摘要
针对无人驾驶系统环境感知中的三维车辆检测精度低的问题,提出了一种基于激光雷达的三维车辆检测算法。通过统计滤波与随机抽样一致算法(Random Sample Consensus,RANSAC)实现地面点云分割,剔除激光雷达数据冗余点及离群点;改进3DSSD深度神经网络,利用融合采样提取点云中车辆语义信息与距离信息;根据特征信息对车辆位置进行二次调整生成中心点,使用三维中心分配器匹配中心点并生成三维车辆检测框。将KITTI数据集划为不同场景作为实验数据,对比多种三维车辆检测算法。实验结果表明:所提出的方法能够快速、准确的实现三维车辆检测,平均检测时间为0.12 s,检测精度最高可达89.72%。
This paper proposes a 3D vehicle detection algorithm for unmanned driving systems to solve the problem of low accuracy in environmental perception based on lidar.First,according to statistical fil⁃tering and a random sampling consensus algorithm(RANSAC),the ground point cloud segmentation was analyzed in order to eliminate the redundant points and outliers of the lidar data.Second,we im⁃proved the 3DSSD deep neural network to extract vehicle semantic and distance information from the point cloud through fusion sampling.According to the feature information,the candidate point position was adjusted twice to generate a center point.The 3D center-ness assignment strategy was adopted to cre⁃ate a 3D vehicle detection box.Finally,we divided the KITTI dataset into different scenes,to be used as experimental data,by comparing various current 3D vehicle detection algorithms.The experimental re⁃sults showed that the proposed method could detect vehicles quickly and accurately.The average detec⁃tion time was 0.12 s,and the highest detection accuracy was 89.72%.
作者
伍锡如
薛其威
WU Xiru;XUE Qiwei(College of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China)
出处
《光学精密工程》
EI
CAS
CSCD
北大核心
2022年第4期489-497,共9页
Optics and Precision Engineering
基金
国家自然科学基金项目(No.61863007)
广西自然科学基金项目(No.2020GXNSFDA238029)
桂林电子科技大学研究生教育创新计划项目(No.2020YCXS103,No.2021YCXS122,No.YCSW2020159)。
关键词
激光雷达
环境感知
无人驾驶系统
三维检测
lidar
environmental perception
unmanned driving systerm
3D detection