Skip to main content
SpringerLink
Log in

3D Object Recognition Based on Point Cloud Geometry Construction and Embeddable Attention

  • Conference paper
  • First Online:
Image and Graphics (ICIG 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14357))

Included in the following conference series:

  • 333 Accesses

Abstract

A point cloud is a collection of disordered and discrete points with irregularity, and it lacks of topological structure. The number of discrete points in the point cloud is huge, and how to capture the key features from the large amount of points is crucial to improve the accuracy of model recognition. In this paper, based on point cloud geometry construction and embeddable attention, a 3D object recognition algorithm is proposed. By constructing triangular geometries between points, topological structure information to the point cloud is stored for points’ geometric construction module. The embeddable attention module uses an improved attention mechanism with feature bias and nonlinear mapping to enable focused attention to capture key features. In addition, a combination of max and average pooling to aggregate global feature has been applied to avoid situations when using only one method would ignore other key information. In comparison with other state-of-the-art methods using ModelNet40 and ScanObjectNN, the proposed method shows significant improvements in identifying both mAcc and OA. The experiments also demonstrate the effectiveness of the modules in this algorithm.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Chiang, C.H., Kuo, C.H., Lin, C.C., Chiang, H.T.: 3D point cloud classification for autonomous driving via dense-residual fusion network. IEEE Access 8, 163775–163783 (2020)

    Article  Google Scholar 

  2. Yang, L., Liu, Y., Peng, J., Liang, Z.: A novel system for off-line 3D seam extraction and path planning based on point cloud segmentation for arc welding robot. Robot. Comput. Integr. Manuf. 64(3), 101929 (2020)

    Article  Google Scholar 

  3. Bolkas, D., Chiampi, J., Chapman, J., Pavill, V.F.: Creating a virtual reality environment with a fusion of sUAS and TLS point-clouds. Int. J. Image Data Fusion 1, 1–26 (2020)

    Google Scholar 

  4. Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. IEEE (2017)

    Google Scholar 

  5. Qi, C.R., Li, Y., Hao, S., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space (2017)

    Google Scholar 

  6. Yan, X., Zheng, C., Li, Z., Wang, S., Cui, S.: PointASNL: robust point clouds processing using nonlocal neural networks with adaptive sampling. IEEE (2020)

    Google Scholar 

  7. Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: convolution on x-transformed points. In: Neural Information Processing Systems (2018)

    Google Scholar 

  8. Wu, W., Qi, Z., Li, F.: PointConv: deep convolutional networks on 3D point clouds. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    Google Scholar 

  9. Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Guibas, L.J.: KpConv: flexible and deformable convolution for point clouds (2019)

    Google Scholar 

  10. Yan, S., et al.: Implicit autoencoder for point cloud self-supervised representation learning. arXiv e-prints (2022)

    Google Scholar 

  11. Guo, M.H., Cai, J.X., Liu, Z.N., Mu, T.J., Martin, R.R., Hu, S.M.: PCT: point cloud transformer. Comput. Visual Media 7(2), 13 (2021)

    Article  Google Scholar 

  12. Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)

    Google Scholar 

  13. Atzmon, M., Maron, H., Lipman, Y.: Point convolutional neural networks by extension operators. ACM Trans. Graph. 37(4CD), 71.1– 71.12 (2018)

    Google Scholar 

  14. Liu, X., Han, Z., Liu, Y.S., Zwicker, M.: Point2Sequence: learning the shape representation of 3D point clouds with an attention-based sequence to sequence network. Proc. AAAI Conf. Artif. Intell. 33, 8778–8785 (2019)

    Google Scholar 

  15. Fan, B., Pan, C., Xiang, S., Liu, Y.: Relation-shape convolutional neural network for point cloud analysis (2019)

    Google Scholar 

  16. Qiu, S., Anwar, S., Barnes, N.: Geometric back-projection network for point cloud classification (2019)

    Google Scholar 

  17. Engel, N., Belagiannis, V., Dietmayer, K.: Point transformer (2020)

    Google Scholar 

  18. Liu, Z., Hu, H., Cao, Y., Zhang, Z., Tong, X.: A closer look at local aggregation operators in point cloud analysis (2020)

