Message Board

Respected readers, authors and reviewers, you can add comments to this page on any questions about the contribution, review,        editing and publication of this journal. We will give you an answer as soon as possible. Thank you for your support!

Name
E-mail
Phone
Title
Content
Verification Code
Turn off MathJax
Article Contents

Xiang Xueyong, Li Guangyun, Wang Li, Zong Wenpeng, Lü Zhipeng, Xiang Fengzhuo. Semantic segmentation of point clouds using local geometric features and dilated neighborhoods[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20200567
Citation: Xiang Xueyong, Li Guangyun, Wang Li, Zong Wenpeng, Lü Zhipeng, Xiang Fengzhuo. Semantic segmentation of point clouds using local geometric features and dilated neighborhoods[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20200567

Semantic segmentation of point clouds using local geometric features and dilated neighborhoods

doi: 10.13203/j.whugis20200567
Funds:

The National Natural Science Foundation of China (42071454)

  • Received Date: 2021-03-01
  • Objectives Point cloud has no topological structure, current deep learning semantic segmentation algorithm is difficult to capture geometric features implied in irregular points. In addition, the point cloud is in three-dimensional space with a large amount of data size. If we blindly expand the captive field size during extract neighborhood information, it will increase the number of model parameters, which will make model training difficult. Methods To this end, we propose a point cloud semantic segmentation model based on the dilated convolution and combining elementary geometric features such as angle as the model input. First of all, during feature extraction, basic geometric features such as the relative coordinates, distance and angle between the centroid and the neighboring points are used as the model input to mine the geometric information. Secondly, in the process of building local neighborhoods, we expand the image dilated convolution operator to point cloud processing, the point cloud dilated operator can expand the receptive field size with no increasing the number of parameters of the model. Then the dilated convolution operator, multi-geometric features encoding modules and U-Net architecture are combined to form a complete point cloud semantic segmentation model. Results Semantic3D is applied to verify the proposed algorithms. The results show that compared with the traditional neighborhood structure, the OA of dilated neighborhood structure is increased by 1.4%. Compared with the model that only uses coordinates as input, multi-geometric features encoding module is increased by 10.7%. The final model based on the two proposed algorithms get mIoU and OA are 91.2% and 68.2%, respectively. Conclusions The dilated neighborhood structure can effectively extract point cloud information in a larger range without increasing the number of model parameters. multi-geometric features encoding module can maximize the capture of shape information in the neighborhood.
  • [1] Hackel T, Wegner J D, Schindler K. Fast Semantic Segmentation of 3D Point Clouds With Strongly Varying Density[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 3(3):177-184
    [2] Castillo E, Liang J, Zhao H. Point Cloud Segmentation and Denoising Via Constrained Nonlinear Least Squares Normal Estimates[M]. Innovations for Shape Analysis. Springer, Berlin, Heidelberg, 2013
    [3] Vo A V, Truong-Hong L, Laefer D F, et al. Octree-Based Region Growing for Point Cloud Segmentation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 104(7):88-100
    [4] Andres M, Ignacio V, Jens B, et al. RangeNet++:Fast and Accurate Lidar Semantic Segmentation[C]. IEEE International Conference on Intelligent Robots and Systems, Macau, China, 2019
    [5] Maturana, Daniel, Sebastian Scherer. Voxnet:A 3d Convolutional Neural Network for Real-time Object Recognition[C]. IEEE International Conference on Intelligent Robots and Systems, Hamburg, Germany, 2015
    [6] Qi C, Su H, Mo K, et al. PointNet:Deep Learning on Point Sets for 3d Classification and Segmentation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017
    [7] Qi C, Yi L, Su H, et al. PointNet++:Deep Hierarchical Feature Learning on Point Sets in a Metric Space[C]. Advances in Neural Information Processing Systems, Long Beach, CA, USA, 2017
    [8] Yu, Fisher, and Vladlen Koltun. Multi-scale context aggregation by dilated convolutions[C]. International Conference on Learning Representations, San Juan, Puerto Rico, 2016
    [9] Jiang M, Wu Y, Zhao T, et al. Pointsift:a Sift-like Network Module for 3D Point Cloud Semantic Segmentation[J]. Arxiv Preprint, ArXiv:1807.00652, 2018
    [10] Li Y, Bu R, Sun M, et al. Pointcnn:Convolution on X-Transformed Points[C]. Advances in Neural Information Processing Systems, Montréal, Canada, 2018
    [11] Liang Z, Yang M, Li H, et al. 3D Instance Embedding Learning With a Structure-Aware Loss Function for Point Cloud Segmentation[J]. IEEE Robotics and Automation Letters, 2020, 5(3):4915-4922
    [12] Ronneberger O, Fischer P, Brox T. U-Net:Convolutional Networks for Biomedical Image Segmentation[C]. International Conference on Medical image computing and computer-assisted intervention, Munich, Germany, 2015
    [13] Zhao H, Jiang L, Fu C. PointWeb:Enhancing local neighborhood features for point cloud processing[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 2019
    [14] Thomas H, Qi C, Deschaud J, et al. Kpconv:Flexible and Deformable Convolution for Point Clouds[C]. Proceedings of the IEEE International Conference on Computer Vision, Seoul, South Korea, 2019
    [15] Hackel T, Savinov N, Ladicky L, et al. Semantic3D Net:a New Large-scale Point Cloud Classification Benchmark[C]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, (IV-1)W1:91-98
    [16] Wang F, Zhuang Y, Gu H, et al. OctreeNet. A Novel Sparse 3-D Convolutional Neural Network for Real-Time 3-D Outdoor Scene Analysis[J]. IEEE Transactions on Automation Science and Engineering, 2019, 17(2):735-747
    [17] Contreras J, Joachim D. Edge-Convolution Point Net for Semantic Segmentation of Large-Scale Point Clouds[C]. IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 2019
    [18] Thomas H, Goulette F, Deschaud J, et al. Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods[C]. International Conference on 3D Vision, Verona, Italy, 2018
    [19] Roynard X, Deschaud J, Goulett F. Classification of Point Cloud Scenes with Multiscale Voxel Deep Network[J]. ArXiv Preprint, ArXiv:1804.03583, 2018
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article Metrics

