SpringerLink
Log in

3D Semantic Segmentation for Large-Scale Scene Understanding

  • Conference paper
  • First Online:
Computer Vision – ACCV 2020 Workshops (ACCV 2020)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12628))

Included in the following conference series:

Abstract

3D semantic segmentation is one of the most challenging events in the robotic vision tasks for detection and identification of various objects in a scene. In this paper, we solve the task of semantic segmentation to classify and assign every point in the scene with an associated label. We propose a lightweight semantic segmentation network for large-scale point clouds which consists of grid subsampling, dilated convolutions, and Gaussian error linear unit activation for gaining better performance. The dilated convolutions increase the receptive field while reducing the number of parameters, making proposed network faster and computationally more efficient with reduced number of parameters. Additionally, we use conditional random field as post processing method to boost the performance of proposed semantic segmentation network. We perform an exhaustive quantitative analysis of the proposed network on SOTA datasets, namely, SHREC 2020 street scenes dataset [1], S3DIS [2] and SemanticKITTI [3]. We show that proposed semantic segmentation network performs effectively and efficiently compared to SOTA methods.

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

Access this chapter

Log in via an institution
Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now
Chapter
EUR 29.95
Price includes VAT (France)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
EUR 42.79
Price includes VAT (France)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
EUR 52.74
Price includes VAT (France)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free ship** worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Ku, T., et al.: Shrec 2020: 3D point cloud semantic segmentation for street scenes. Comput. Graphics 93(2020), 13–24 (2020)

    Article  Google Scholar 

  2. Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2D–3D-semantic data for indoor scene understanding. CoRR abs/1702.01105 (2017)

    Google Scholar 

  3. Behley, J., et al.: Semantickitti: a dataset for semantic scene understanding of lidar sequences. In: IEEE ICCV, pp. 9296–9306 (2019)

    Google Scholar 

  4. Wu, B., Wan, A., Yue, X., Keutzer, K.: Squeezeseg: convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D lidar point cloud. In: IEEE ICRA, pp. 1887–1893 (2018)

    Google Scholar 

  5. Wang, Y., Shi, T., Yun, P., Tai, L., Liu, M.: Pointseg: real-time semantic segmentation based on 3D lidar point cloud. CoRR abs/1807.06288 (2018)

    Google Scholar 

  6. Biasutti, P., Bugeau, A., Aujol, J.F., Brédif, M.: Riu-net: embarrassingly simple semantic segmentation of 3d lidar point cloud. Ar**v abs/1905.08748 (2019)

    Google Scholar 

  7. Krispel, G., Opitz, M., Waltner, G., Possegger, H., Bischof, H.: Fuseseg: lidar point cloud segmentation fusing multi-modal data. In: IEEE WACV, pp. 1863–1872 (2020)

    Google Scholar 

  8. Huang, J., You, S.: Point cloud labeling using 3D convolutional neural network. In: ICPR, pp. 2670–2675 (2016)

    Google Scholar 

  9. Tchapmi, L.P., Choy, C.B., Armeni, I., Gwak, J., Savarese, S.: Segcloud: semantic segmentation of 3D point clouds. In: 3DV, pp. 537–547 (2017)

    Google Scholar 

  10. Choy, C.B., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: Minkowski convolutional neural networks. In: IEEE CVPR, pp. 3070–3079 (2019)

    Google Scholar 

  11. Graham, B., Engelcke, M., van der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: IEEE CVPR, pp. 9224–9232 (2018)

    Google Scholar 

  12. Meng, H.Y., Gao, L., Lai, Y.K., Manocha, D.: Vv-net: Voxel vae net with group convolutions for point cloud segmentation. In: IEEE ICCV, pp. 8499–8507 (2019)

    Google Scholar 

  13. Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: IEEE CVPR, pp. 77–85 (2017)

    Google Scholar 

  14. Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space, pp. 5099–5108 (2017)

    Google Scholar 

  15. Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: Pointcnn: convolution on x-transformed points. In: NeurIPS, pp. 828–838 (2018)

    Google Scholar 

  16. Wang, L., Huang, Y., Hou, Y., Zhang, S., Shan, J.: Graph attention convolution for point cloud semantic segmentation. In: IEEE CVPR, pp. 10296–10305 (2019)

    Google Scholar 

  17. Wang, C., Samari, B., Siddiqi, K.: Local spectral graph convolution for point set feature learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 56–71. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_4

    Chapter  Google Scholar 

  18. Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: Kpconv: flexible and deformable convolution for point clouds. In: IEEE ICCV, pp. 6410–6419 (2019)

    Google Scholar 

  19. Landrieu, L., Simonovsky, M.: Large-scale point cloud semantic segmentation with superpoint graphs. In: IEEE CVPR, pp. 4558–4567 (2018)

    Google Scholar 

  20. Hu, Q., et al.: Randla-net: efficient semantic segmentation of large-scale point clouds. In: IEEE CVPR, pp. 11105–11114 (2020)

    Google Scholar 

  21. Hamaguchi, R., Fujita, A., Nemoto, K., Imaizumi, T., Hikosaka, S.: Effective use of dilated convolutions for segmenting small object instances in remote sensing imagery. In: IEEE WACV, pp. 1442–1450 (2018)

    Google Scholar 

  22. Hackel, T., Savinov, N., Ladicky, L., Wegner, J.D., Schindler, K., Pollefeys, M.: Semantic3d.net: a new large-scale point cloud classification benchmark. CoRR abs/1704.03847 (2017)

    Google Scholar 

  23. Roynard, X., Deschaud, J., Goulette, F.: Paris-lille-3D: a point cloud dataset for urban scene segmentation and classification. In: CVPR Workshops, pp. 2027–2030 (2018)

