Place recognition is a key module for long-term SLAM systems. Current LiDAR-based place recognition methods are usually based on representations of point clouds such as unordered points or range images. These methods achieve high recall rates of retrieval, but their performance may degrade in the case of view variation or scene changes. In this work, we explore the potential of a different representation in place recognition, i.e. bird's eye view (BEV) images. We observe that the structural contents of BEV images are less influenced by rotations and translations of point clouds. We validate that, without any delicate design, a simple VGGNet trained on BEV images achieves comparable performance with the state-of-the-art place recognition methods in scenes of slight viewpoint changes. For more robust place recognition, we design a rotation-invariant network called BEVPlace. We use group convolution to extract rotation-equivariant local features from the images and NetVLAD for global feature aggregation. In addition, we observe that the distance between BEV features is correlated with the geometry distance of point clouds. Based on the observation, we develop a method to estimate the position of the query cloud, extending the usage of place recognition. The experiments conducted on large-scale public datasets show that our method 1) achieves state-of-the-art performance in terms of recall rates, 2) is robust to view changes, 3) shows strong generalization ability, and 4) can estimate the positions of query point clouds. Source code will be made publicly available at https://github.com/zjuluolun/BEVPlace.

翻译：地点识别是长期SLAM系统的关键模块。当前的基于激光雷达的地点识别方法通常基于诸如无序点云或距离图像等点云表示。这些方法在检索方面达到了高召回率，但在视角变化或场景变化的情况下性能可能会下降。本文探索了不同表示方法在地点识别中的潜力，即鸟瞰图图像。我们观察到，鸟瞰图图像的结构内容受点云旋转和平移的影响较小。我们验证了，无需任何精细设计，仅使用在鸟瞰图上训练的简单VGGNet，即可在轻微视角变化的场景中达到与最先进地点识别方法相当的性能。为了实现更鲁棒的地点识别，我们设计了一种旋转不变网络，称为BEVPlace。我们使用分组卷积从图像中提取旋转等变局部特征，并利用NetVLAD进行全局特征聚合。此外，我们观察到鸟瞰图特征之间的距离与点云的几何距离相关。基于这一发现，我们开发了一种估计查询点云位置的方法，扩展了地点识别的应用场景。在大型公开数据集上进行的实验表明，我们的方法1）在召回率方面达到了最先进性能，2）对视角变化具有鲁棒性，3）展现了强泛化能力，4）能估计查询点云的位置。源代码将公开发布于https://github.com/zjuluolun/BEVPlace。