Skip to main content
Springer Nature Link
Log in

Point-attention Net: a graph attention convolution network for point cloudsegmentation

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Point cloud classification and segmentation is a crucial yet challenging step towards 3D scene understanding. In response to the fact that 3D point clouds cannot be directly applied to traditional 2D image convolutional neural networks and sparse point cloud features are difficult to capture, an improved segmentation network Point-Attention Net is proposed. In comparison with existing techniques, the proposed method models on point cloud directly, avoiding the extra computational and memory cost of converting point cloud to other forms. It also employs a novel proportional discrete dilation model for analyzing the features of a point cloud on different scales simultaneously. Additionally, the proposed method combines the graph attention convolution and adaptive weight assignment techniques, yielding better segmentation performance on the edge point cloud and more accurate analysis of the adjacency and spatial geometric distribution. Experimental results show that our algorithm achieves 64.56 % and 74.1 % IoU on average on S3DIS and Semantic3D datasets respectively, outperforming the state of the art.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

We have referenced the relevant data sets.

References

  1. Hui L, Xu R, Xie J, Qian J, Yang J (2020) Progressive point cloud deconvolution generation network. In: Computer vision–ECCV 2020: 16th european conference, Glasgow, UK, August 23–28, 2020, proceedings, part XV 16, pp 397–413

  2. Zhang Z, Li K, Yin X, Piao X, Wang Y, Yang X, Yin B (2020) Point cloud semantic scene segmentation based on coordinate convolution. Comput Animat Virtual Worlds 31(4-5):1948

    Article  Google Scholar 

  3. Behmann N, Cheng Y, Schleusner J, Blume H (2019) Probabilistic 3d point cloud fusion on graphics processors for automotive (poster). In: 2019 22th international conference on information fusion (FUSION), IEEE, pp 1–6

  4. Pomerleau F, Colas F, Siegwart R (2015) A review of point cloud registration algorithms for mobile robotics. Found Trends Robot 4(1):1–104

    Article  Google Scholar 

  5. Balali V, Jahangiri A, Machiani SG (2017) Multi-class us traffic signs 3d recognition and localization via image-based point cloud model using color candidate extraction and texture-based recognition. Adv Eng Inf 32:263–274

    Article  Google Scholar 

  6. Chen SW, Nardari GV, Lee ES, Qu C, Liu X, Romero RAF, Kumar V (2020) Sloam: Semantic lidar odometry and mapping for forest inventory. IEEE Robot Autom Lett 5(2):612–619

    Article  Google Scholar 

  7. Fan Y, Zhang Q, Liu S, Tang Y, Jing X, Yao J, Han H (2020) Semantic slam with more accurate point cloud map in dynamic environments. IEEE Access 8:112237–112252

    Article  Google Scholar 

  8. Wang Y, Jiang T, Yu M, Tao S, Sun J, Liu S (2020) Semantic-based building extraction from lidar point clouds using contexts and optimization in complex environment. Sensors 20(12):3386

    Article  Google Scholar 

  9. Che E, Olsen MJ (2017) Fast edge detection and segmentation of terrestrial laser scans through normal variation analysis. In: ISPRS annals of photogrammetry, remote sensing & spatial information sciences, p 4

  10. Mineo C, Pierce S G, Summan R (2019) Novel algorithms for 3d surface point cloud boundary detection and edge reconstruction. J Comput Design Eng 6(1):81–91

    Article  Google Scholar 

  11. Che E, Olsen MJ (2018) Multi-scan segmentation of terrestrial laser scanning data based on normal variation analysis. ISPRS J Photogramm Remote Sens 143:233–248

    Article  Google Scholar 

  12. Kim J, Lee S (2015) Extracting major lines by recruiting zero-threshold canny edge links along sobel highlights. IEEE Signal Process Lett 22(10):1689–1692

    Article  MathSciNet  Google Scholar 

  13. Gyulassy A, Bremer P-T, Pascucci V (2018) Shared-memory parallel computation of morse-smale complexes with improved accuracy. IEEE Trans Vis Comput Graph 25(1):1183–1192

    Article  Google Scholar 

  14. Zhang C (2020) Topological feature recognition and transition feature protection of non dual point cloud. Opt Precis Eng 28(10):2301

    Article  Google Scholar 

  15. Guenther GC, Cunningham AG, LaRocque PE, Reid DJ (2000) Meeting the accuracy challenge in airborne bathymetry. Technical report, NATIONAL OCEANIC ATMOSPHERIC ADMINISTRATION/NESDIS SILVER SPRING MD

  16. Fernandez-Diaz JC, Glennie CL, Carter WE, Shrestha RL, Sartori MP, Singhania A, Legleiter CJ, Overstreet BT (2013) Early results of simultaneous terrain and shallow water bathymetry mapping using a single-wavelength airborne lidar sensor. IEEE J Sel Top Appl Earth Obs Remote Sens 7(2):623–635

    Article  Google Scholar 

  17. Ding Y, Zheng X, Xiong H, Zhang Y (2019) Semantic segmentation of indoor 3d point cloud with slenet. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences

