We propose an extension to the segment-based global localization method for LiDAR SLAM using descriptors learned considering the visual context of the segments. A new architecture of the deep neural network is presented that learns the visual context acquired from synthetic LiDAR intensity images. This approach allows a single multi-beam LiDAR to produce rich and highly descriptive location signatures. The method is tested on two public datasets, demonstrating an improved descriptiveness of the new descriptors, and more reliable loop closure detection in SLAM. Attention analysis of the network is used to show the importance of focusing on the broader context rather than only on the 3-D segment.

中文翻译：

---

激光雷达强度​​图像对 3D SLAM 中基于分段的环路闭合的描述能力

我们建议使用考虑到片段的视觉上下文学习的描述符来扩展基于片段的全局定位方法，用于 LiDAR SLAM。提出了一种新的深度神经网络架构，可以学习从合成 LiDAR 强度图像中获取的视觉上下文。这种方法允许单个多光束 LiDAR 产生丰富且高度描述性的位置签名。该方法在两个公共数据集上进行了测试，证明了新描述符的改进描述性，以及更可靠的 SLAM 闭环检测。网络的注意力分析用于表明关注更广泛的背景而不是仅关注 3-D 部分的重要性。