All Title Author
Keywords Abstract

Publish in OALib Journal
ISSN: 2333-9721
APC: Only $99


Relative Articles


Point Cloud Segmentation Based on Neighboring Information Encoding

DOI: 10.12677/HJDM.2023.132019, PP. 194-201

Keywords: 点云,语义分割,局部特征编码,邻域信息编码,Point Cloud, Semantic Segmentation, Local Feature Encoding, Neighboring Feature Encoding

Full-Text   Cite this paper   Add to My Lib


How to take full advantages of point cloud is an urgent task due to the universal application of point cloud data format. Superb semantic segmentation of point cloud can be the solid basis of subsequent task of point cloud application. For semantic segmentation task, both the global and local feature play significant role. Based on the basic truth that the better the local feature, the better the segmentation performance, the neighboring feature encoding module is elaborated, this module aims to make the most of direction feature between center point and its neighboring points during the local feature extraction process. Original input feature is considered as concatenation of spatial information and plus feature (e.g.: RGB and depth), the plus feature will be handled by shared MultiLayer Perceptron, the spatial information will be sent to proposed neighboring feature encoding module to capture neighboring feature of every center point, output of two part will be concatenated as final local feature. From the perspective of result of experiment on public dataset S3DIS, the proposed model has excellent performance on feature extraction, its performance excels SOTA baseline model with 1.8% mIoU.


[1]  Lawin, F.J., Danelljan, M., Tosteberg, P., et al. (2017) Deep Projective 3D Semantic Segmentation. In: Felsberg, M., Heyden, A. and Kruger, N., Eds., Computer Analysis of Images and Patterns, Springer International Publishing, Cham, 95-107.
[2]  Long, J., et al. (2015) Fully Convolutional Networks for Semantic Segmentation. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 3431-3440.
[3]  Boulch, A., Saux, B.L. and Audebert, N. (2017) Unstructured Point Cloud Semantic La-beling Using Deep Segmentation Networks. Proceedings of the Workshop on 3D Object Retrieval, 3, 17-24.
[4]  Iandola, F.N., Han, S., Moskewicz, M.W., et al. (2016) SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and < 0.5 MB Model Size.
[5]  Wu, B., Wan, A., Yue, X., et al. (2017) Squeezeseg: Convolutional Neural Nets with Recurrent crf for Real-Time 290 Road-Object Segmentation from 3d LiDAR Point Cloud. 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, 21-25 May 2018, 1887-1893.
[6]  Wu, B., Zhou, X., Zhao, S., et al. (2018) SqueezeSegV2: Im-proved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud. 2019 International Conference on Robotics and Automation (ICRA), Montreal, 20-24 May 2019, 4376-4382.
[7]  Milioto, A., Vizzo, I., Behley, J., et al. (2019) RangeNet ++: Fast and Accurate LiDAR Semantic Segmentation. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, 3-8 November 2019, 4213-4220.
[8]  Huang, J. and You, S. (2016) Point Cloud Labeling Using 3D Convolutional Neural Network. 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, 4-8 December 2016, 2670-2675.
[9]  Tchapmi, L., Choy, C., Armeni, I., et al. (2017) Segcloud: Semantic Segmentation of 3D Point Clouds. 2017 International Conference on 3D Vision (3DV), Qingdao, 10-12 October 2017, 537-547.
[10]  Rethage, D., Wald, J., Sturm, J., et al. (2018) Fully-Convolutional Point Networks for Large-Scale Point Clouds. 15th European Conference, Munich, 8-14 September 2018, 625-640.
[11]  Meng, H.-Y., Gao, L., Lai, Y.-K., et al. (2019) Vv-net: Voxel Vae Net with Group Convolutions for Point Cloud Segmentation. 2019 IEEE/CVF International Conference on Com-puter Vision (ICCV), Seoul, 27 October-2 November 2019, 8499-8507.
[12]  Dai, A., Ritchie, D., Bokeloh, M., et al. (2018) ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans. 2018 IEEE/CVF Conference on Computer Vi-sion and Pattern Recognition, Salt Lake City, 18-23 June 2018, 4578-4587.
[13]  Qi, C.R., Su, H., Mo, K., et al. (2017) PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 77-85.
[14]  Qi, C.R., Li, Y., Hao, S., et al. (2017) PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. Proceedings of the 31st International Conference on Neural Infor-mation Processing Systems, Long Beach, 4-9 December 2017, 5105-5114.
[15]  Hu, Q., Yang, B., Xie, L., Rosa, S., et al. (2020) RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 13-19 June 2020, 11105-11114.
[16]  Fan, S., Dong, Q., Zhu, F., et al. (2021) SCF-Net: Learning Spatial Contextual Features for Large Scale Point Cloud Segmentation. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 14499-14508.
[17]  Lu, T., Wang, L.M. and Wu, G.S. (2021) CGA-Net: Cate-gory Guided Aggregation for Point Cloud Semantic Segmentation. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 11688-11697.
[18]  Jiang, M.Y., Wu, Y.R., Zhao, T.Q., et al. (2018) PointSIFT: A SIFT-Like Network Module for 3D Point Cloud Semantic Segmentation. arXiv:1807.00652.
[19]  Engelmann, F., Kontogianni, T., Schult, J., et al. (2019) Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds. Computer Vision—ECCV 2018 Workshops, Munich, 8-14 September 2018, 395-409.
[20]  Zhao, H., Jiang, L., Fu, C.W., et al. (2019) PointWeb: En-hancing Local Neighborhood Features for Point Cloud Processing. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 5560-5568.


comments powered by Disqus

Contact Us


WhatsApp +8615387084133

WeChat 1538708413