Bilevel Convolutional Neural Networks for 3D Semantic Segmentation Using Large-scale LiDAR Point Clouds in Complex Environments

被引：0

作者：

Jiang T. ^{[1
,2
]}

Yang B. ^{[1
,2
]}

Zhou Y. ^{[1
,2
]}

Zhu R. ^{[1
,2
]}

Hu Z. ^{[1
,2
]}

Dong Z. ^{[1
,2
]}

机构：

[1] State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan

[2] Engineering Research Center for Spatiotempoal Data Smart Acquisition and Application, Ministry of Education, Wuhan University, Wuhan

来源：

Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | 2020年 / 45卷 / 12期

基金：

中国国家自然科学基金; 中国博士后科学基金;

关键词：

Bilevel CNN; Feature aggregation; Point cloud; Semantic segmentation; Supervoxel;

D O I：

10.13203/j.whugis20200081

中图分类号：

学科分类号：

摘要：

In large-scale road environment, point-based methods require dynamic calculations, and voxel-based methods often lose a lot of information when balancing resolution and performance. To overcome the drawbacks of the above two classical methods, this paper proposes a general network architecture that combines bi-level convolution and dynamic graph edge convolution optimization for multi-object recognition of large-scale road scenes. The framework integrates the convolution operations of two different domains of points and supervoxels to avoid redundant calculations and storage of spatial information in the network. Coupled with the dynamic graph edge convolution optimization, our model enables it to process large-scale point clouds end-to-end at once. Our method was tested and evaluated on different datasets. The experimental results show that our method can achieve higher accuracy in complex road scenes, which is superior to the existing advanced methods. © 2020, Editorial Board of Geomatics and Information Science of Wuhan University. All right reserved.

引用

页码：1942 / 1948

页数：6

共 27 条

[1] Yang Bisheng, Liang Fuxun, Huang Ronggang, Progress, Challenges and Perspectives of 3D LiDAR Point Cloud Processing, Acta Geodaetica et Cartographica Sinica, 46, 10, pp. 1509-1516, (2017)
[2] Yang Bisheng, Dong Zhen, Progress and Perspective of Point Cloud Intelligence, Acta Geodaetica et Cartographica Sinica, 48, 12, pp. 1575-1585, (2019)
[3] Wang Y, Jiang T, Yu M, Et al., Semantic-Based Building Extraction from LiDAR Point Clouds Using Contexts and Optimization in Complex Environment[J], Sensors, 20, 12, pp. 3-386, (2020)
[4] Luo Z, Li J, Xiao Z, Et al., Learning High-Level Features by Fusing Multi-view Representation of MLS Point Clouds for 3D Object Recognition in Road Environments, ISPRS J Photogramm Remote Sens, 150, pp. 44-58, (2019)
[5] Dong Zhen, Feature Description and 3D Object Extraction from Large-scale Laser Scanning Point Clouds, (2018)
[6] Xiong Hanjiang, Zheng Xianwei, Ding Youli, Et al., Semantic Segmentation of Indoor 3D Point Cloud Model Based on 2D-3D Semantic Transfer, Geomatics and Information Science of Wuhan University, 43, 12, pp. 2303-2309, (2018)
[7] Tchapmi L P, Choy C B, Armeni I, Et al., Segcloud: Semantic Segmentation of 3D Point Clouds, International Conference on 3D Vision, (2017)
[8] Liu Z, Tang H, Lin Y, Et al., Point-Voxel CNN for Efficient 3D Deep Learning, Conference and Workshop on Neural Information Processing Systems, (2019)
[9] Qi C, Su H, Mo K, Et al., PointNet: Deep Learning on Point Sets for 3D Classiﬁcation and Segmentation, IEEE Conference on Computer Vision and Pattern Recognition, (2017)
[10] Hu Q, Yang B, Xie L, Et al., RandLA-Net: Efﬁcient Semantic Segmentation of Large-scale Point Clouds, IEEE Conference on Computer Vision and Pattern Recognition, (2020)

← 1 2 3 →