Optimized PointNet for 3D Object Classification

  • Zhuangzhuang Li
  • Wenmei LiEmail author
  • Haiyan Liu
  • Yu Wang
  • Guan Gui
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 301)


Three-dimensional (3D) laser scanning technology is widely used to get the 3D geometric information of the surrounding environment, which leads to a huge increase interest of point cloud. The PointNet based on neural network can directly process point clouds, and it provides a unified frame to handle the task of object classification, part segmentation and semantic segmentation. It is indicated that the PointNet is efficient for target segmentation. However, the number of neural network layers and loss function are not good enough for target classification. In this paper, we optimize the original neural network by deepen the layers of neural network. Simulation result shows that the overall accuracy increases from 89.20% to 89.35%. Meanwhile, the combination of softmax loss with center loss function is adopt to enhance the robustness of classification, and the overall accuracy is up to 89.95%.


Point cloud PointNet Object classification Center loss 


  1. 1.
    Yanaka, K., Yamanouchi, T.: 3D image display courses for information media students. IEEE Comput. Graph. Appl. 36(2), 68–73 (2016)CrossRefGoogle Scholar
  2. 2.
    Grubisic, I., Gjenero, L., Lipic, T., Sovic, I., Skala, T.: Active 3D scanning based 3D thermography system and medical applications. In: Proceedings of the 34th International Convention MIPRO, pp. 269–273 (2011)Google Scholar
  3. 3.
    Ravi, D., et al.: Deep learning for health informatics. IEEE J. Biomed. Heal. Inform. 21(1), 4–21 (2016)CrossRefGoogle Scholar
  4. 4.
    Huang, H., Yang, J., Song, Y., Huang, H., Gui, G.: Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system. IEEE Trans. Veh. Technol. 67(9), 8549–8560 (2018)CrossRefGoogle Scholar
  5. 5.
    Zhang, L., Jia, J., Gui, G., Hao, X., Gao, W., Wang, M.: Deep learning based improved classification system for designing tomato harvesting robot. IEEE Access 6, 67940–67950 (2018)CrossRefGoogle Scholar
  6. 6.
    Li, W., Liu, H., Wang, Y., Li, Z., Jia, Y., Gui, G.: Deep learning-based classification methods for remote sensing images in urban built-up areas. IEEE Access 7, 36274–36284 (2019)CrossRefGoogle Scholar
  7. 7.
    Garcia-Garcia, A., Gomez-Donoso, F., Garcia-Rodriguez, J., Orts-Escolano, S., Cazorla, M., Azorin-Lopez, J.: PointNet: a 3D convolutional neural network for real-time object class recognition. In: Proceedings of the International Joint Conference on Neural Networks, vol. 2016, pp. 1578–1584, October 2016Google Scholar
  8. 8.
    Wang, X., Liu, M.: Multi-view deep metric learning for volumetric image recognition. In: Proceedings - IEEE International Conference on Multimedia and Expo, Mvdml, 2018, vol. 2018, pp. 1–6, July 2018Google Scholar
  9. 9.
    Gao, Y., Radha, H.: Multi-view image coding using 3-D voxel models. In: Proceedings - International Conference on Image Processing, ICIP, vol. 2, pp. 257–260 (2005)Google Scholar
  10. 10.
    Ge, L., Cai, Y., Weng, J., Yuan, J.: Hand PointNet: 3D hand pose estimation using point sets. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 8417–8426 (2018)Google Scholar
  11. 11.
    Li, Z.: A discriminative learning convolutional neural network for facial expression recognition. In: 2017 3rd IEEE International Conference on Computer and Communications, pp. 1641–1646 (2017)Google Scholar
  12. 12.
    Ge, L., Liang, H., Yuan, J., Thalmann, D.: Robust 3d hand pose estimation in single depth images: from single-view cnn to multi-view CNNs. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016, pp. 3593–3601 (2016)Google Scholar
  13. 13.
    Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017, pp. 77–85, January 2017Google Scholar
  14. 14.
    Chen, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: International Conference on Neural Information Processing Systems, pp. 1988–1996 (2014)Google Scholar
  15. 15.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 07–12 June, pp. 815–823 (2015)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019

Authors and Affiliations

  • Zhuangzhuang Li
    • 1
  • Wenmei Li
    • 1
    • 2
    Email author
  • Haiyan Liu
    • 1
  • Yu Wang
    • 1
  • Guan Gui
    • 1
  1. 1.College of Telecommunications and Information EngineeringNanjing University of Posts and TelecommunicationsNanjingChina
  2. 2.School of Geographic and Biologic InformationNanjing University of Posts and TelecommunicationsNanjingChina

Personalised recommendations