  18. Luo Z, Li J, Xiao Z, Mou ZG, Cai X, Wang C (2019) Learning high-level features by fusing multi-view representation of mls point clouds for 3d object recognition in road environments. ISPRS J Photogramm Remote Sens 150:44–58

    Article  Google Scholar 

  19. Tchapmi L, Choy C, Armeni I, Gwak J, Savarese S (2017) Segcloud: Semantic segmentation of 3d point clouds. In: 2017 international conference on 3D vision (3DV), IEEE, pp 537–547

  20. Qi C R, Su H, Mo K, Guibas LJ (2017) Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 652–660

  21. Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: Deep hierarchical feature learning on point sets in a metric space. arXiv:1706.02413

  22. Su H, Maji S, Kalogerakis E, Learned-miller E (2015) Multi-view convolutional neural networks for 3d shape recognition. In: Proceedings of the IEEE international conference on computer vision, pp 945–953

  23. Qi CR, Su H, Nießner M, Dai A, Yan M, Guibas LJ (2016) Volumetric and multi-view cnns for object classification on 3d data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5648–5656

  24. Le T, Bui G, Duan Y (2017) A multi-view recurrent neural network for 3d mesh segmentation. Comput Graph 66:103–112

  25. Maturana D, Scherer S (2015) Voxnet: A 3d convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 922–928

  26. Li Y, Pirk S, Su H, Qi CR, Guibas LJ (2016) Fpnn: Field probing neural networks for 3d data. Adv Neural Inf Process Syst 29:307–315

    Google Scholar 

  27. Xu Y, Hoegner L, Tuttas S, Stilla U (2017) Voxel-and graph-based point cloud segmentation of 3d scenes using perceptual grouping laws. ISPRS Annals of Photogrammetry Remote Sensing & Spatial Information Sciences 4

  28. Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vis 59(2):167–181

    Article  MATH  Google Scholar 

  29. Van den Bergh M, Boix X, Roig G, de Capitani B, Van Gool L (2012) Seeds: superpixels extracted via energy-driven sampling. In: European conference on computer vision, Springer, pp 13–26

  30. Klokov R, Lempitsky V (2017) Escape from cells: deep kd-networks for the recognition of 3d point cloud models. In: Proceedings of the IEEE international conference on computer vision, pp 863–872

  31. Wang C, Samari B, Siddiqi K (2018) Local spectral graph convolution for point set feature learning. In: Proceedings of the european conference on computer vision (ECCV), pp 52–66

  32. Wang Y, Sun Y, Liu Z, Sarma SE, Bronstein MM, Solomon JM (2019) Dynamic graph CNN for learning on point clouds. ACM Trans Graph (tog) 38(5):1–12

    Article  Google Scholar 

  33. Huang Q, Wang W, Neumann U (2018) Recurrent slice networks for 3d segmentation of point clouds. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2626–2635

  34. Engelmann F, Kontogianni T, Hermans A, Leibe B (2017) Exploring spatial context for 3d semantic segmentation of point clouds. In: Proceedings of the IEEE international conference on computer vision workshops, pp 716–724

  35. Zhao C, Zhou W, Lu L, Zhao Q (2019) Pooling scores of neighboring points for improved 3d point cloud segmentation. In: 2019 IEEE international conference on image processing (ICIP), pp 1475–1479

  36. Xie S, Liu S, Chen Z, Tu Z (2018) Attentional shapecontextnet for point cloud recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4606–4615

  37. Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122

  38. Li G, Muller M, Thabet A, Ghanem B (2019) Deepgcns: can gcns go as deep as cnns?

  39. Long J, Zhang S, Li C (2019) Evolving deep echo state networks for intelligent fault diagnosis. IEEE Trans Ind Inf 16(7):4928–4937

    Article  Google Scholar 

  40. Tchapmi L, Choy C, Armeni I, Gwak J, Savarese S (2017) Segcloud: Semantic segmentation of 3d point clouds. In: 2017 international conference on 3D vision (3DV), IEEE, pp 537–547

  41. Landrieu L, Simonovsky M (2018) Large-scale point cloud semantic segmentation with superpoint graphs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4558–4567

  42. Boulch A, Guerry J, Le Saux B, Audebert N (2018) Snapnet: 3d point cloud semantic labeling with 2d deep segmentation networks. Comput Graph 71:189–198

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Nos.61906097) and a project funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD).

Author information

Authors and Affiliations

  1. Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science & Technology, Nanjing, 210044, China

    Suting Chen

  2. School of Artificial Intelligence/School of Future Technology, Nanjing University of Information Science & Technology, Nanjing, 210044, China

    Suting Chen, Zelin Miao & Mithun Mukherjee

  3. Nanjing University of Information Science & Technology, Nanjing, 210044, China

    Huaixin Chen & Yanyan Zhang

Authors
  1. Suting Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Zelin Miao
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Huaixin Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Mithun Mukherjee
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Yanyan Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Suting Chen.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, S., Miao, Z., Chen, H. et al. Point-attention Net: a graph attention convolution network for point cloudsegmentation. Appl Intell 53, 11344–11356 (2023). https://doi.org/10.1007/s10489-022-03985-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03985-4

Keywords