary Strategies forImproved Numerical Optimization. In: Proc. 11th MAICS (1999)
Salzmann, M., Hartley, R., Fua, P.: Convex Optimization forDeformable Surface 3-D Tracking. In: IEEE International Conference on Computer Vision (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, X., Wang, F., Chen, L. (2014). Monocular 3D Shape Recovery of Inextensibility Deformable Surface by Using DE-Based Niching Algorithm with Partial Reinitialization. In: Huang, DS., Jo, KH., Wang, L. (eds) Intelligent Computing Methodologies. ICIC 2014. Lecture Notes in Computer Science(), vol 8589. Springer, Cham. https://doi.org/10.1007/978-3-319-09339-0_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-09339-0_34
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09338-3
Online ISBN: 978-3-319-09339-0
eBook Packages: Computer ScienceComputer Science (R0)