融合球坐标与激光强度，提升点云场景识别鲁棒性
MinkUNeXt-SI: Improving point cloud-based place recognition including spherical coordinates and LiDAR intensity
- 输入点云提取球坐标与归一化强度，增强几何与物理特征
- 基于Minkowski卷积与U-Net结构，实现高精度场景匹配
- 在多环境数据集上表现超越现有方法，适合自动驾驶定位
在自动驾驶导航系统中，场景识别是保障安全运行的关键。但该问题极具挑战，需在季节变化、天气差异等条件下保持准确性，并具备跨环境泛化能力。本文提出MinkUNeXt-SI方法，从激光雷达点云出发，对每个点进行球坐标提取与强度值归一化（0~1范围），生成鲁棒的场景识别描述符。采用结合Minkowski卷积与带跳跃连接的U-Net架构的深度学习模型。实验表明，该方法性能达到并超越当前最优水平，且在多个不同数据集上均表现出良好泛化能力。此外，我们构建了一个自定义数据集并用于评估，结果同样优异。代码与数据集均已公开，支持复现。
原文摘要 · Abstract (English)
In autonomous navigation systems, the solution of the place recognition problem is crucial for their safe functioning. But this is not a trivial solution, since it must be accurate regardless of any changes in the scene, such as seasonal changes and different weather conditions, and it must be generalizable to other environments. This paper presents our method, MinkUNeXt-SI, which, starting from a LiDAR point cloud, preprocesses the input data to obtain its spherical coordinates and intensity values normalized within a range of 0 to 1 for each point, and it produces a robust place recognition descriptor. To that end, a deep learning approach that combines Minkowski convolutions and a U-net architecture with skip connections is used. The results of MinkUNeXt-SI demonstrate that this method reaches and surpasses state-of-the-art performance while it also generalizes satisfactorily to other datasets. Additionally, we showcase the capture of a custom dataset and its use in evaluating our solution, which also achieves outstanding results. Both the code of our solution and the runs of our dataset are publicly available for reproducibility purposes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。