Recognition and Classification for Three-Dimensional Model Based on Deep Voxel Convolution Neural Network

被引：0
|
作者：
Yang J. [1 ]
Wang S. [2 ]
Zhou P. [1 ]
机构：
[1] School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou, 730070, Gansu
[2] School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, 730070, Gansu
来源：
Guangxue Xuebao/Acta Optica Sinica | 2019年 / 39卷 / 04期
关键词：
Computer vision; Convolutional neural network; Image processing; Recognition of three-dimensional model; Softmax classifier; Voxelization;
D O I：
10.3788/AOS201939.0415007
中图分类号：
学科分类号：
摘要：
An algorithm of recognition and classification of three-dimensional (3D) model based on deep voxel convolution neural network is proposed. The voxelization technology is used to transform 3D polygon mesh model into a voxel matrix, and the deep features of the matrix are extracted by the deep voxel convolution neural network to enhance the expressive ability and difference of the features. The experimental results on ModelNet40 dataset show that the accuracy of the algorithm can reach about 87% for recognizing and classifying 3D mesh model. The constructed deep voxel convolution neural network can effectively enhance the feature extraction and expression ability of 3D model, as well as improve the classification accuracy of large-scale complex 3D mesh models, which is better than the current mainstream methods. © 2019, Chinese Lasers Press. All right reserved.
引用
收藏
相关论文
共 26 条
  • [1] Silberman N., Hoiem D., Kohli P., Et al., Indoor segmentation and support inference from RGBD images, Computer Vision-ECCV 2012, 2012, pp. 746-760, (2012)
  • [2] Xiao J.X., Owens A., Torralba A., SUN<sub>3</sub>D: a database of big spaces reconstructed using SfM and object labels, Sydney: 2013 IEEE International Conference on Computer Vision, pp. 1625-1632, (2013)
  • [3] Song S.R., Lichtenberg S.P., Xiao J.X., SUN RGB-D: a RGB-D scene understanding benchmark suite, 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 567-576, (2015)
  • [4] Chang A.X., Funkhouser T., Guibas L., Et al., ShapeNet: an information-rich 3D model repository, Computer Science, 1512, pp. 3-12, (2015)
  • [5] Qu L., Wang K.R., Chen L.L., Et al., Fast road detection based on RGBD images and convolutional neural network, Acta Optica Sinica, 37, 10, (2017)
  • [6] Masci J., Boscaini D., Bronstein M.M., Et al., Geodesic convolutional neural networks on Riemannian manifolds, 2015 IEEE International Conference on Computer Vision Workshop, pp. 832-840, (2015)
  • [7] Wu Z.R., Song S.R., Khosla A., Et al., 3D ShapeNets: a deep representation for volumetric shapes, Boston: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912-1920, (2015)
  • [8] Boscaini D., Masci J., Rodola E., Et al., Learning shape correspondence with anisotropic convolutional neural networks, Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 3197-3205, (2016)
  • [9] Boscaini D., Masci J., Melzi S., Et al., Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks, Computer Graphics Forum, 34, 5, pp. 13-23, (2015)
  • [10] Bronstein A.M., Bronstein M.M., Guibas L.J., Et al., Shape google, ACM Transactions on Graphics, 30, 1, pp. 1-20, (2011)
123