3D point cloud object detection method in view of voxel based on graph convolution network

被引：0

作者：

Zhao Y. ^{[1
]}

Arxidin A. ^{[1
]}

Chen R. ^{[1
]}

Zhou Y. ^{[1
]}

Zhang Q. ^{[1
]}

机构：

[1] School of Microelectronics, Tianjin University, Tianjin

来源：

Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering | 2021年 / 50卷 / 10期

关键词：

3D point cloud object detection; Graph convolution neural network; KITTI dataset; Lidar; Topological information;

D O I：

10.3788/IRLA20200500

中图分类号：

学科分类号：

摘要：

In view of the sparsity and spatial discrete distribution of lidar point cloud, a graph convolution feature extraction module was designed by combining voxel partition and graph representation, and a 3D lidar point cloud object detection algorithm in view of voxel based graph convolution neural network was proposed. By eliminating the computational redundancy of the traditional 3D convolution neural network, this method not only improved the object detection ability of the network, but also improved the analysis ability of the point cloud topology information. Compared with the baseline network, the detection performance of vehicle, pedestrian and cyclist 3D object detection and bird's eye view object detection tasks in KITTI public dataset were improved greatly, especially improved with 13.75% precision in 3D object detection task of vehicle at maximal. Experimental results show that the proposed method improves the detection performance of the network and the learning ability of data topological relationship via graph convolution feature extraction module, which provides a new method for 3D point cloud object detection task. © 2021, Editorial Board of Journal of Infrared and Laser Engineering. All right reserved.

引用

共 11 条

[1] Zhang Nan, Sun Jianfeng, Jiang Peng, Et al., Pose estimation algorithms for lidar scene based on point normal vector, Infrared and Laser Engineering, 49, 1, (2020)
[2] Xia Xianzhao, Zhu Shixian, Zhou Yiyao, Et al., LiDAR K-means clustering algorithm based on threshold, Journal of Beijing University of Aeronautics and Astronautics, 46, 1, pp. 115-121, (2020)
[3] Zhou Y, Tuzel O., Voxelnet: End-to-end learning for point cloud based3d object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490-4499, (2018)
[4] Yan Yan, Mao Yuxing, Bo Li, Second: Sparsely embedded convolutional detection, Sensors, 18, 10, (2018)
[5] Qi C R, Yi L, Su H, Et al., Pointnet++: Deep hierarchical feature learning on point sets in a metric space, Advances in Neural Information Processing Systems, pp. 5099-5108, (2017)
[6] Shi Weijing, Raj Rajkumar, Point-gnn: Graph neural network for 3d object detection in a point cloud, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1711-1719, (2020)
[7] Kipe Thomas N, Max Welling, Semi-supervised classification with graph convolutional networks, 1609, (2016)
[8] Xue Shan, Zhang Zhen, Lu Qiongying, Et al., Image recognition method of anti UAV system based on convolutional neural network, Infrared and Laser Engineering, 49, 7, (2020)
[9] Geiger A, Lenz P, Urtasun R., Are we ready for autonomous driving? the kitti vision benchmark suite, 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354-3361, (2012)
[10] Chen Xiaozhi, Ma Huimin, Wan Ji, Et al., Multi-view 3d object detection network for autonomous driving, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907-1915, (2017)

← 1 2 →