Semantic Segmentation Method of Point Cloud in Automatic Driving Scene Based on Self-attention Mechanism

被引：0
|
作者：
Wang D. [1 ]
Shang H. [1 ]
Cao J. [1 ]
Wang T. [2 ]
Xia X. [1 ]
Han Y. [1 ]
机构：
[1] School of Automotive Engineering, Harbin Institute of Technology, Weihai
[2] Army Academy of Armored Forces, Beijing
来源：
Qiche Gongcheng/Automotive Engineering | 2022年 / 44卷 / 11期
关键词：
large-scale point cloud; self-attention mechanism; semantic segmentation;
D O I：
10.19562/j.chinasae.qcgc.2022.11.004
中图分类号：
学科分类号：
摘要：
Semantic segmentation of vehicle lidar scene point cloud is the basic work of automatic driving environment perception. In view of the insufficient ability to extract local features and difficulty to capture the global context information of the existing processing method of point cloud in large-scale automatic driving scene，the local and global self-attention encoders are designed based on the self-attention mechanism and the feature aggregation module is built for feature extraction. The experimental results show that compared with RandLA-Net，also adopting local feature aggregation，the method proposed can increase the MIoU by 5.7 percentage points on SemanticKITTI dataset，and adding local self-attention encoder also raises the segmentation accuracy of small targets such as vehicles and pedestrians by more than 2 percentage points. © 2022 SAE-China. All rights reserved.
引用
收藏
页码：1656 / 1664
页数：8
相关论文
共 30 条
  • [1] JIANG F, HAO H Z，, Et al., Survey on content-based image segmentation methods［J］, Journal of Software, 28, 1, pp. 160-183, (2017)
  • [2] DARRELL T., Fully convolutional networks for semantic segmentation［C］, Proceedings of the IEEE Conference on Computer Vision And Pattern Recognition, pp. 3431-3440, (2015)
  • [3] GUO Y, Et al., Deep learning for 3D point clouds：a survey［J］, IEEE transactions on Pattern Analysis and Machine Intelligence, 43, 12, pp. 4338-4364, (2020)
  • [4] BROX T., U-net：convolutional networks for biomedical image segmentation［C］, International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234-241, (2015)
  • [5] Mask r-cnn［C］, Proceedings of the IEEE International Conference on Computer Vision, pp. 2961-2969, (2017)
  • [6] CHEN L C，, PAPANDREOU G, KOKKINOS I, Et al., Deeplab：semantic image segmentation with deep convolutional nets，atrous convolution，and fully connected CRFS［J］, IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 4, pp. 834-848, (2017)
  • [7] Multi-view convolutional neural networks for 3D shape recognition［C］, Proceedings of the IEEE International Conference on Computer Vision, pp. 945-953, (2015)
  • [8] Squeezeseg：convolutional neural nets with recurrent crf for real-time road-object segmentation from 3D lidar point cloud［C］, 2018 IEEE International Conference on Robotics and Automation（ICRA）, pp. 1887-1893, (2018)
  • [9] SqueezeNet：AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size［J］, (2016)
  • [10] 2019 International Conference on Robotics and Automation （ICRA）, pp. 4376-4382, (2019)
123