The Algorithm of Multi-Category Object Recognition in Road Scene Based on Voxel Network

被引：0
作者：
Gong Z. [1 ]
Wang G. [1 ]
Yu S. [1 ]
机构：
[1] College of Engineering, China Agriculture University, Beijing
来源：
Qiche Gongcheng/Automotive Engineering | 2021年 / 43卷 / 04期
关键词：
Lidar; Multi-category; Object recognition; Robustness; Voxel network;
D O I：
10.19562/j.chinasae.qcgc.2021.04.003
中图分类号：
学科分类号：
摘要：
The 3D object recognition based on lidar data is a key part of autopilot system. Voxel network is a good container for extracting point cloud features, but most of the research at present on object recognition based on voxel network focuses on single-category object. In order to meet the application demand of unmanned vehicle, it is urgent to carry out research on multi-category object recognition. In this paper, a multi-category object recognition algorithm based on voxel network is established and its performance is validated. The category label, confidence label and bounding borders regression values of the voxels around the tag are created by calculating the maximal intersection over union(IoU) among prior candidate borders of all categories simultaneously, which resolves the possible mismatch among the three predicted values. The test results indicate that the average recall of category prediction of the proposed multi-category object recognition algorithm is 88.6% and taking the IoU threshold of 0.5 as the correct one, the border regression is 84.8%. Compared with the single-category object recognition network, each category performs an obviously improved accuracy using the proposed algorithm, which proves that the multi-category object recognition algorithm effectively enhances the ability of characteristics learning, and contributes to the improvement of the robustness of the object recognition network. © 2021, Society of Automotive Engineers of China. All right reserved.
引用
收藏
页码：469 / 477
页数：8
相关论文
共 18 条
  • [1] JI Y M, CHEN Z Y, TIAN P H, Et al., A survey of 3D target detection methods in unmanned driving, Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 39, 4, pp. 72-79, (2019)
  • [2] LI Q J, ZHENG J Q, ZHOU H P, Et al., Point cloud recognition of street tree target based on variable-scale grid index and machine learning, Transactions of the Chinese Society for Agricultural Machinery, 49, 6, pp. 32-37, (2018)
  • [3] XU G Y, NIU H, GUO C Y, Et al., Research on target recognition and tracking based on 3D laser point cloud, Automotive Engineering, 42, 1, pp. 38-46, (2020)
  • [4] REDMON J, FARHAD A., YOLO9000: better, faster, stronger, IEEE Conference on Computer Vision and Pattern Recognition, (2017)
  • [5] REN S, HE K, GIRSHICK R, Et al., Faster r-cnn: towards real-time object detection with region proposal networks, IEEE Transactions on Pattern Analysis & Machine Intelligence, 39, 6, pp. 1137-1149, (2017)
  • [6] Qi C R, 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)
  • [7] XU K, YANG Z L, XU Y J, Et al., Residual blocks pointnet: a novel faster pointnet framework for segmentation and estimated pose, IEEE International Conference on Cloud Computing and Intelligence Systems, (2018)
  • [8] PAMPLONA J, MADRIGAL C, ESCALERA A., Pointnet evaluation for on-road object detection using a multi-resolution conditioning, Iberoamerican Congress, (2018)
  • [9] SHI W J, RAJKUMAR R., Point-GNN: graph neural network for 3D object detection in a point cloud, IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2020)
  • [10] CHEN X Z, MA H M, WAN J, Et al., Multi-view 3D object detection network for autonomous driving, IEEE Conference on Computer Vision and Pattern Recognition, (2017)
12