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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ku, T., et al.: Shrec 2020: 3D point cloud semantic segmentation for street scenes. Comput. Graphics 93(2020), 13–24 (2020)
Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2D–3D-semantic data for indoor scene understanding. CoRR abs/1702.01105 (2017)
Behley, J., et al.: Semantickitti: a dataset for semantic scene understanding of lidar sequences. In: IEEE ICCV, pp. 9296–9306 (2019)
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)
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)
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)
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)
Huang, J., You, S.: Point cloud labeling using 3D convolutional neural network. In: ICPR, pp. 2670–2675 (2016)
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)
Choy, C.B., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: Minkowski convolutional neural networks. In: IEEE CVPR, pp. 3070–3079 (2019)
Graham, B., Engelcke, M., van der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: IEEE CVPR, pp. 9224–9232 (2018)
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)
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)
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)
Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: Pointcnn: convolution on x-transformed points. In: NeurIPS, pp. 828–838 (2018)
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)
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
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)
Landrieu, L., Simonovsky, M.: Large-scale point cloud semantic segmentation with superpoint graphs. In: IEEE CVPR, pp. 4558–4567 (2018)
Hu, Q., et al.: Randla-net: efficient semantic segmentation of large-scale point clouds. In: IEEE CVPR, pp. 11105–11114 (2020)
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)
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)
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)
Zolanvari, S.M.I., et al.: Dublincity: annotated lidar point cloud and its applications. In: BMVC, vol. 44. BMVA Press (2019)
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)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84–90 (2017)
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)
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)
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)
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)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (Poster) (2016)
Hendrycks, D., Gimpel, K.: Bridging nonlinearities and stochastic regularizers with gaussian error linear units. CoRR abs/1606.08415 (2016)
Lin, M., Chen, Q., Yan, S.: Network in network. CoRR abs/1312.4400 (2014)
Agarap, A.F.: Deep learning using rectified linear units (relu). CoRR abs/1803.08375 (2018)
CloudCompare: 3D point cloud and mesh processing software open source project (2020)
Huang, Q., Wang, W., Neumann, U.: Recurrent slice networks for 3D segmentation of point clouds. In: IEEE CVPR, pp. 2626–2635 (2018)
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
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)
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)
Su, H., et al.: Splatnet: sparse lattice networks for point cloud processing. In: IEEE CVPR, pp. 2530–2539 (2018)
Tatarchenko, M., Park, J., Koltun, V., Zhou, Q.Y.: Tangent convolutions for dense prediction in 3D. In: IEEE CVPR, pp. 3887–3896 (2018)
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)
Milioto, A., Vizzo, I., Behley, J., Stachniss, C.: Rangenet ++: fast and accurate lidar semantic segmentation. In: IEEE IROS, pp. 4213–4220 (2019)
Rosu, R.A., Schütt, P., Quenzel, J., Behnke, S.: Latticenet: fast point cloud segmentation using permutohedral lattices. CoRR abs/1912.05905 (2019)
Cortinhal, T., Tzelepis, G., Aksoy, E.E.: Salsanext: fast, uncertainty-aware semantic segmentation of lidar point clouds for autonomous driving (2020)
Xu, C., et al.: Squeezesegv3: spatially-adaptive convolution for efficient point-cloud segmentation. CoRR abs/2004.01803 (2020)
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
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
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)