OverlapTransformer：一种用于基于LiDAR的地点识别的高效且旋转不变的Transformer网络
OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition
AI总结：
本文提出OverlapTransformer，一种利用距离图像和Transformer实现偏航角不变、每帧少于2毫秒的轻量LiDAR地点识别网络，并在KITTI、Ford Campus及新长期数据集上验证其先进性能。
摘要：
地点识别是在复杂环境和变化条件下运行的自主导航车辆的一项重要能力。它是SLAM中的回环闭合或全局定位等任务的关键组成部分。在本文中，我们解决基于自主车辆记录的3D LiDAR扫描的地点识别问题。我们提出了一种新颖的轻量级神经网络，利用LiDAR传感器的距离图像表示来实现每帧少于2毫秒的快速执行。我们设计了一种利用Transformer网络的偏航角不变架构，这提升了我们方法的地点识别性能。我们在KITTI和Ford Campus数据集上评估了我们的方法。实验结果表明，与最先进的方法相比，我们的方法能够有效检测回环闭合，并且在不同环境中具有良好的泛化能力。为了评估长期地点识别性能，我们提供了一个新颖的数据集，其中包含由移动机器人在不同时间于重复地点记录的LiDAR序列。我们方法的实现和数据集发布于此：https://github.com/haomo-ai/OverlapTransformer
英文摘要：
Place recognition is an important capability for autonomously navigating vehicles operating in complex environments and under changing conditions. It is a key component for tasks such as loop closing in SLAM or global localization. In this paper, we address the problem of place recognition based on 3D LiDAR scans recorded by an autonomous vehicle. We propose a novel lightweight neural network exploiting the range image representation of LiDAR sensors to achieve fast execution with less than 2 ms per frame. We design a yaw-angle-invariant architecture exploiting a transformer network, which boosts the place recognition performance of our method. We evaluate our approach on the KITTI and Ford Campus datasets. The experimental results show that our method can effectively detect loop closures compared to the state-of-the-art methods and generalizes well across different environments. To evaluate long-term place recognition performance, we provide a novel dataset containing LiDAR sequences recorded by a mobile robot in repetitive places at different times. The implementation of our method and dataset are released here: https://github.com/haomo-ai/OverlapTransformer
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。