    Google Scholar 

  19. Han, X.F., Kuang, Y.J., Xiao, G.Q.: Point cloud learning with transformer (2021)

    Google Scholar 

  20. Zhao, H., Jiang, L., Jia, J., Torr, P., Koltun, V.: Point transformer (2020)

    Google Scholar 

  21. Ran, H., Liu, J., Wang, C.: Surface representation for point clouds (2022)

    Google Scholar 

  22. Liu, S., Liu, D., Chen, C., Xu, C.: SGCNN for 3D point cloud classification. In: 2022 14th International Conference on Machine Learning and Computing (ICMLC) (2022)

    Google Scholar 

  23. Lu, D., Xie, Q., Xu, L., Li, J.: 3DCTN: 3D convolution-transformer network for point cloud classification (2022)

    Google Scholar 

  24. Xu, Y., Fan, T., Xu, M., Long, Z., Yu, Q.: SpiderCNN: deep learning on point sets with parameterized convolutional filters (2018)

    Google Scholar 

  25. Uy, M.A., Pham, Q.H., Hua, B.S., Nguyen, T., Yeung, S.K.: Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data. IEEE (2020)

    Google Scholar 

  26. Goyal, A., Law, H., Liu, B., Newell, A., Deng, J.: Revisiting point cloud shape classification with a simple and effective baseline (2021)

    Google Scholar 

  27. Qiu, S., Anwar, S., Barnes, N.: Dense-resolution network for point cloud classification and segmentation (2020)

    Google Scholar 

  28. Cheng, S., Chen, X., He, X., Liu, Z., Bai, X.: PRA-Net: point relation-aware network for 3D point cloud analysis. IEEE Trans. Image Process. 30, 4436–4448 (2021)

    Article  Google Scholar 

  29. Hamdi, A., Giancola, S., Li, B., Thabet, A., Ghanem, B.: MVTN: multi-view transformation network for 3D shape recognition (2020)

    Google Scholar 

  30. Klokov, R., Lempitsky, V.: Escape from cells: deep Kd-networks for the recognition of 3D point cloud models. IEEE (2017)

    Google Scholar 

Download references

Acknowledgements

This work is supported by Natural Science Foundation of Hebei Province (F2019202054).

Author information

Authors and Affiliations

  1. School of Artificial Intelligence, Hebei University of Technology, Tianjin, 300401, China

    Jingshan Shi, Zhuyan Guo, Shujia Cheng, Yuhan Liu & Mandun Zhang

  2. Tianjin International Joint Center for Virtual Reality and Visual Computing, Tianjin, 300401, China

    Jingshan Shi, Zhuyan Guo, Shujia Cheng, Yuhan Liu & Mandun Zhang

  3. Faculty of Media and Communication, Bournemouth University, Bournemouth, BH12 5BB, UK

    Zhidong Xiao

Authors
  1. Jingshan Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhuyan Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shujia Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuhan Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mandun Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhidong Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mandun Zhang .

Editor information

Editors and Affiliations

  1. Dalian University of Technology, Dalian, China

    Huchuan Lu

  2. University of Sydney, Sydney, NSW, Australia

    Wanli Ouyang

  3. Shenzhen University, Shenzhen, China

    Hui Huang

  4. Tsinghua University, Beijing, China

    Jiwen Lu

  5. Dalian University of Technology, Dalian, China

    Risheng Liu

  6. Institute of Automation, CAS, Beijing, China

    Jing Dong

  7. University of Technology Sydney, Sydney, NSW, Australia

    Min Xu

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Shi, J., Guo, Z., Cheng, S., Liu, Y., Zhang, M., Xiao, Z. (2023). 3D Object Recognition Based on Point Cloud Geometry Construction and Embeddable Attention. In: Lu, H., et al. Image and Graphics . ICIG 2023. Lecture Notes in Computer Science, vol 14357. Springer, Cham. https://doi.org/10.1007/978-3-031-46311-2_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-46311-2_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-46310-5

  • Online ISBN: 978-3-031-46311-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation