arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.01665cs.CVcs.RO
收藏

CVTNet: 一种用于LiDAR数据地点识别的跨视图Transformer网络

CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data

Beijing Institute of Technology(北京理工大学);National University of Defense Technology(国防科技大学)

Junyi Ma, Guangming Xiong, Jingyi Xu, Xieyuanli Chen

AI总结:

针对现有LiDAR地点识别方法未充分利用多视角信息的问题,提出跨视图Transformer网络CVTNet,融合距离图像视图与鸟瞰视图生成偏航角不变全局描述符,在多数据集上性能优于现有方法且具备实时性。

摘要:

基于LiDAR的地点识别(LPR)是自动驾驶车辆在GPS拒止环境中识别曾到访地点的核心组件之一。现有大多数LPR方法对输入点云采用常规表征,未考虑不同视角,可能无法充分挖掘LiDAR传感器的信息。本文提出一种基于跨视图Transformer的网络CVTNet,用于融合从LiDAR数据生成的距离图像视图(RIVs)和鸟瞰视图(BEVs)。该网络通过视图内Transformer提取单视图内部的关联,通过视图间Transformer提取两种不同视图之间的关联。在此基础上,本文提出的CVTNet可端到端在线为每帧激光扫描生成偏航角不变的全局描述符,并通过当前查询扫描与预构建数据库之间的描述符匹配检索曾到访的地点。我们在三种采用不同传感器配置和环境条件采集的数据集上评估了所提方法。实验结果表明,该方法优于当前最优的LPR方法,对视角变化和长时间跨度具有强鲁棒性。此外,该方法具备良好的实时性能,运行速度快于典型的LiDAR帧速率。该方法的实现已在以下地址开源:https://github.com/BIT-MJY/CVTNet。

英文摘要:

LiDAR-based place recognition (LPR) is one of the most crucial components of autonomous vehicles to identify previously visited places in GPS-denied environments. Most existing LPR methods use mundane representations of the input point cloud without considering different views, which may not fully exploit the information from LiDAR sensors. In this paper, we propose a cross-view transformer-based network, dubbed CVTNet, to fuse the range image views (RIVs) and bird's eye views (BEVs) generated from the LiDAR data. It extracts correlations within the views themselves using intra-transformers and between the two different views using inter-transformers. Based on that, our proposed CVTNet generates a yaw-angle-invariant global descriptor for each laser scan end-to-end online and retrieves previously seen places by descriptor matching between the current query scan and the pre-built database. We evaluate our approach on three datasets collected with different sensor setups and environmental conditions. The experimental results show that our method outperforms the state-of-the-art LPR methods with strong robustness to viewpoint changes and long-time spans. Furthermore, our approach has a good real-time performance that can run faster than the typical LiDAR frame rate. The implementation of our method is released as open source at: https://github.com/BIT-MJY/CVTNet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