基于车载激光雷达BEV旋转不变特征的城市道路场景地点识别与定位方法OA
Place Recognition and Localization Method for Urban Road Scenes Based on Vehicle-Mounted LiDAR BEV Rotation-Invariant Features
面向城市道路场景自主定位任务,提出一种基于车载激光雷达鸟瞰图(BEV)旋转不变特征的地点识别与定位方法.首先,将车载激光雷达三维点云通过归一化点密度方法转换为二维BEV图像;其次,分析激光雷达BEV平移与旋转不变性特征,设计旋转平移等变的BEV图像局部特征提取网络(RE-Net)和全局特征聚合方法;最后,实现基于车载激光雷达BEV旋转不变特征的城市道路场景地点识别与定位.实验结果表明,该方法在NCLT上的Recall@1相比主流方法至少提升5个百分点,在自采集城市广角激光雷达数据集上Recall@1高于90%,并证明了训练数据多样性比数据规模更能提升模型泛化能力.
A place recognition and localization method based on vehicle-mounted LiDAR bird's-eye view(BEV)rotation-invariant features is proposed for autonomous positioning in urban road scenes.Firstly,three-dimensional point clouds acquired by vehicle-mounted LiDAR are transformed into two-di-mensional BEV images through a normalized point-density representation.Subsequently,the translation and rotation invariance properties of LiDAR BEV features are analyzed.On this basis,a rotation-transla-tion-equivariant local feature extraction network for BEV images,termed rotation equivariant local feature extraction network(RE-Net),is designed,together with a global feature aggregation strategy.Finally,place recognition and localization in urban road scenes are performed based on the rotation-invariant BEV fea-tures extracted from vehicle-mounted LiDAR data.The experimental results show that the proposed method improves Recall@1 on the NCLT dataset by at least 5 percentage points compared with main-stream methods,achieves a Recall@1 of over 90%on the self-collected urban wide-angle LiDAR dataset,and demonstrates that training data diversity contributes more than data scale to model generalization.
周梦鸽;曹雪峰;何静怡
信息工程大学,河南 郑州 450001信息工程大学,河南 郑州 450001信息工程大学,河南 郑州 450001
天文与地球科学
地点识别激光雷达鸟瞰图旋转不变城市道路场景
place recognitionLiDARbird's-eye viewrotation-invarianceurban road scenes
《信息工程大学学报》 2026 (4)
391-398,8
评论