Article views(450) PDF downloads(25) Cited by()

Related
Proportional views

Semantic segmentation of point clouds using local geometric features and dilated neighborhoods

doi: 10.13203/j.whugis20200567
Funds:

The National Natural Science Foundation of China (42071454)

Abstract: Objectives Point cloud has no topological structure, current deep learning semantic segmentation algorithm is difficult to capture geometric features implied in irregular points. In addition, the point cloud is in three-dimensional space with a large amount of data size. If we blindly expand the captive field size during extract neighborhood information, it will increase the number of model parameters, which will make model training difficult. Methods To this end, we propose a point cloud semantic segmentation model based on the dilated convolution and combining elementary geometric features such as angle as the model input. First of all, during feature extraction, basic geometric features such as the relative coordinates, distance and angle between the centroid and the neighboring points are used as the model input to mine the geometric information. Secondly, in the process of building local neighborhoods, we expand the image dilated convolution operator to point cloud processing, the point cloud dilated operator can expand the receptive field size with no increasing the number of parameters of the model. Then the dilated convolution operator, multi-geometric features encoding modules and U-Net architecture are combined to form a complete point cloud semantic segmentation model. Results Semantic3D is applied to verify the proposed algorithms. The results show that compared with the traditional neighborhood structure, the OA of dilated neighborhood structure is increased by 1.4%. Compared with the model that only uses coordinates as input, multi-geometric features encoding module is increased by 10.7%. The final model based on the two proposed algorithms get mIoU and OA are 91.2% and 68.2%, respectively. Conclusions The dilated neighborhood structure can effectively extract point cloud information in a larger range without increasing the number of model parameters. multi-geometric features encoding module can maximize the capture of shape information in the neighborhood.

Xiang Xueyong, Li Guangyun, Wang Li, Zong Wenpeng, Lü Zhipeng, Xiang Fengzhuo. Semantic segmentation of point clouds using local geometric features and dilated neighborhoods[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20200567
Citation: Xiang Xueyong, Li Guangyun, Wang Li, Zong Wenpeng, Lü Zhipeng, Xiang Fengzhuo. Semantic segmentation of point clouds using local geometric features and dilated neighborhoods[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20200567
Reference (19)

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return