Redirigiendo al acceso original de articulo en 21 segundos...
Inicio  /  Algorithms  /  Vol: 14 Par: 3 (2021)  /  Artículo
ARTÍCULO
TITULO

3D Mesh Model Classification with a Capsule Network

Yang Zheng    
Jieyu Zhao    
Yu Chen    
Chen Tang and Shushi Yu    

Resumen

With the widespread success of deep learning in the two-dimensional field, how to apply deep learning methods from two-dimensional to three-dimensional field has become a current research hotspot. Among them, the polygon mesh structure in the three-dimensional representation as a complex data structure provides an effective shape approximate representation for the three-dimensional object. Although the traditional method can extract the characteristics of the three-dimensional object through the graphical method, it cannot be applied to more complex objects. However, due to the complexity and irregularity of the mesh data, it is difficult to directly apply convolutional neural networks to 3D mesh data processing. Considering this problem, we propose a deep learning method based on a capsule network to effectively classify mesh data. We first design a polynomial convolution template. Through a sliding operation similar to a two-dimensional image convolution window, we directly sample on the grid surface, and use the window sampling surface as the minimum unit of calculation. Because a high-order polynomial can effectively represent a surface, we fit the approximate shape of the surface through the polynomial, use the polynomial parameter as the shape feature of the surface, and add the center point coordinates and normal vector of the surface as the pose feature of the surface. The feature is used as the feature vector of the surface. At the same time, to solve the problem of the introduction of a large number of pooling layers in traditional convolutional neural networks, the capsule network is introduced. For the problem of nonuniform size of the input grid model, the capsule network attitude parameter learning method is improved by sharing the weight of the attitude matrix. The amount of model parameters is reduced, and the training efficiency of the 3D mesh model is further improved. The experiment is compared with the traditional method and the latest two methods on the SHREC15 data set. Compared with the MeshNet and MeshCNN, the average recognition accuracy in the original test set is improved by 3.4% and 2.1%, and the average after fusion of features the accuracy reaches 93.8%. At the same time, under the premise of short training time, this method can also achieve considerable recognition results through experimental verification. The three-dimensional mesh classification method proposed in this paper combines the advantages of graphics and deep learning methods, and effectively improves the classification effect of 3D mesh model.

 Artículos similares

       
 
Morhaf Aljber, Han Soo Lee, Jae-Soon Jeong and Jonathan Salar Cabrera    
In tsunami studies, understanding the intricate dynamics in the swash area, characterised by the shoaling effect, remains a challenge. In this study, we employed the adaptive mesh refinement (AMR) method to model tsunami inundation and propagation in the... ver más

 
Zhenyang He, Wenbin Wu, Junrong Wang, Lan Ding, Qiangbo Chang and Yahao Huang    
When the underwater submersible encounters an internal solitary wave (ISW), its loadings and motions are significantly disturbed. To investigate the interaction mechanism between the suspended submersible and the ISW, a three-dimensional ISW?submersible-... ver más

 
Yacong Wu, Jun Huang, Boqian Ji and Lei Song    
Most existing studies on aerodynamic shape optimization have not considered longitudinal trim under control surface deflection, typically achieving self-trim through a constraint of zero pitching moment or adjusting the optimized configuration for longit... ver más
Revista: Aerospace

 
Balavignesh Vemparala, Wadi H. Imseeh, Salil Pai, Anand Nagarajan, Timothy Truster and Soheil Soghrati    
A new algorithm named PolyCISAMR is introduced to automatically generate high-fidelity conforming finite element (FE) meshes for two-dimensional polycrystalline microstructures. PolyCISAMR extends the capabilities of the Conforming to Interface Structure... ver más
Revista: Applied Sciences

 
Jianguo Zhao, Yang Yu, Hao Xu, Rongtang Zhang, Yuxi Ma and Jialiang Li    
Numerical seismic wave field simulation is essential for studying the dynamic responses in semi-infinite space, and the absorbing boundary setting is critical for simulation accuracy. This study addresses spherical waves incident from the free boundary b... ver más
Revista: Applied Sciences