Abstract
To solve the problem of the three-dimensional point clouds segmentation of complex structure, a new segmentation algorithm by discrete unit sampling module (DUSM) based on PointSIFT is proposed. Due to the inherent disorder and density difference of 3D point cloud, as well as the redundant surrounding noise points, which make some limitations on the representation and segmentation of complex components. Therefore, based on the PointSIFT input parameters and point cloud collection method, this paper improves the algorithm and completes the point cloud segmentation of complex structure. In this paper, PointSIFT that the point cloud segmentation network is improved appropriately. Secondly, point clouds data that selecting hull structure as a complex structure is derived from the CAD and annotation, which forms the training and validation data sets. Finally, the improved algorithm was adopted to complete the training and verification for the point cloud segmentation network model. The accuracy rate is 81.7% by verification. Experimental results show that the improved point cloud segmentation network model can be applied to the segmentation of complex structure, and has a good generalization effect.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhang, X., Liu, J., Shi, Z., et al.: Review of deep learning based semantic segmentation. Laser Optoelectron. Prog. 56(15) (2016)
Chen, L., Papandreou, G., Kokkinos, I., et al.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2016)
He, K., Georgia, G., Piotr, D., et al.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 386–397 (2018)
Hang, S., Maji, S., Kalogerakis, E., et al: Multi-view convolutional neural networks for 3D shape recognition. arXiv preprint arXiv:1505.00880 (2015)
Zhi, S., Liu, Y., Li, X., et al.: LightNet: a lightweight 3D convolutional neural network for real-time 3D object recognition. In: Eurographics Workshop on 3D Object Retrieval, Lyon, pp. 009–016 (2017)
Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, pp. 1912–1920. IEEE (2015)
Jiang, M., Wu, Y., Lu, C., PointSIFT: a SIFT-like network module for 3D point cloud semantic segmentation. arXiv preprint arXiv:1807.00652 (2018)
Shi, Y., Chu, Z.: Principle and application of 3D point cloud segmentation. Sci. Technol. Inf. (24) (2016)
Qi, C., Su, H., Mo, K., et al.: PointNet: deep learning on point sets for 3D classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, pp. 77–85. IEEE (2017)
Qi, C., Yi, L., Su, H., et al.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the Conference on Neural Information Processing Systems, Long Beach, pp. 77–85. NIPS (2017)
Ren, X., Wang, W., Xu, S.: An innovative segmentation method with multi-feature fusion for 3D point cloud. J. Intell. Fuzzy Syst. 38(1), 345–353 (2020)
Yang, Y., Chen, F., Wu, F., Zeng, D., et al.: Multi-view semantic learning network for point cloud based 3D object detection. Neurocomputing 397, 477–485 (2020)
Jaritz, M., Gu, J., Su, H.: Multi-view PointNet for 3D scene understanding. arXiv preprint arXiv:1909.13603 (2019)
Pham, Q., Duc, T., et al.: JSIS3D: joint semantic instance segmentation of 3D point clouds with multi-task pointwise networks and multi-value conditional random fields. In: 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, pp. 8827–8836. IEEE (2019)
Wu, W., Qi, Z., Li, F., PointConv: deep convolutional networks on 3D point clouds. In: 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beac, pp. 9621–9630. IEEE (2019)
Cheng, S., Wang, J., Liu, Y., Zhang, X.: Intelligent recognition of block erection surface based on PointNet++. Mar. Eng. 41(12), 138–141 (2019)
Yang, B., Dong, Z., Liu, Y., et al.: Computing multiple aggregation levels and contextual features for road facilities recognition using mobile laser scanning data. ISPRS J. Photogramm. Remote Sens. 126, 180–194 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Z., Wang, J., Qu, X., Xiao, J. (2020). 3D Point Cloud Segmentation for Complex Structure Based on PointSIFT. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12305. Springer, Cham. https://doi.org/10.1007/978-3-030-60633-6_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-60633-6_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60632-9
Online ISBN: 978-3-030-60633-6
eBook Packages: Computer ScienceComputer Science (R0)