Place recognition gives a SLAM system the ability to correct cumulative errors. Unlike images that contain rich texture features, point clouds are almost pure geometric information which makes place recognition based on point clouds challenging. Existing works usually encode low-level features such as coordinate, normal, reflection intensity, etc., as local or global descriptors to represent scenes. Besides, they often ignore the translation between point clouds when matching descriptors. Different from most existing methods, we explore the use of high-level features, namely semantics, to improve the descriptor's representation ability. Also, when matching descriptors, we try to correct the translation between point clouds to improve accuracy. Concretely, we propose a novel global descriptor, Semantic Scan Context, which explores semantic information to represent scenes more effectively. We also present a two-step global semantic ICP to obtain the 3D pose (x, y, yaw) used to align the point cloud to improve matching performance. Our experiments on the KITTI dataset show that our approach outperforms the state-of-the-art methods with a large margin. Our code is available at: https://github.com/lilin-hitcrt/SSC.
翻译:定位识别系统能够纠正累积错误。 与含有丰富纹理特征的图像不同, 点云几乎是纯几何信息, 使得基于点云的定位具有挑战性。 现有的作品通常将低层次特征( 如坐标、 正常、 反射强度等) 编码为本地或全球描述器, 以代表场景。 此外, 在匹配描述符时, 它们往往忽略点云之间的翻译。 与大多数现有方法不同, 我们探索使用高点云( 语义学) 来提高描述符的表达能力。 另外, 在匹配描述符时, 我们试图纠正点云之间的翻译, 以提高准确性。 具体地说, 我们提出一个新的全球描述符、 和 映射 环境, 以更有效地代表场景。 我们还提出了一个两步全球语义化比较方案, 以获得 3D 方形( x, y, yaw) 来调整点云来改进匹配性能。 我们在 KITTI 数据集上进行的实验显示, 我们的方法超越了 状态- art 方法与大边距 。 我们的代码可以在 http:// SSCL/ sqr 。 。 。 我们的代码可以在 。