Closed yinhaosen closed 1 year ago
Hi, thanks for your interest in our work. The ground-truth data for indoor sequences, where MOCAP and GNSS/RTK are unavailable, are generated by NDT matching real-time pointcloud with a High-definition map. We explained how we build an HD map with solid-state lidar in the preprint paper here:https://arxiv.org/abs/2210.00812. You will get more details on how we built this dataset from the paper.
I didn't find which slam did you use to generate ground-truth for each dataset?