LiDAR Odometry by Deep Learning-based Feature Points with Two-step Pose Estimation

Liu, Tianyi; Wang, Yan; niu, xiaoji; Le, Chang; Zhang, Tisheng; Liu, Jingnan

doi:10.36227/techrxiv.17212967.v1

LiDAR Odometry by Deep Learning-based Feature Points with Two-step Pose Estimation.pdf (7.88 MB)

LiDAR Odometry by Deep Learning-based Feature Points with Two-step Pose Estimation

preprint

posted on 2021-12-20, 19:58 authored by Tianyi LiuTianyi Liu, Yan WangYan Wang, xiaoji niu, Chang Le, Tisheng Zhang, Jingnan Liu

KITTI dataset is collected from three types of environments, i.e., country, urban and highway The types of feature point cover a variety of scenes. The KITTI dataset provides 22 sequences of LiDAR data. 11 sequences of them from sequence 00 to sequence 10 are "training" data. The training data are provided with ground truth translation and rotation. In addition, field experiment data is collected by low-resolution LiDAR, VLP-16 in Wuhan Research and Innovation Center.