    Google Scholar 

  24. Zolanvari, S.M.I., et al.: Dublincity: annotated lidar point cloud and its applications. In: BMVC, vol. 44. BMVA Press (2019)

    Google Scholar 

  25. Biasutti, P., Aujol, J.F., Brédif, M., Bugeau, A.: Range-image: incorporating sensor topology for lidar point cloud processing. Photogram. Eng. Remote Sensing 84, 367–375 (2018)

    Article  Google Scholar 

  26. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84–90 (2017)

    Article  Google Scholar 

  27. Alonso, I., Riazuelo, L., Montesano, L., Murillo, A.C.: 3D-mininet: Learning a 2D representation from point clouds for fast and efficient 3D lidar semantic segmentation (2020)

    Google Scholar 

  28. Ma, Y., Guo, Y., Liu, H., Lei, Y., Wen, G.: Global context reasoning for semantic segmentation of 3D point clouds. In: IEEE WACV, pp. 2920–2929 (2020)

    Google Scholar 

  29. Wang, X., Liu, S., Shen, X., Shen, C., Jia, J.: Associatively segmenting instances and semantics in point clouds. In: IEEE CVPR, pp. 4091–4100 (2019)

    Google Scholar 

  30. Pham, Q.H., Nguyen, T., Hua, B.S., Roig, G., Yeung, S.K.: Jsis3D: joint semantic-instance segmentation of 3D point clouds with multi-task pointwise networks and multi-value conditional random fields. In: IEEE CVPR, pp. 8827–8836 (2019)

    Google Scholar 

  31. Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (Poster) (2016)

    Google Scholar 

  32. Hendrycks, D., Gimpel, K.: Bridging nonlinearities and stochastic regularizers with gaussian error linear units. CoRR abs/1606.08415 (2016)

    Google Scholar 

  33. Lin, M., Chen, Q., Yan, S.: Network in network. CoRR abs/1312.4400 (2014)

    Google Scholar 

  34. Agarap, A.F.: Deep learning using rectified linear units (relu). CoRR abs/1803.08375 (2018)

    Google Scholar 

  35. CloudCompare: 3D point cloud and mesh processing software open source project (2020)

    Google Scholar 

  36. Huang, Q., Wang, W., Neumann, U.: Recurrent slice networks for 3D segmentation of point clouds. In: IEEE CVPR, pp. 2626–2635 (2018)

    Google Scholar 

  37. Ye, X., Li, J., Huang, H., Du, L., Zhang, X.: 3D recurrent neural networks with context fusion for point cloud semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 415–430. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_25

    Chapter  Google Scholar 

  38. Zhao, H., Jiang, L., Fu, C.W., Jia, J.: Pointweb: enhancing local neighborhood features for point cloud processing. In: IEEE CVPR, pp. 5560–5568 (2019)

    Google Scholar 

  39. Zhang, Z., Hua, B.S., Yeung, S.K.: Shellnet: Efficient point cloud convolutional neural networks using concentric shells statistics. In: IEEE ICCV, pp. 1607–1616 (2019)

    Google Scholar 

  40. Su, H., et al.: Splatnet: sparse lattice networks for point cloud processing. In: IEEE CVPR, pp. 2530–2539 (2018)

    Google Scholar 

  41. Tatarchenko, M., Park, J., Koltun, V., Zhou, Q.Y.: Tangent convolutions for dense prediction in 3D. In: IEEE CVPR, pp. 3887–3896 (2018)

    Google Scholar 

  42. Wu, B., Zhou, X., Zhao, S., Yue, X., Keutzer, K.: Squeezesegv 2: improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud. In: ICRA, pp. 4376–4382 (2019)

    Google Scholar 

  43. Milioto, A., Vizzo, I., Behley, J., Stachniss, C.: Rangenet ++: fast and accurate lidar semantic segmentation. In: IEEE IROS, pp. 4213–4220 (2019)

    Google Scholar 

  44. Rosu, R.A., Schütt, P., Quenzel, J., Behnke, S.: Latticenet: fast point cloud segmentation using permutohedral lattices. CoRR abs/1912.05905 (2019)

    Google Scholar 

  45. Cortinhal, T., Tzelepis, G., Aksoy, E.E.: Salsanext: fast, uncertainty-aware semantic segmentation of lidar point clouds for autonomous driving (2020)

    Google Scholar 

  46. Xu, C., et al.: Squeezesegv3: spatially-adaptive convolution for efficient point-cloud segmentation. CoRR abs/2004.01803 (2020)

    Google Scholar 

Download references

Acknowledgement

This research work is partly supported (DST/ICPS/IHDS/2018) under the Indian Heritage in Digital Space (IHDS) of Interdisciplinary Cyber Physical Systems (ICPS) Programme of the Department of Science and Technology (DST), Government of India.

Author information

Authors and Affiliations

  1. KLE Technological University, Hubballi, India

    Kiran Akadas & Shankar Gangisetty

Authors
  1. Kiran Akadas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shankar Gangisetty
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kiran Akadas .

Editor information

Editors and Affiliations

  1. National Institute of Informatics, Tokyo, Japan

    Imari Sato

  2. Seoul National University, Seoul, Korea (Republic of)

    Bohyung Han

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Akadas, K., Gangisetty, S. (2021). 3D Semantic Segmentation for Large-Scale Scene Understanding. In: Sato, I., Han, B. (eds) Computer Vision – ACCV 2020 Workshops. ACCV 2020. Lecture Notes in Computer Science(), vol 12628. Springer, Cham. https://doi.org/10.1007/978-3-030-69756-3_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-69756-3_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-69755-6

  • Online ISBN: 978-3-030-69756-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation