OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios
This addresses the problem of robust place recognition in challenging long-term outdoor conditions for robotics and autonomous systems, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of oriented place recognition with 3D LiDAR scans in outdoor scenarios, introducing a method that uses a CNN with triplet loss and hard-negative mining to extract descriptors for retrieval and yaw estimation, and demonstrates that it outperforms state-of-the-art approaches on NCLT and KITTI datasets.
We introduce a novel method for oriented place recognition with 3D LiDAR scans. A Convolutional Neural Network is trained to extract compact descriptors from single 3D LiDAR scans. These can be used both to retrieve near-by place candidates from a map, and to estimate the yaw discrepancy needed for bootstrapping local registration methods. We employ a triplet loss function for training and use a hard-negative mining strategy to further increase the performance of our descriptor extractor. In an evaluation on the NCLT and KITTI datasets, we demonstrate that our method outperforms related state-of-the-art approaches based on both data-driven and handcrafted data representation in challenging long-term outdoor conditions.