基于点云稀疏语义特征的智能网联汽车协同感知配准算法

A cooperative perception registration algorithm for intelligent and connected vehicles based on sparse semantic features

针对道路场景下多智能网联汽车协同感知问题,本文提出一种基于点云稀疏语义特征的智能网联汽车协同感知配准算法。所提算法旨在通过点云集成配准扩展智能网联汽车感知范围,进而实现智能网联汽车协同感知。首先,在道路语义特征基础上进行几何特征提取进而得到点云稀疏语义特征。其次,计算道路语义特征点云间的角度偏差以提供配准初值,并将点云语义信息作为配准约束条件实现全局语义集成配准。实验表明所提算法有效扩大了多智能网联汽车协同感知范围,提高了多点云集成配准的精度与鲁棒性。与当前主流算法JRMPC相比,本文所提算法配准精度提高了2.45%。

To address the problem of cooperative perception for multiple intelligent and connected vehicles(ICVs)in road scenarios,this article proposes a cooperative perception registration algorithm for ICVs,which is based on sparse semantic features.The proposed algorithm aims to extend the perception range of ICVs by point cloud ensemble registration.Therefore,the cooperative perception for ICVs is achieved.Firstly,the sparse semantic features are obtained by geometric feature extraction based on road semantic features.Secondly,the angle deviation among the road semantic features is calculated to provide the initial registration value.The point cloud semantic information is used as the registration constraint condition to realize the global semantic ensemble registration.The experiments show that the proposed algorithm effectively expands the cooperative sensing range of multi-ICVs.The accuracy and robustness of multipoint cloud ensemble registration are enhanced.Compared with the current mainstream algorithm JRMPC,the registration accuracy of the proposed algorithm is improved by 2.45%.