PinNet用关键点和几何注意力提升激光雷达回环检测精度
PinNet: Keypoint-Aware Learned Local Descriptors with Geometric Embedding for Loop Closure in LiDAR SLAM
- 基于关键点与几何自注意力生成可区分的局部描述子
- 在多数据集上实现高精度位姿估计与单次定位成功
- 适合需要精确回环检测的激光雷达导航系统
回环检测对于在大规模环境中减少漂移、构建全局一致地图至关重要。然而，仅依靠激光雷达等传感器的几何信息进行可靠回环检测仍具挑战性，主要源于难以构建具有区分性的几何特征。本文提出PinNet，一种从点云生成局部几何描述子的神经网络，用于场景识别与扫描配准。PinNet结合了关键点检测网络与描述子生成网络，并引入基于平面的几何自注意力模块，建模关键点间的空间关系，从而增强描述子在回环检测与点云配准中的区分能力。该方法在多种不同激光雷达传感器采集的多个数据集上进行了全面评估。实验结果表明，PinNet在场景识别方面表现优异，能实现精确的相对位姿估计，并在不同环境下成功完成单次定位。
原文摘要 · Abstract (English)
Loop closure is essential to reduce drift and build globally consistent maps in large-scale environments. However, reliable loop closure with only geometric information from, e.g., a LiDAR sensor, remains challenging due to the difficulty of constructing discriminative geometric features. We present PinNet, a neural network that produces local geometric descriptors from point clouds for place recognition and scanto-scan registration. PinNet incorporates a neural network that generates keypoints and their corresponding descriptors, together with a plane-based geometric self-attention module that models inter-keypoint spatial relationships to enhance descriptor discriminability for loop-closure detection and point-cloud registration. The approach is comprehensively evaluated on multiple datasets collected with different LiDAR sensors. Experimental results demonstrate strong place-recognition performance, precise relative pose estimation, and successful single-shot localization in different environments.
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。