3D Object Detection Method for Autonomous Vehicle Based on Sparse Color Point Cloud

被引：0

作者：

Luo Y. ^{[1
]}

Qin H. ^{[1
]}

机构：

[1] School of Mechanical & Automotive Engineering, South China University of Technology, Guangzhou

来源：

Qiche Gongcheng/Automotive Engineering | 2021年 / 43卷 / 04期

关键词：

Lidar; Neural network; Object detection; Sensor fusion;

D O I：

10.19562/j.chinasae.qcgc.2021.04.006

中图分类号：

学科分类号：

摘要：

Aiming at the current problem of the low accuracy of point cloud segmentation and recognition algorithm in object detection of autonomous vehicle, a sparse color point cloud (SCPC) structure is proposed, which is formed by spatial matching and feature superposition of the image information collected by camera and the point cloud information acquired from lidar. Then, the improved PointPillars neural network algorithm is adopted to conduct operation on the fused SCPC. The results of experiment show that this method can achieve a major rise in average accuracy, compared with original PointPillars algorithm, especially the recognition accuracy of pedestrians and cyclists. The average accuracy of pedestrian and cyclist detections on 3D view under medium difficulty increases by 13.8% and 6.6% respectively, demonstrating the effectiveness of the method adopted. © 2021, Society of Automotive Engineers of China. All right reserved.

引用

页码：492 / 500

页数：8

共 28 条

[1]

HIMMELSBACH M, MUELLER A, LUTTEL T, Et al., LIDAR-based 3D object perception, Proceedings of 1st International Workshop on Cognition for Technical Systems, (2008)

[2]

CHARLES R Q, SU H, KAICHUN M, Et al., PointNet: deep learning on point sets for 3D classification and segmentation, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017)

[3]

YANG B, LIANG M, URTASUN R., Hdnet: Exploiting HD maps for 3D object detection, Conference on Robot Learning, (2018)

[4]

ZHOU Y, TUZEL O., VoxelNet: end-to-end learning for point cloud based 3D object detection, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2018)

[5]

YAN Y, MAO Y, LI B., Second: sparsely embedded convolutional detection, Sensors, 18, 10, (2018)

[6]

LANG A H, VORA S, CAESAR H, Et al., PointPillars: fast encoders for object detection from point clouds, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019)

[7]

CHEN X, MA H, WAN J, Et al., Multi-view 3D object detection network for autonomous driving, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017)

[8]

LIANG M, YANG B, WANG S, Et al., Deep continuous fusion for multi-sensor 3D object detection, European Conference on Computer Vision, (2018)

[9]

KU J, MOZIFIAN M, LEE J, Et al., Joint 3D proposal generation and object detection from view aggregation, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), (2018)

[10]

CHO H, SEO Y, KUMAR B V, Et al., A multi-sensor fusion system for moving object detection and tracking in urban driving environments, 2014 IEEE International Conference on Robotics and Automation (ICRA), (2014)

← 1 2 3 →